diff --git "a/baseline/shortcut_baseline_euler.txt" "b/baseline/shortcut_baseline_euler.txt" new file mode 100644--- /dev/null +++ "b/baseline/shortcut_baseline_euler.txt" @@ -0,0 +1,2187 @@ +Using devices [TpuDevice(id=0, process_index=0, coords=(0,0,0), core_on_chip=0), TpuDevice(id=1, process_index=0, coords=(1,0,0), core_on_chip=0), TpuDevice(id=2, process_index=0, coords=(0,1,0), core_on_chip=0), TpuDevice(id=3, process_index=0, coords=(1,1,0), core_on_chip=0)] +Device count 4 +Global device count 4 +Global Batch: 256 +Node Batch: 256 +Device Batch: 64 +Loading dataset +Loading dataset +DiT: Input of shape (1, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (1, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (1, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (1, 768) dtype float32 + + DiT Summary  +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ path  ┃ module  ┃ inputs  ┃ outputs  ┃ params  ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ │ DiT │ - float32[1,32,32,4] │ bfloat16[1,32,32,4] │ │ +│ │ │ - float32[1] │ │ │ +│ │ │ - float32[1] │ │ │ +│ │ │ - int32[1] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ PatchEmbed_0 │ PatchEmbed │ float32[1,32,32,4] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ PatchEmbed_0/Conv_0 │ Conv │ float32[1,32,32,4] │ bfloat16[1,16,16,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2,2,4,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 13,056 (52.2 KB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_0 │ TimestepEmbedder │ float32[1] │ float32[1,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_0/Dense_0 │ Dense │ bfloat16[1,256] │ bfloat16[1,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[256,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 197,376 (789.5 KB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_0/Dense_1 │ Dense │ bfloat16[1,768] │ float32[1,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_1 │ TimestepEmbedder │ float32[1] │ float32[1,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_1/Dense_0 │ Dense │ bfloat16[1,256] │ bfloat16[1,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[256,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 197,376 (789.5 KB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_1/Dense_1 │ Dense │ bfloat16[1,768] │ float32[1,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ LabelEmbedder_0 │ LabelEmbedder │ int32[1] │ bfloat16[1,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────���───────────────────────┼──────────────────────────────┤ +│ LabelEmbedder_0/Embed_0 │ Embed │ int32[1] │ bfloat16[1,768] │ embedding: float32[1001,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 768,768 (3.1 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────��───────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼─���────────────────────────────┤ +│ DiTBlock_0/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────���───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ ��� │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼──────────────────────��┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼─────────���─────────────┼──────────────────────────────┤ +│ DiTBlock_8/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────���───────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11 │ DiTBlock │ - bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_2 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_3 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_4 │ Dense │ float32[1,256,768] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/LayerNorm_1 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/MlpBlock_0 │ MlpBlock │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/MlpBlock_0/Dense_0 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,3072] │ bias: float32[3072] │ +│ │ │ │ │ kernel: float32[768,3072] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,362,368 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/MlpBlock_0/Dropout_0 │ Dropout │ bfloat16[1,256,3072] │ bfloat16[1,256,3072] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/MlpBlock_0/Dense_1 │ Dense │ bfloat16[1,256,3072] │ bfloat16[1,256,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[3072,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 2,360,064 (9.4 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/MlpBlock_0/Dropout_1 │ Dropout │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ FinalLayer_0 │ FinalLayer │ - bfloat16[1,256,768] │ bfloat16[1,256,16] │ │ +│ │ │ - float32[1,768] │ │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ FinalLayer_0/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,1536] │ bias: float32[1536] │ +│ │ │ │ │ kernel: float32[768,1536] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,181,184 (4.7 MB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ FinalLayer_0/LayerNorm_0 │ LayerNorm │ bfloat16[1,256,768] │ bfloat16[1,256,768] │ │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ FinalLayer_0/Dense_1 │ Dense │ bfloat16[1,256,768] │ bfloat16[1,256,16] │ bias: float32[16] │ +│ │ │ │ │ kernel: float32[768,16] │ +│ │ │ │ │ │ +│ │ │ │ │ 12,304 (49.2 KB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ Embed_0 │ Embed │ int32[1] │ float32[1,1] │ embedding: float32[256,1] │ +│ │ │ │ │ │ +│ │ │ │ │ 256 (1.0 KB) │ +├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│   │   │   │  Total │ 131,091,728 (524.4 MB)  │ +└──────────────────────────────────┴──────────────────┴───────────────────────┴───────────────────────┴──────────────────────────────┘ +  + Total Parameters: 