Upload 19 files

.gitattributes

@@ -87,3 +87,4 @@ output_fp16_fp32_joined/008229_collage.png filter=lfs diff=lfs merge=lfs -text
 output_fp16_fp32_joined/008468_collage.png filter=lfs diff=lfs merge=lfs -text
 output_fp16_fp32_joined/008597_collage.png filter=lfs diff=lfs merge=lfs -text
 output_fp16_fp32_joined/008768_collage.png filter=lfs diff=lfs merge=lfs -text
+pretrained_ckpts/shape_predictor_68_face_landmarks.dat filter=lfs diff=lfs merge=lfs -text

pretrained_ckpts/auxiliray/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7914f1dccb37ab2f307703f2593efd74cc327d9db974424dff8d7510b46d85b5
+size 7813380

pretrained_ckpts/auxiliray/model_ir_se50.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a035c768259b98ab1ce0e646312f48b9e1e218197a0f80ac6765e88f8b6ddf28
+size 175367323

pretrained_ckpts/e4s/iteration_300000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a5b496f876442bc9051c6b7435d9268ee392a0d707edaa73cacd2846572771
+size 1452893535

pretrained_ckpts/face_parsing/79999_iter.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468e13ca13a9b43cc0881a9f99083a430e9c0a38abd935431d1c28ee94b26567
+size 53289463

pretrained_ckpts/face_parsing/segnext.base.512x512.celebamaskhq.160k.py

@@ -0,0 +1,179 @@
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained=None,
+    backbone=dict(
+        type='MSCAN',
+        embed_dims=[64, 128, 320, 512],
+        mlp_ratios=[8, 8, 4, 4],
+        drop_rate=0.0,
+        drop_path_rate=0.1,
+        depths=[3, 3, 12, 3],
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='pretrained/mscan_b.pth')),
+    decode_head=dict(
+        type='LightHamHead',
+        in_channels=[128, 320, 512],
+        in_index=[1, 2, 3],
+        channels=512,
+        ham_channels=512,
+        dropout_ratio=0.1,
+        num_classes=150,
+        norm_cfg=dict(type='GN', num_groups=32, requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+dataset_type = 'CelebAMaskHQDataset'
+data_root = './data/CelebAMaskHQ'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=False),
+    dict(type='Resize', img_scale=(512, 512), ratio_range=(1.0, 1.0)),
+    dict(type='RandomFlip', prob=0),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1024, 1024),
+        img_ratios=[0.5],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip', prob=0),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=6,
+    workers_per_gpu=8,
+    train=dict(
+        type='RepeatDataset',
+        times=50,
+        dataset=dict(
+            type='CelebAMaskHQDataset',
+            data_root='./data/CelebAMaskHQ',
+            img_dir='CelebA-HQ-img/',
+            ann_dir='CelebA-HQ-mask/',
+            pipeline=[
+                dict(type='LoadImageFromFile'),
+                dict(type='LoadAnnotations', reduce_zero_label=False),
+                dict(
+                    type='Resize',
+                    img_scale=(512, 512),
+                    ratio_range=(1.0, 1.0)),
+                dict(type='RandomFlip', prob=0),
+                dict(type='PhotoMetricDistortion'),
+                dict(
+                    type='Normalize',
+                    mean=[123.675, 116.28, 103.53],
+                    std=[58.395, 57.12, 57.375],
+                    to_rgb=True),
+                dict(type='DefaultFormatBundle'),
+                dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+            ],
+            split='train_split.txt')),
+    val=dict(
+        type='CelebAMaskHQDataset',
+        data_root='./data/CelebAMaskHQ',
+        img_dir='CelebA-HQ-img/',
+        ann_dir='CelebA-HQ-mask/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                img_ratios=[0.5],
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip', prob=0),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        split='val_split.txt'),
+        test=dict(
+        type='CelebAMaskHQDataset',
+        data_root='./data/CelebAMaskHQ',
+        img_dir='CelebA-HQ-img/',
+        ann_dir='CelebA-HQ-mask/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                img_ratios=[0.5],
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip', prob=0),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        split='val_split.txt'))
+log_config = dict(
+    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True
+optimizer = dict(
+    type='AdamW',
+    lr=6e-05,
+    betas=(0.9, 0.999),
+    weight_decay=0.01,
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            pos_block=dict(decay_mult=0.0),
+            norm=dict(decay_mult=0.0),
+            head=dict(lr_mult=10.0))))
+optimizer_config = dict()
+lr_config = dict(
+    policy='poly',
+    warmup='linear',
+    warmup_iters=1500,
+    warmup_ratio=1e-06,
+    power=1.0,
+    min_lr=0.0,
+    by_epoch=False)
+runner = dict(type='IterBasedRunner', max_iters=160000)
+checkpoint_config = dict(by_epoch=False, interval=10000, max_keep_ckpts=5)
+evaluation = dict(interval=10000, metric='mIoU', save_best='mIoU')
+find_unused_parameters = True
+work_dir = './work_dirs/segnext.base.512x512.celebamaskhq.160k'
+gpu_ids = [0]
+auto_resume = False

