Upload folder using huggingface_hub

scannet/semseg-ptv3_weight=distill-ptv3_scannet200+structured3d_dino-L/config.py

@@ -0,0 +1,310 @@
+weight = 'exp/scannet200/2025-03-01_221653/model/model_last.pth'
+resume = False
+evaluate = True
+test_only = False
+seed = 490701
+save_path = 'exp/scannet/2025-03-04_165711'
+wandb_project = 'semseg_scannet'
+num_worker = 24
+batch_size = 12
+batch_size_val = None
+batch_size_test = None
+epoch = 80
+eval_epoch = 80
+clip_grad = None
+sync_bn = False
+enable_amp = True
+empty_cache = False
+empty_cache_per_epoch = False
+find_unused_parameters = True
+mix_prob = 0.8
+param_dicts = [
+    dict(keyword='block', lr=6e-05),
+    dict(keyword='backbone', lr=0.0006)
+]
+hooks = [
+    dict(type='CheckpointLoader'),
+    dict(type='IterationTimer', warmup_iter=2),
+    dict(type='InformationWriter'),
+    dict(type='SemSegEvaluator'),
+    dict(type='CheckpointSaver', save_freq=None),
+    dict(type='PreciseEvaluator', test_last=False)
+]
+train = dict(type='DefaultTrainer')
+test = dict(type='SemSegTester', verbose=True)
+model = dict(
+    type='DefaultSegmentorV2',
+    num_classes=20,
+    backbone_out_channels=64,
+    backbone=dict(
+        type='PT-v3m1',
+        in_channels=6,
+        order=('z', 'z-trans', 'hilbert', 'hilbert-trans'),
+        stride=(2, 2, 2, 2),
+        enc_depths=(2, 2, 2, 6, 2),
+        enc_channels=(32, 64, 128, 256, 512),
+        enc_num_head=(2, 4, 8, 16, 32),
+        enc_patch_size=(1024, 1024, 1024, 1024, 1024),
+        dec_depths=(2, 2, 2, 2),
+        dec_channels=(64, 64, 128, 256),
+        dec_num_head=(4, 4, 8, 16),
+        dec_patch_size=(1024, 1024, 1024, 1024),
+        mlp_ratio=4,
+        qkv_bias=True,
+        qk_scale=None,
+        attn_drop=0.0,
+        proj_drop=0.0,
+        drop_path=0.3,
+        shuffle_orders=True,
+        pre_norm=True,
+        enable_rpe=False,
+        enable_flash=True,
+        upcast_attention=False,
+        upcast_softmax=False,
+        cls_mode=False,
+        pdnorm_bn=True,
+        pdnorm_ln=True,
+        pdnorm_decouple=True,
+        pdnorm_adaptive=False,
+        pdnorm_affine=True,
+        pdnorm_conditions=('ScanNet', 'S3DIS', 'Structured3D')),
+    criteria=[
+        dict(type='CrossEntropyLoss', loss_weight=1.0, ignore_index=-1),
+        dict(
+            type='LovaszLoss',
+            mode='multiclass',
+            loss_weight=1.0,
+            ignore_index=-1)
+    ])
+optimizer = dict(type='AdamW', lr=0.006, weight_decay=0.05)
+scheduler = dict(
+    type='OneCycleLR',
+    max_lr=[0.006, 6e-05, 0.0006],
+    pct_start=0.05,
+    anneal_strategy='cos',
+    div_factor=10.0,
+    final_div_factor=1000.0)
+dataset_type = 'ScanNetDataset'
+data_root = 'data/scannet'
+data = dict(
+    num_classes=20,
+    ignore_index=-1,
+    names=[
+        'wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table', 'door',
+        'window', 'bookshelf', 'picture', 'counter', 'desk', 'curtain',
+        'refridgerator', 'shower curtain', 'toilet', 'sink', 'bathtub',
+        'otherfurniture'
+    ],
+    train=dict(
+        type='ScanNetDataset',
+        split='train',
+        data_root='data/scannet',
+        transform=[
+            dict(type='CenterShift', apply_z=True),
+            dict(
+                type='RandomDropout',
+                dropout_ratio=0.2,
+                dropout_application_ratio=0.2),
+            dict(
+                type='RandomRotate',
+                angle=[-1, 1],
+                axis='z',
+                center=[0, 0, 0],
+                p=0.5),
+            dict(
+                type='RandomRotate',
+                angle=[-0.015625, 0.015625],
+                axis='x',
+                p=0.5),
+            dict(
+                type='RandomRotate',
+                angle=[-0.015625, 0.015625],
+                axis='y',
+                p=0.5),
+            dict(type='RandomScale', scale=[0.9, 1.1]),
+            dict(type='RandomFlip', p=0.5),
+            dict(type='RandomJitter', sigma=0.005, clip=0.02),
+            dict(
+                type='ElasticDistortion',
+                distortion_params=[[0.2, 0.4], [0.8, 1.6]]),
+            dict(type='ChromaticAutoContrast', p=0.2, blend_factor=None),
+            dict(type='ChromaticTranslation', p=0.95, ratio=0.05),
+            dict(type='ChromaticJitter', p=0.95, std=0.05),
+            dict(
+                type='GridSample',