131,091,728 (524.4 MB)  + + +DiT: Input of shape (1, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (1, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (1, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (1, 768) dtype float32 +Loaded checkpoint from 1016051 seconds ago. + + parameter shapes: +('PatchEmbed_0', 'Conv_0', 'kernel'): (2, 2, 4, 768) +('PatchEmbed_0', 'Conv_0', 'bias'): (768,) +('TimestepEmbedder_0', 'Dense_0', 'kernel'): (256, 768) +('TimestepEmbedder_0', 'Dense_0', 'bias'): (768,) +('TimestepEmbedder_0', 'Dense_1', 'kernel'): (768, 768) +('TimestepEmbedder_0', 'Dense_1', 'bias'): (768,) +('TimestepEmbedder_1', 'Dense_0', 'kernel'): (256, 768) +('TimestepEmbedder_1', 'Dense_0', 'bias'): (768,) +('TimestepEmbedder_1', 'Dense_1', 'kernel'): (768, 768) +('TimestepEmbedder_1', 'Dense_1', 'bias'): (768,) +('LabelEmbedder_0', 'Embed_0', 'embedding'): (1001, 768) +('DiTBlock_0', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_0', 'Dense_0', 'bias'): (4608,) +('DiTBlock_0', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_0', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_0', 'Dense_2', 'bias'): (768,) +('DiTBlock_0', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_0', 'Dense_3', 'bias'): (768,) +('DiTBlock_0', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_0', 'Dense_4', 'bias'): (768,) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_1', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_1', 'Dense_0', 'bias'): (4608,) +('DiTBlock_1', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_1', 'Dense_1', 'bias'): (768,) +('DiTBlock_1', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_1', 'Dense_2', 'bias'): (768,) +('DiTBlock_1', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_1', 'Dense_3', 'bias'): (768,) +('DiTBlock_1', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_1', 'Dense_4', 'bias'): (768,) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_2', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_2', 'Dense_0', 'bias'): (4608,) +('DiTBlock_2', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_2', 'Dense_1', 'bias'): (768,) +('DiTBlock_2', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_2', 'Dense_2', 'bias'): (768,) +('DiTBlock_2', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_2', 'Dense_3', 'bias'): (768,) +('DiTBlock_2', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_2', 'Dense_4', 'bias'): (768,) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_3', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_3', 'Dense_0', 'bias'): (4608,) +('DiTBlock_3', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_3', 'Dense_1', 'bias'): (768,) +('DiTBlock_3', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_3', 'Dense_2', 'bias'): (768,) +('DiTBlock_3', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_3', 'Dense_3', 'bias'): (768,) +('DiTBlock_3', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_3', 'Dense_4', 'bias'): (768,) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_4', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_4', 'Dense_0', 'bias'): (4608,) +('DiTBlock_4', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_4', 'Dense_1', 'bias'): (768,) +('DiTBlock_4', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_4', 'Dense_2', 'bias'): (768,) +('DiTBlock_4', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_4', 'Dense_3', 'bias'): (768,) +('DiTBlock_4', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_4', 'Dense_4', 'bias'): (768,) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_5', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_5', 'Dense_0', 'bias'): (4608,) +('DiTBlock_5', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_5', 'Dense_1', 'bias'): (768,) +('DiTBlock_5', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_5', 'Dense_2', 'bias'): (768,) +('DiTBlock_5', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_5', 'Dense_3', 'bias'): (768,) +('DiTBlock_5', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_5', 'Dense_4', 'bias'): (768,) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_6', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_6', 'Dense_0', 'bias'): (4608,) +('DiTBlock_6', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_6', 'Dense_1', 'bias'): (768,) +('DiTBlock_6', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_6', 'Dense_2', 'bias'): (768,) +('DiTBlock_6', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_6', 'Dense_3', 'bias'): (768,) +('DiTBlock_6', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_6', 'Dense_4', 'bias'): (768,) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_7', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_7', 'Dense_0', 'bias'): (4608,) +('DiTBlock_7', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_7', 'Dense_1', 'bias'): (768,) +('DiTBlock_7', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_7', 'Dense_2', 'bias'): (768,) +('DiTBlock_7', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_7', 'Dense_3', 'bias'): (768,) +('DiTBlock_7', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_7', 'Dense_4', 'bias'): (768,) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_8', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_8', 'Dense_0', 'bias'): (4608,) +('DiTBlock_8', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_8', 'Dense_1', 'bias'): (768,) +('DiTBlock_8', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_8', 'Dense_2', 'bias'): (768,) +('DiTBlock_8', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_8', 'Dense_3', 