pretrained_ckpts/face_parsing/segnext.large.512x512.celebamaskhq.160k.py

@@ -0,0 +1,179 @@
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained=None,
+    backbone=dict(
+        type='MSCAN',
+        embed_dims=[64, 128, 320, 512],
+        mlp_ratios=[8, 8, 4, 4],
+        drop_rate=0.0,
+        drop_path_rate=0.3,
+        depths=[3, 5, 27, 3],
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='pretrained/mscan_l.pth')),
+    decode_head=dict(
+        type='LightHamHead',
+        in_channels=[128, 320, 512],
+        in_index=[1, 2, 3],
+        channels=1024,
+        ham_channels=1024,
+        dropout_ratio=0.1,
+        num_classes=150,
+        norm_cfg=dict(type='GN', num_groups=32, requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+dataset_type = 'CelebAMaskHQDataset'
+data_root = './data/CelebAMaskHQ'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=False),
+    dict(type='Resize', img_scale=(512, 512), ratio_range=(1.0, 1.0)),
+    dict(type='RandomFlip', prob=0),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1024, 1024),
+        img_ratios=[0.5],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip', prob=0),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=8,
+    train=dict(
+        type='RepeatDataset',
+        times=50,
+        dataset=dict(
+            type='CelebAMaskHQDataset',
+            data_root='./data/CelebAMaskHQ',
+            img_dir='CelebA-HQ-img/',
+            ann_dir='CelebA-HQ-mask/',
+            pipeline=[
+                dict(type='LoadImageFromFile'),
+                dict(type='LoadAnnotations', reduce_zero_label=False),
+                dict(
+                    type='Resize',
+                    img_scale=(512, 512),
+                    ratio_range=(1.0, 1.0)),
+                dict(type='RandomFlip', prob=0),
+                dict(type='PhotoMetricDistortion'),
+                dict(
+                    type='Normalize',
+                    mean=[123.675, 116.28, 103.53],
+                    std=[58.395, 57.12, 57.375],
+                    to_rgb=True),
+                dict(type='DefaultFormatBundle'),
+                dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+            ],
+            split='train_split.txt')),
+    val=dict(
+        type='CelebAMaskHQDataset',
+        data_root='./data/CelebAMaskHQ',
+        img_dir='CelebA-HQ-img/',
+        ann_dir='CelebA-HQ-mask/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                img_ratios=[0.5],
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip', prob=0),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        split='val_split.txt'),
+    test=dict(
+        type='CelebAMaskHQDataset',
+        data_root='./data/CelebAMaskHQ',
+        img_dir='CelebA-HQ-img/',
+        ann_dir='CelebA-HQ-mask/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                img_ratios=[0.5],
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip', prob=0),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        split='val_split.txt'))
+log_config = dict(
+    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True
+optimizer = dict(
+    type='AdamW',
+    lr=6e-05,
+    betas=(0.9, 0.999),
+    weight_decay=0.01,
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            pos_block=dict(decay_mult=0.0),
+            norm=dict(decay_mult=0.0),
+            head=dict(lr_mult=10.0))))
+optimizer_config = dict()
+lr_config = dict(
+    policy='poly',
+    warmup='linear',
+    warmup_iters=1500,
+    warmup_ratio=1e-06,
+    power=1.0,
+    min_lr=0.0,
+    by_epoch=False)
+runner = dict(type='IterBasedRunner', max_iters=160000)
+checkpoint_config = dict(by_epoch=False, interval=10000, max_keep_ckpts=5)
+evaluation = dict(interval=10000, metric='mIoU', save_best='mIoU')
+find_unused_parameters = True
+work_dir = './work_dirs/segnext.large.512x512.celebamaskhq.160k'
+gpu_ids = [0]
+auto_resume = False

