Liif config (#234)

* Add config of LIIF. * Rebase and modify pipeline. * Add download links. * Move link position. * Modify README.md Co-authored-by: liyinshuo <[email protected]>
open-mmlab · Apr 7, 2021 · 432b5be · 432b5be
1 parent 3a04b6e
commit 432b5be
Show file tree

Hide file tree

Showing 3 changed files with 322 additions and 0 deletions.
diff --git a/configs/restorers/liif/README.md b/configs/restorers/liif/README.md
@@ -0,0 +1,38 @@
+# Learning Continuous Image Representation with Local Implicit Image Function (LIIF)
+
+## Introduction
+
+[ALGORITHM]
+
+```bibtex
+@article{chen2020learning,
+  title={Learning Continuous Image Representation with Local Implicit Image Function},
+  author={Chen, Yinbo and Liu, Sifei and Wang, Xiaolong},
+  journal={arXiv preprint arXiv:2012.09161},
+  year={2020}
+}
+```
+
+## Results and Models
+
+Evaluated on RGB channels, `scale` pixels in each border are cropped before evaluation.
+
+The metrics are `PSNR / SSIM`.
+
+Data is normalized according to [EDSR](/configs/restorers/edsr).
+
+△ refers to ditto.
+
+|method|scale|Set5|    Set14     |    DIV2K     |    Download   |
+| :--------------: | :--------------: | :--------------: | :--------------: | :--------------: | :--------------: |
+|[liif_edsr_norm_x2-4_c64b16_g1_1000k_div2k](configs/restorers/liif/liif_edsr_norm_x2-4_c64b16_g1_1000k_div2k.py)| x2  | 35.7148 / 0.9367 | 31.5936 / 0.8889 | 34.5896 / 0.9352 | [model](https://download.openmmlab.com/mmediting/restorers/liif/liif_edsr_norm_c64b16_g1_1000k_div2k_20210319-329ce255.pth) \| [log](https://download.openmmlab.com/mmediting/restorers/liif/liif_edsr_norm_c64b16_g1_1000k_div2k_20210319-329ce255.log.json) |
+|△| x3  | 32.3596 / 0.8914 | 28.4475 / 0.8040 | 30.9154 / 0.8720 | △ |
+|△| x4  | 30.2583 / 0.8513 | 26.7867 / 0.7377 | 29.0048 / 0.8183 | △ |
+|[liif_edsr_norm_c64b16_g1_1000k_div2k](/configs/restorers/liif/liif_edsr_norm_c64b16_g1_1000k_div2k.py)| x2 | 35.7120 / 0.9365 | 31.6106 / 0.8891 | 34.6401 / 0.9353 | △ |
+|△| x3 | 32.3655 / 0.8913 | 28.4605 / 0.8039 | 30.9597 / 0.8711 | △ |
+|△| x4 | 30.2668 / 0.8511 | 26.8093 / 0.7377 | 29.0059 / 0.8183 | △ |
+|△| x6 | 27.0907 / 0.7775 | 24.7129 / 0.6438 | 26.7694 / 0.7422 | △ |
+|△| x12 | 22.9046 / 0.6255 | 21.5378 / 0.5088 | 23.7269 / 0.6373 | △ |
+|△| x18 | 20.8445 / 0.5390 | 20.0215 / 0.4521 | 22.1920 / 0.5947 | △ |
+|△| x24 | 19.7305 / 0.5033 | 19.0703 / 0.4218 | 21.2025 / 0.5714 | △ |
+|△| x30 | 18.6646 / 0.4818 | 18.0210 / 0.3905 | 20.5022 / 0.5568 | △ |
diff --git a/configs/restorers/liif/liif_edsr_norm_c64b16_g1_1000k_div2k.py b/configs/restorers/liif/liif_edsr_norm_c64b16_g1_1000k_div2k.py
@@ -0,0 +1,131 @@
+exp_name = 'liif_edsr_norm_c64b16_g1_1000k_div2k'
+scale_min, scale_max = 1, 4
+
+# model settings
+model = dict(
+    type='LIIF',
+    generator=dict(
+        type='EDSR',
+        in_channels=3,
+        out_channels=3,
+        mid_channels=64,
+        num_blocks=16),
+    imnet=dict(
+        type='MLPRefiner',
+        in_dim=64,
+        out_dim=3,
+        hidden_list=[256, 256, 256, 256]),
+    local_ensemble=True,
+    feat_unfold=True,
+    cell_decode=True,
+    rgb_mean=(0.4488, 0.4371, 0.4040),
+    rgb_std=(1., 1., 1.),
+    eval_bsize=30000,
+    pixel_loss=dict(type='L1Loss', loss_weight=1.0, reduction='mean'))
+# model training and testing settings
+train_cfg = None
+test_cfg = dict(metrics=['PSNR', 'SSIM'], crop_border=scale_max)
+
+# dataset settings
+scale_min, scale_max = 1, 4
+# dataset settings
+train_dataset_type = 'SRFolderGTDataset'
+val_dataset_type = 'SRFolderGTDataset'