'bias'): (768,) +('DiTBlock_8', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_8', 'Dense_4', 'bias'): (768,) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_9', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_9', 'Dense_0', 'bias'): (4608,) +('DiTBlock_9', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_9', 'Dense_1', 'bias'): (768,) +('DiTBlock_9', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_9', 'Dense_2', 'bias'): (768,) +('DiTBlock_9', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_9', 'Dense_3', 'bias'): (768,) +('DiTBlock_9', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_9', 'Dense_4', 'bias'): (768,) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_10', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_10', 'Dense_0', 'bias'): (4608,) +('DiTBlock_10', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_10', 'Dense_1', 'bias'): (768,) +('DiTBlock_10', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_10', 'Dense_2', 'bias'): (768,) +('DiTBlock_10', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_10', 'Dense_3', 'bias'): (768,) +('DiTBlock_10', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_10', 'Dense_4', 'bias'): (768,) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_11', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_11', 'Dense_0', 'bias'): (4608,) +('DiTBlock_11', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_11', 'Dense_1', 'bias'): (768,) +('DiTBlock_11', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_11', 'Dense_2', 'bias'): (768,) +('DiTBlock_11', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_11', 'Dense_3', 'bias'): (768,) +('DiTBlock_11', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_11', 'Dense_4', 'bias'): (768,) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('FinalLayer_0', 'Dense_0', 'kernel'): (768, 1536) +('FinalLayer_0', 'Dense_0', 'bias'): (1536,) +('FinalLayer_0', 'Dense_1', 'kernel'): (768, 16) +('FinalLayer_0', 'Dense_1', 'bias'): (16,) +('Embed_0', 'embedding'): (256, 1) + + parameter shapes: +('DiTBlock_0', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_0', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_1', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_1', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_1', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_10', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_10', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_10', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_11', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_11', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_11', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_2', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_2', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_2', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_3', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_3', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_3', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_4', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_4', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_4', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_5', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_5', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_5', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_6', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_6', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_6', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_7', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_7', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_7', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_8', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_8', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_8', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_9', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_9', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_9', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('Embed_0', 'embedding'): (1, 256, 1) +('FinalLayer_0', 'Dense_0', 'bias'): (1, 1536) +('FinalLayer_0', 'Dense_0', 'kernel'): (1, 768, 1536) +('FinalLayer_0', 'Dense_1', 'bias'): (1, 16) +('FinalLayer_0', 'Dense_1', 'kernel'): (1, 768, 16) +('LabelEmbedder_0', 'Embed_0', 'embedding'): (1, 1001, 768) +('PatchEmbed_0', 'Conv_0', 'bias'): (1, 768) +('PatchEmbed_0', 'Conv_0', 'kernel'): (1, 2, 2, 4, 768) +('TimestepEmbedder_0', 'Dense_0', 'bias'): (1, 768) +('TimestepEmbedder_0', 'Dense_0', 'kernel'): (1, 256, 768) +('TimestepEmbedder_0', 'Dense_1', 'bias'): (1, 768) +('TimestepEmbedder_0', 'Dense_1', 'kernel'): (1, 768, 768) +('TimestepEmbedder_1', 'Dense_0', 'bias'): (1, 768) +('TimestepEmbedder_1', 'Dense_0', 'kernel'): (1, 256, 768) +('TimestepEmbedder_1', 'Dense_1', 'bias'): (1, 768) +('TimestepEmbedder_1', 'Dense_1', 'kernel'): (1, 768, 768) + + parameter shapes: +('DiTBlock_0', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_0', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_1', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_1', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_1', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_10', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_10', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_10', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_11', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_11', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_11', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_2', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_2', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_2', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_3', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_3', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_3', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_4', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_4', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_4', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_5', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_5', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_5', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_6', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_6', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_6', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_7', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_7', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_7', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_8', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_8', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_8', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_9', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_9', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_9', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('Embed_0', 'embedding'): (1, 256, 1) +('FinalLayer_0', 'Dense_0', 'bias'): (1, 1536) +('FinalLayer_0', 'Dense_0', 'kernel'): (1, 768, 1536) +('FinalLayer_0', 'Dense_1', 'bias'): (1, 16) +('FinalLayer_0', 'Dense_1', 'kernel'): (1, 768, 16) +('LabelEmbedder_0', 'Embed_0', 'embedding'): (1, 1001, 768) +('PatchEmbed_0', 'Conv_0', 'bias'): (1, 768) +('PatchEmbed_0', 'Conv_0', 'kernel'): (1, 2, 2, 4, 768) +('TimestepEmbedder_0', 'Dense_0', 'bias'): (1, 768) +('TimestepEmbedder_0', 'Dense_0', 'kernel'): (1, 256, 768) +('TimestepEmbedder_0', 'Dense_1', 'bias'): (1, 768) +('TimestepEmbedder_0', 'Dense_1', 'kernel'): (1, 768, 768) +('TimestepEmbedder_1', 'Dense_0', 'bias'): (1, 768) +('TimestepEmbedder_1', 'Dense_0', 'kernel'): (1, 256, 768) +('TimestepEmbedder_1', 'Dense_1', 'bias'): (1, 768) +('TimestepEmbedder_1', 'Dense_1', 'kernel'): (1, 768, 768) + + parameter shapes: +('DiTBlock_0', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_0', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_1', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_1', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_1', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_10', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_10', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_10', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_11', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_11', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_11', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_2', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_2', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_2', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_3', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_3', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_3', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_4', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_4', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_4', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_5', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_5', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_5', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_6', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_6', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_6', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_7', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_7', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_7', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_8', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_8', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_8', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_9', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_9', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_9', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('Embed_0', 'embedding'): (1, 256, 1) +('FinalLayer_0', 'Dense_0', 'bias'): (1, 1536) +('FinalLayer_0', 'Dense_0', 'kernel'): (1, 768, 1536) +('FinalLayer_0', 'Dense_1', 'bias'): (1, 16) +('FinalLayer_0', 'Dense_1', 'kernel'): (1, 768, 16) +('LabelEmbedder_0', 'Embed_0', 'embedding'): (1, 1001, 768) +('PatchEmbed_0', 'Conv_0', 'bias'): (1, 768) +('PatchEmbed_0', 'Conv_0', 'kernel'): (1, 2, 2, 4, 768) +('TimestepEmbedder_0', 'Dense_0', 'bias'): (1, 768) +('TimestepEmbedder_0', 'Dense_0', 'kernel'): (1, 256, 768) +('TimestepEmbedder_0', 'Dense_1', 'bias'): (1, 768) +('TimestepEmbedder_0', 'Dense_1', 'kernel'): (1, 768, 768) +('TimestepEmbedder_1', 'Dense_0', 'bias'): (1, 768) +('TimestepEmbedder_1', 'Dense_0', 'kernel'): (1, 256, 768) +('TimestepEmbedder_1', 'Dense_1', 'bias'): (1, 768) +('TimestepEmbedder_1', 'Dense_1', 'kernel'): (1, 768, 768) + + parameter shapes: +('DiTBlock_0', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_0', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_0', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_1', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_1', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_1', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_1', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_10', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_10', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_10', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_10', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_11', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_11', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_11', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_11', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_2', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_2', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_2', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_2', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_3', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_3', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_3', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_3', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_4', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_4', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_4', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_4', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_5', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_5', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_5', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_5', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_6', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_6', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_6', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_6', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_7', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_7', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_7', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_7', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_8', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_8', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_8', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_8', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('DiTBlock_9', 'Dense_0', 'bias'): (1, 4608) +('DiTBlock_9', 'Dense_0', 'kernel'): (1, 768, 4608) +('DiTBlock_9', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_1', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_2', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_2', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_3', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_3', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'Dense_4', 'bias'): (1, 768) +('DiTBlock_9', 'Dense_4', 'kernel'): (1, 768, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768) +('Embed_0', 'embedding'): (1, 256, 1) +('FinalLayer_0', 'Dense_0', 'bias'): (1, 1536) +('FinalLayer_0', 'Dense_0', 'kernel'): (1, 768, 1536) +('FinalLayer_0', 'Dense_1', 'bias'): (1, 16) +('FinalLayer_0', 'Dense_1', 'kernel'): (1, 768, 16) +('LabelEmbedder_0', 'Embed_0', 'embedding'): (1, 1001, 768) +('PatchEmbed_0', 'Conv_0', 'bias'): (1, 768) +('PatchEmbed_0', 'Conv_0', 'kernel'): (1, 2, 2, 4, 768) +('TimestepEmbedder_0', 'Dense_0', 'bias'): (1, 768) +('TimestepEmbedder_0', 'Dense_0', 'kernel'): (1, 256, 768) +('TimestepEmbedder_0', 'Dense_1', 'bias'): (1, 768) +('TimestepEmbedder_0', 'Dense_1', 'kernel'): (1, 768, 768) +('TimestepEmbedder_1', 'Dense_0', 'bias'): (1, 768) +('TimestepEmbedder_1', 'Dense_0', 'kernel'): (1, 256, 768) +('TimestepEmbedder_1', 'Dense_1', 'bias'): (1, 768) +('TimestepEmbedder_1', 'Dense_1', 'kernel'): (1, 768, 768) + + parameter shapes: +('DiTBlock_0', 'Dense_0', 'bias'): (4608,) +('DiTBlock_0', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_0', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_0', 'Dense_2', 'bias'): (768,) +('DiTBlock_0', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_0', 'Dense_3', 'bias'): (768,) +('DiTBlock_0', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_0', 'Dense_4', 'bias'): (768,) +('DiTBlock_0', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_1', 'Dense_0', 'bias'): (4608,) +('DiTBlock_1', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_1', 'Dense_1', 'bias'): (768,) +('DiTBlock_1', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_1', 'Dense_2', 'bias'): (768,) +('DiTBlock_1', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_1', 'Dense_3', 'bias'): (768,) +('DiTBlock_1', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_1', 'Dense_4', 'bias'): (768,) +('DiTBlock_1', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_10', 'Dense_0', 'bias'): (4608,) +('DiTBlock_10', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_10', 'Dense_1', 'bias'): (768,) +('DiTBlock_10', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_10', 'Dense_2', 'bias'): (768,) +('DiTBlock_10', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_10', 'Dense_3', 'bias'): (768,) +('DiTBlock_10', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_10', 'Dense_4', 'bias'): (768,) +('DiTBlock_10', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_11', 'Dense_0', 'bias'): (4608,) +('DiTBlock_11', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_11', 'Dense_1', 'bias'): (768,) +('DiTBlock_11', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_11', 'Dense_2', 'bias'): (768,) +('DiTBlock_11', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_11', 'Dense_3', 'bias'): (768,) +('DiTBlock_11', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_11', 'Dense_4', 'bias'): (768,) +('DiTBlock_11', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_2', 'Dense_0', 'bias'): (4608,) +('DiTBlock_2', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_2', 'Dense_1', 'bias'): (768,) +('DiTBlock_2', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_2', 