pretrained_ckpts/face_parsing/segnext.small.512x512.celebamaskhq.160k.py

@@ -0,0 +1,180 @@
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained=None,
+    backbone=dict(
+        type='MSCAN',
+        embed_dims=[64, 128, 320, 512],
+        mlp_ratios=[8, 8, 4, 4],
+        drop_rate=0.0,
+        drop_path_rate=0.1,
+        depths=[2, 2, 4, 2],
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='pretrained/mscan_s.pth')),
+    decode_head=dict(
+        type='LightHamHead',
+        in_channels=[128, 320, 512],
+        in_index=[1, 2, 3],
+        channels=256,
+        ham_channels=256,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=dict(type='GN', num_groups=32, requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+        ham_kwargs=dict(MD_R=16)),
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+dataset_type = 'CelebAMaskHQDataset'
+data_root = './data/CelebAMaskHQ'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=False),
+    dict(type='Resize', img_scale=(512, 512), ratio_range=(1.0, 1.0)),
+    dict(type='RandomFlip', prob=0),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1024, 1024),
+        img_ratios=[0.5],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip', prob=0),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=16,
+    workers_per_gpu=8,
+    train=dict(
+        type='RepeatDataset',
+        times=50,
+        dataset=dict(
+            type='CelebAMaskHQDataset',
+            data_root='./data/CelebAMaskHQ',
+            img_dir='CelebA-HQ-img/',
+            ann_dir='CelebA-HQ-mask/',
+            pipeline=[
+                dict(type='LoadImageFromFile'),
+                dict(type='LoadAnnotations', reduce_zero_label=False),
+                dict(
+                    type='Resize',
+                    img_scale=(512, 512),
+                    ratio_range=(1.0, 1.0)),
+                dict(type='RandomFlip', prob=0),
+                dict(type='PhotoMetricDistortion'),
+                dict(
+                    type='Normalize',
+                    mean=[123.675, 116.28, 103.53],
+                    std=[58.395, 57.12, 57.375],
+                    to_rgb=True),
+                dict(type='DefaultFormatBundle'),
+                dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+            ],
+            split='train_split.txt')),
+    val=dict(
+        type='CelebAMaskHQDataset',
+        data_root='./data/CelebAMaskHQ',
+        img_dir='CelebA-HQ-img/',
+        ann_dir='CelebA-HQ-mask/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                img_ratios=[0.5],
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip', prob=0),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        split='val_split.txt'),
+    test=dict(
+        type='CelebAMaskHQDataset',
+        data_root='./data/CelebAMaskHQ',
+        img_dir='CelebA-HQ-img/',
+        ann_dir='CelebA-HQ-mask/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                img_ratios=[0.5],
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip', prob=0),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        split='val_split.txt'))
+log_config = dict(
+    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True
+optimizer = dict(
+    type='AdamW',
+    lr=6e-05,
+    betas=(0.9, 0.999),
+    weight_decay=0.01,
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            pos_block=dict(decay_mult=0.0),
+            norm=dict(decay_mult=0.0),
+            head=dict(lr_mult=10.0))))
+optimizer_config = dict()
+lr_config = dict(
+    policy='poly',
+    warmup='linear',
+    warmup_iters=1500,
+    warmup_ratio=1e-06,
+    power=1.0,
+    min_lr=0.0,
+    by_epoch=False)
+runner = dict(type='IterBasedRunner', max_iters=160000)
+checkpoint_config = dict(by_epoch=False, interval=10000, max_keep_ckpts=5)
+evaluation = dict(interval=10000, metric='mIoU', save_best='mIoU')
+find_unused_parameters = True
+work_dir = './work_dirs/segnext.small.512x512.celebamaskhq.160k'
+gpu_ids = [0]
+auto_resume = False

pretrained_ckpts/face_parsing/segnext.small.best_mIoU_iter_140000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f87738b6b6f5dca82cc63298d3d625f81915a9c1ed3d0a359b8866b2b76b321
+size 167259923