+                grid_size=0.02,
+                hash_type='fnv',
+                mode='train',
+                return_grid_coord=True),
+            dict(type='SphereCrop', point_max=102400, mode='random'),
+            dict(type='CenterShift', apply_z=False),
+            dict(type='NormalizeColor'),
+            dict(type='Add', keys_dict=dict(condition='ScanNet')),
+            dict(type='ToTensor'),
+            dict(
+                type='Collect',
+                keys=('coord', 'grid_coord', 'segment', 'condition'),
+                feat_keys=('color', 'normal'))
+        ],
+        test_mode=False,
+        loop=1),
+    val=dict(
+        type='ScanNetDataset',
+        split='val',
+        data_root='data/scannet',
+        transform=[
+            dict(type='CenterShift', apply_z=True),
+            dict(
+                type='GridSample',
+                grid_size=0.02,
+                hash_type='fnv',
+                mode='train',
+                return_grid_coord=True),
+            dict(type='CenterShift', apply_z=False),
+            dict(type='NormalizeColor'),
+            dict(type='Add', keys_dict=dict(condition='ScanNet')),
+            dict(type='ToTensor'),
+            dict(
+                type='Collect',
+                keys=('coord', 'grid_coord', 'segment', 'condition'),
+                feat_keys=('color', 'normal'))
+        ],
+        test_mode=False),
+    test=dict(
+        type='ScanNetDataset',
+        split='val',
+        data_root='data/scannet',
+        transform=[
+            dict(type='CenterShift', apply_z=True),
+            dict(type='NormalizeColor')
+        ],
+        test_mode=True,
+        test_cfg=dict(
+            voxelize=dict(
+                type='GridSample',
+                grid_size=0.02,
+                hash_type='fnv',
+                mode='test',
+                keys=('coord', 'color', 'normal'),
+                return_grid_coord=True),
+            crop=None,
+            post_transform=[
+                dict(type='CenterShift', apply_z=False),
+                dict(type='ToTensor'),
+                dict(type='Add', keys_dict=dict(condition='ScanNet')),
+                dict(
+                    type='Collect',
+                    keys=('coord', 'grid_coord', 'index', 'condition'),
+                    feat_keys=('color', 'normal'))
+            ],
+            aug_transform=[[{
+                'type': 'RandomRotateTargetAngle',
+                'angle': [0],
+                'axis': 'z',
+                'center': [0, 0, 0],
+                'p': 1
+            }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [0.95, 0.95]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [0.95, 0.95]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [0.95, 0.95]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [0.95, 0.95]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [1.05, 1.05]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [0.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [1.05, 1.05]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [1.05, 1.05]
+                           }],
+                           [{
+                               'type': 'RandomRotateTargetAngle',
+                               'angle': [1.5],
+                               'axis': 'z',
+                               'center': [0, 0, 0],
+                               'p': 1
+                           }, {
+                               'type': 'RandomScale',
+                               'scale': [1.05, 1.05]
+                           }], [{
+                               'type': 'RandomFlip',
+                               'p': 1
+                           }]])))

scannet/semseg-ptv3_weight=distill-ptv3_scannet200+structured3d_dino-L/events.out.tfevents.1741103921.n23g0009.hpc.itc.rwth-aachen.de

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46598741252268954157a484206e81091acd7f43cf28f04b0ab7701b84fca72
+size 786643

scannet/semseg-ptv3_weight=distill-ptv3_scannet200+structured3d_dino-L/model/model_best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8522fc7400d5535b9b7863f55a5c9c94e7e71d7a81f5470fca3aa5584e5fb039
+size 554980580

scannet/semseg-ptv3_weight=distill-ptv3_scannet200+structured3d_dino-L/model/model_last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ff18b4519118984e69f40caf591d9f044260d7dc7396de17c2dfce399248b5
+size 554980580