'Dense_2', 'bias'): (768,) +('DiTBlock_2', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_2', 'Dense_3', 'bias'): (768,) +('DiTBlock_2', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_2', 'Dense_4', 'bias'): (768,) +('DiTBlock_2', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_3', 'Dense_0', 'bias'): (4608,) +('DiTBlock_3', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_3', 'Dense_1', 'bias'): (768,) +('DiTBlock_3', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_3', 'Dense_2', 'bias'): (768,) +('DiTBlock_3', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_3', 'Dense_3', 'bias'): (768,) +('DiTBlock_3', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_3', 'Dense_4', 'bias'): (768,) +('DiTBlock_3', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_4', 'Dense_0', 'bias'): (4608,) +('DiTBlock_4', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_4', 'Dense_1', 'bias'): (768,) +('DiTBlock_4', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_4', 'Dense_2', 'bias'): (768,) +('DiTBlock_4', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_4', 'Dense_3', 'bias'): (768,) +('DiTBlock_4', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_4', 'Dense_4', 'bias'): (768,) +('DiTBlock_4', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_5', 'Dense_0', 'bias'): (4608,) +('DiTBlock_5', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_5', 'Dense_1', 'bias'): (768,) +('DiTBlock_5', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_5', 'Dense_2', 'bias'): (768,) +('DiTBlock_5', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_5', 'Dense_3', 'bias'): (768,) +('DiTBlock_5', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_5', 'Dense_4', 'bias'): (768,) +('DiTBlock_5', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_6', 'Dense_0', 'bias'): (4608,) +('DiTBlock_6', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_6', 'Dense_1', 'bias'): (768,) +('DiTBlock_6', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_6', 'Dense_2', 'bias'): (768,) +('DiTBlock_6', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_6', 'Dense_3', 'bias'): (768,) +('DiTBlock_6', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_6', 'Dense_4', 'bias'): (768,) +('DiTBlock_6', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_7', 'Dense_0', 'bias'): (4608,) +('DiTBlock_7', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_7', 'Dense_1', 'bias'): (768,) +('DiTBlock_7', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_7', 'Dense_2', 'bias'): (768,) +('DiTBlock_7', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_7', 'Dense_3', 'bias'): (768,) +('DiTBlock_7', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_7', 'Dense_4', 'bias'): (768,) +('DiTBlock_7', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_8', 'Dense_0', 'bias'): (4608,) +('DiTBlock_8', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_8', 'Dense_1', 'bias'): (768,) +('DiTBlock_8', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_8', 'Dense_2', 'bias'): (768,) +('DiTBlock_8', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_8', 'Dense_3', 'bias'): (768,) +('DiTBlock_8', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_8', 'Dense_4', 'bias'): (768,) +('DiTBlock_8', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('DiTBlock_9', 'Dense_0', 'bias'): (4608,) +('DiTBlock_9', 'Dense_0', 'kernel'): (768, 4608) +('DiTBlock_9', 'Dense_1', 'bias'): (768,) +('DiTBlock_9', 'Dense_1', 'kernel'): (768, 768) +('DiTBlock_9', 'Dense_2', 'bias'): (768,) +('DiTBlock_9', 'Dense_2', 'kernel'): (768, 768) +('DiTBlock_9', 'Dense_3', 'bias'): (768,) +('DiTBlock_9', 'Dense_3', 'kernel'): (768, 768) +('DiTBlock_9', 'Dense_4', 'bias'): (768,) +('DiTBlock_9', 'Dense_4', 'kernel'): (768, 768) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,) +('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768) +('Embed_0', 'embedding'): (256, 1) +('FinalLayer_0', 'Dense_0', 'bias'): (1536,) +('FinalLayer_0', 'Dense_0', 'kernel'): (768, 1536) +('FinalLayer_0', 'Dense_1', 'bias'): (16,) +('FinalLayer_0', 'Dense_1', 'kernel'): (768, 16) +('LabelEmbedder_0', 'Embed_0', 'embedding'): (1001, 768) +('PatchEmbed_0', 'Conv_0', 'bias'): (768,) +('PatchEmbed_0', 'Conv_0', 'kernel'): (2, 2, 4, 768) +('TimestepEmbedder_0', 'Dense_0', 'bias'): (768,) +('TimestepEmbedder_0', 'Dense_0', 'kernel'): (256, 768) +('TimestepEmbedder_0', 'Dense_1', 'bias'): (768,) +('TimestepEmbedder_0', 'Dense_1', 'kernel'): (768, 768) +('TimestepEmbedder_1', 'Dense_0', 'bias'): (768,) +('TimestepEmbedder_1', 'Dense_0', 'kernel'): (256, 768) +('TimestepEmbedder_1', 'Dense_1', 'bias'): (768,) +('TimestepEmbedder_1', 'Dense_1', 'kernel'): (768, 768) +┌────────────────────────────────────────────────┐ +│ │ +│ │ +│ │ +│ │ +│ TPU 0,1,2,3 │ +│ │ +│ │ +│ │ +│ │ +└────────────────────────────────────────────────┘ +┌─────────────────────────────────────────────────────────────────────────┐ +│ │ +│ │ +│ │ +│ │ +│ TPU 0,1,2,3 │ +│ │ +│ │ +│ │ +│ │ +└─────────────────────────────────────────────────────────────────────────┘ +Calc FID for CFG 1.0 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 37.387489318847656 +Calc FID for CFG 1.0 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 19.11016845703125 +Calc FID for CFG 1.0 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 19.257938385009766 +Calc FID for CFG 1.0 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 21.54532241821289 +Calc FID for CFG 1.0 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 23.33385467529297 +Calc FID for CFG 1.0 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 