pretrained_ckpts/face_parsing/segnext.tiny.512x512.celebamaskhq.160k.py

@@ -0,0 +1,180 @@
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+ham_norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained=None,
+    backbone=dict(
+        type='MSCAN',
+        embed_dims=[32, 64, 160, 256],
+        mlp_ratios=[8, 8, 4, 4],
+        drop_rate=0.0,
+        drop_path_rate=0.1,
+        depths=[3, 3, 5, 2],
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        init_cfg=dict(type='Pretrained', checkpoint='pretrained/mscan_t.pth')),
+    decode_head=dict(
+        type='LightHamHead',
+        in_channels=[64, 160, 256],
+        in_index=[1, 2, 3],
+        channels=256,
+        ham_channels=256,
+        dropout_ratio=0.1,
+        num_classes=150,
+        norm_cfg=dict(type='GN', num_groups=32, requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+        ham_kwargs=dict(MD_R=16)),
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+dataset_type = 'CelebAMaskHQDataset'
+data_root = './data/CelebAMaskHQ'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=False),
+    dict(type='Resize', img_scale=(512, 512), ratio_range=(1.0, 1.0)),
+    dict(type='RandomFlip', prob=0),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1024, 1024),
+        img_ratios=[0.5],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip', prob=0),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=16,
+    workers_per_gpu=8,
+    train=dict(
+        type='RepeatDataset',
+        times=50,
+        dataset=dict(
+            type='CelebAMaskHQDataset',
+            data_root='./data/CelebAMaskHQ',
+            img_dir='CelebA-HQ-img/',
+            ann_dir='CelebA-HQ-mask/',
+            pipeline=[
+                dict(type='LoadImageFromFile'),
+                dict(type='LoadAnnotations', reduce_zero_label=False),
+                dict(
+                    type='Resize',
+                    img_scale=(512, 512),
+                    ratio_range=(1.0, 1.0)),
+                dict(type='RandomFlip', prob=0),
+                dict(type='PhotoMetricDistortion'),
+                dict(
+                    type='Normalize',
+                    mean=[123.675, 116.28, 103.53],
+                    std=[58.395, 57.12, 57.375],
+                    to_rgb=True),
+                dict(type='DefaultFormatBundle'),
+                dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+            ],
+            split='train_split.txt')),
+    val=dict(
+        type='CelebAMaskHQDataset',
+        data_root='./data/CelebAMaskHQ',
+        img_dir='CelebA-HQ-img/',
+        ann_dir='CelebA-HQ-mask/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                img_ratios=[0.5],
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip', prob=0),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        split='val_split.txt'),
+    test=dict(
+        type='CelebAMaskHQDataset',
+        data_root='./data/CelebAMaskHQ',
+        img_dir='CelebA-HQ-img/',
+        ann_dir='CelebA-HQ-mask/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                img_ratios=[0.5],
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip', prob=0),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        split='val_split.txt'))
+log_config = dict(
+    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True
+optimizer = dict(
+    type='AdamW',
+    lr=6e-05,
+    betas=(0.9, 0.999),
+    weight_decay=0.01,
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            pos_block=dict(decay_mult=0.0),
+            norm=dict(decay_mult=0.0),
+            head=dict(lr_mult=10.0))))
+optimizer_config = dict()
+lr_config = dict(
+    policy='poly',
+    warmup='linear',
+    warmup_iters=1500,
+    warmup_ratio=1e-06,
+    power=1.0,
+    min_lr=0.0,
+    by_epoch=False)
+runner = dict(type='IterBasedRunner', max_iters=160000)
+checkpoint_config = dict(by_epoch=False, interval=10000, max_keep_ckpts=5)
+evaluation = dict(interval=10000, metric='mIoU', save_best='mIoU')
+find_unused_parameters = True
+work_dir = './work_dirs/segnext.tiny.512x512.celebamaskhq.160k'
+gpu_ids = [0]
+auto_resume = False

pretrained_ckpts/facevid2vid/00000189-checkpoint.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec00af84967380eb696cd836b948de98a0eddbc8de683101ab886de182789cd
+size 2112477593

pretrained_ckpts/facevid2vid/vox-256.yaml

@@ -0,0 +1,88 @@
+dataset_params:
+  root_dir: /zlh/VoxCeleb/first-order-256
+  frame_shape: [256, 256, 3]
+  id_sampling: True
+  pairs_list: None
+  augmentation_params:
+    flip_param:
+      horizontal_flip: True
+      time_flip: True
+    jitter_param:
+      brightness: 0.1
+      contrast: 0.1
+      saturation: 0.1
+      hue: 0.1
+
+
+model_params:
+  common_params:
+    num_kp: 15 
+    image_channel: 3                    
+    feature_channel: 32
+    estimate_jacobian: False   # True
+  kp_detector_params:
+     temperature: 0.1
+     block_expansion: 32            
+     max_features: 1024
+     scale_factor: 0.25         # 0.25
+     num_blocks: 5
+     reshape_channel: 16384  # 16384 = 1024 * 16
+     reshape_depth: 16
+  he_estimator_params:
+     block_expansion: 64            
+     max_features: 2048
+     num_bins: 66
+  generator_params:
+    block_expansion: 64
+    max_features: 512
+    num_down_blocks: 2
+    reshape_channel: 32
+    reshape_depth: 16         # 512 = 32 * 16
+    num_resblocks: 6
+    estimate_occlusion_map: True
+    dense_motion_params:
+      block_expansion: 32
+      max_features: 1024
+      num_blocks: 5
+      # reshape_channel: 32
+      reshape_depth: 16
+      compress: 4
+  discriminator_params:
+    scales: [1]
+    block_expansion: 32                 
+    max_features: 512
+    num_blocks: 4
+    sn: True
+
+train_params:
+  num_epochs: 300
+  num_repeats: 75
+  epoch_milestones: [180,]
+  lr_generator: 2.0e-4
+  lr_discriminator: 2.0e-4
+  lr_kp_detector: 2.0e-4
+  lr_he_estimator: 2.0e-4
+  gan_mode: 'hinge'    # hinge or ls
+  batch_size: 32
+  scales: [1, 0.5, 0.25, 0.125]
+  checkpoint_freq: 10
+  hopenet_snapshot: '/zlh/Project/deep-head-pose/checkpoints/hopenet_robust_alpha1.pkl'
+  transform_params:
+    sigma_affine: 0.05
+    sigma_tps: 0.005
+    points_tps: 5
+  loss_weights:
+    generator_gan: 1                  
+    discriminator_gan: 1
+    feature_matching: [10, 10, 10, 10]
+    perceptual: [10, 10, 10, 10, 10]
+    equivariance_value: 10
+    equivariance_jacobian: 0    # 10
+    keypoint: 10
+    headpose: 20
+    expression: 5
+
+visualizer_params:
+  kp_size: 5
+  draw_border: True
+  colormap: 'gist_rainbow'

pretrained_ckpts/gpen/fetch_gepn_models.sh

@@ -0,0 +1,8 @@
+mkdir weights
+
+wget https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/RetinaFace-R50.pth
+wget https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/realesrnet_x4.pth
+wget https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-BFR-512.pth
+wget https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/ParseNet-latest.pth
+
+mv *.pth ./weights

pretrained_ckpts/gpen/weights/GPEN-BFR-512.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1002c41add95b0decad69604d80455576f7187dd99ca16bd611bcfd44c10b51
+size 284085738

pretrained_ckpts/gpen/weights/ParseNet-latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d558d8d0e42c20224f13cf5a29c79eba2d59913419f945545d8cf7b72920de2
+size 85331193

pretrained_ckpts/gpen/weights/RetinaFace-R50.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1de9c2944f2ccddca5f5e010ea5ae64a39845a86311af6fdf30841b0a5a16d
+size 109497761

pretrained_ckpts/gpen/weights/realesrnet_x4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa00f09ad753d88576b21ed977e97d634976377031b178acc3b5b238df463400
+size 67040989

pretrained_ckpts/put_ckpts_accordingly.txt

@@ -0,0 +1 @@
+please download the pre-trained models according to the Doc and place them in the corresponding folder

pretrained_ckpts/shape_predictor_68_face_landmarks.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdc2cb80eb9aa7a758672cbfdda32ba6300efe9b6e6c7a299ff7e736b11b92f
+size 99693937

pretrained_ckpts/stylegan2/stylegan2-ffhq-config-f.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae494ef77e32a9cd1792a81a3c167692a0e64f6bcd8b06592ff42917e2ed46e
+size 381462551