25.587535858154297 +Calc FID for CFG 1.0 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 29.807153701782227 +Calc FID for CFG 1.0 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 39.091678619384766 +Calc FID for CFG 1.25 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 22.221250534057617 +Calc FID for CFG 1.25 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 11.570603370666504 +Calc FID for CFG 1.25 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 12.220520973205566 +Calc FID for CFG 1.25 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 13.82143783569336 +Calc FID for CFG 1.25 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 15.426876068115234 +Calc FID for CFG 1.25 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 17.737201690673828 +Calc FID for CFG 1.25 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 22.075279235839844 +Calc FID for CFG 1.25 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 30.63207244873047 +Calc FID for CFG 1.75 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 9.545238494873047 +Calc FID for CFG 1.75 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 9.33624267578125 +Calc FID for CFG 1.75 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 10.053601264953613 +Calc FID for CFG 1.75 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 10.555886268615723 +Calc FID for CFG 1.75 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 11.555614471435547 +Calc FID for CFG 1.75 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 13.556663513183594 +Calc FID for CFG 1.75 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 18.457218170166016 +Calc FID for CFG 1.75 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 32.443660736083984 +Calc FID for CFG 2.0 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 7.952014446258545 +Calc FID for CFG 2.0 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 10.269155502319336 +Calc FID for CFG 2.0 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 10.874478340148926 +Calc FID for CFG 2.0 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 10.988443374633789 +Calc FID for CFG 2.0 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 11.683184623718262 +Calc FID for CFG 2.0 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 13.468219757080078 +Calc FID for CFG 2.0 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 18.74422264099121 +Calc FID for CFG 2.0 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 37.30630111694336 +Calc FID for CFG 2.25 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 7.709861755371094 +Calc FID for CFG 2.25 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 11.461021423339844 +Calc FID for CFG 2.25 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 11.928138732910156 +Calc FID for CFG 2.25 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 11.797296524047852 +Calc FID for CFG 2.25 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 12.200786590576172 +Calc FID for CFG 2.25 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 13.812845230102539 +Calc FID for CFG 2.25 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 19.628908157348633 +Calc FID for CFG 2.25 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 43.063232421875 +Calc FID for CFG 2.5 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 8.207809448242188 +Calc FID for CFG 2.5 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 12.744096755981445 +Calc FID for CFG 2.5 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 13.088956832885742 +Calc FID for CFG 2.5 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 12.705114364624023 +Calc FID for CFG 2.5 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 12.84981918334961 +Calc FID for CFG 2.5 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 14.408833503723145 +Calc FID for CFG 2.5 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 21.05376434326172 +Calc FID for CFG 2.5 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 48.83190155029297 +Calc FID for CFG 2.75 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 9.041845321655273 +Calc FID for CFG 2.75 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 13.93620491027832 +Calc FID for CFG 2.75 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 14.154558181762695 +Calc FID for CFG 2.75 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 13.628525733947754 +Calc FID for CFG 2.75 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 13.56204605102539 +Calc FID for CFG 2.75 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 15.14876937866211 +Calc FID for CFG 2.75 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 22.85244369506836 +Calc FID for CFG 2.75 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 54.34938049316406 +Calc FID for CFG 3.0 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 10.043798446655273 +Calc FID for CFG 3.0 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 14.961636543273926 +Calc FID for CFG 3.0 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 15.10209846496582 +Calc FID for CFG 3.0 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 14.477651596069336 +Calc FID for CFG 3.0 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 14.275424003601074 +Calc FID for CFG 3.0 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 16.039209365844727 +Calc FID for CFG 3.0 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 24.985836029052734 +Calc FID for CFG 3.0 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 256, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +FID is 59.46251678466797