+test_dataset_type = 'SRFolderGTDataset'
+train_pipeline = [
+    dict(
+        type='LoadImageFromFile',
+        io_backend='disk',
+        key='gt',
+        flag='color',
+        channel_order='rgb'),
+    dict(
+        type='RandomDownSampling',
+        scale_min=scale_min,
+        scale_max=scale_max,
+        inp_size=48),
+    dict(type='RescaleToZeroOne', keys=['lq', 'gt']),
+    dict(
+        type='Flip', keys=['lq', 'gt'], flip_ratio=0.5,
+        direction='horizontal'),
+    dict(type='Flip', keys=['lq', 'gt'], flip_ratio=0.5, direction='vertical'),
+    dict(type='RandomTransposeHW', keys=['lq', 'gt'], transpose_ratio=0.5),
+    dict(type='ImageToTensor', keys=['lq', 'gt']),
+    dict(type='GenerateCoordinateAndCell', sample_q=2304),
+    dict(
+        type='Collect',
+        keys=['lq', 'gt', 'coord', 'cell'],
+        meta_keys=['gt_path'])
+]
+valid_pipeline = [
+    dict(
+        type='LoadImageFromFile',
+        io_backend='disk',
+        key='gt',
+        flag='color',
+        channel_order='rgb'),
+    dict(type='RandomDownSampling', scale_min=scale_max, scale_max=scale_max),
+    dict(type='RescaleToZeroOne', keys=['lq', 'gt']),
+    dict(type='ImageToTensor', keys=['lq', 'gt']),
+    dict(type='GenerateCoordinateAndCell'),
+    dict(
+        type='Collect',
+        keys=['lq', 'gt', 'coord', 'cell'],
+        meta_keys=['gt_path'])
+]
+
+data = dict(
+    workers_per_gpu=8,
+    train_dataloader=dict(samples_per_gpu=16, drop_last=True),
+    val_dataloader=dict(samples_per_gpu=1),
+    test_dataloader=dict(samples_per_gpu=1),
+    train=dict(
+        type='RepeatDataset',
+        times=20,
+        dataset=dict(
+            type=train_dataset_type,
+            gt_folder='data/DIV2K/DIV2K_train_HR',
+            pipeline=train_pipeline,
+            scale=scale_max)),
+    val=dict(
+        type=val_dataset_type,
+        gt_folder='data/val_set5/Set5',
+        pipeline=valid_pipeline,
+        scale=scale_max),
+    test=dict(
+        type=test_dataset_type,
+        gt_folder='data/val_set5/Set5',
+        pipeline=valid_pipeline,
+        scale=scale_max,
+        filename_tmpl='{}'))
+
+# optimizer
+optimizers = dict(type='Adam', lr=1.e-4)
+
+# learning policy
+iter_per_epoch = 1000
+total_iters = 1000 * iter_per_epoch
+lr_config = dict(
+    policy='Step',
+    by_epoch=False,
+    step=[200000, 400000, 600000, 800000],
+    gamma=0.5)
+
+checkpoint_config = dict(
+    interval=iter_per_epoch, save_optimizer=True, by_epoch=False)
+evaluation = dict(interval=iter_per_epoch, save_image=True, gpu_collect=True)
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook', by_epoch=False),
+        dict(type='TensorboardLoggerHook')
+    ])
+visual_config = None
+
+# runtime settings
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = f'./work_dirs/{exp_name}'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/restorers/liif/liif_edsr_norm_x2-4_c64b16_g1_1000k_div2k.py b/configs/restorers/liif/liif_edsr_norm_x2-4_c64b16_g1_1000k_div2k.py
@@ -0,0 +1,153 @@
+exp_name = 'liif_edsr_norm_x2-4_c64b16_g1_1000k_div2k'
+scale_min, scale_max = 1, 4
+
+# model settings
+model = dict(
+    type='LIIF',
+    generator=dict(
+        type='EDSR',
+        in_channels=3,
+        out_channels=3,
+        mid_channels=64,
+        num_blocks=16),
+    imnet=dict(
+        type='MLPRefiner',
+        in_dim=64,
+        out_dim=3,
+        hidden_list=[256, 256, 256, 256]),
+    local_ensemble=True,
+    feat_unfold=True,
+    cell_decode=True,
+    rgb_mean=(0.4488, 0.4371, 0.4040),
+    rgb_std=(1., 1., 1.),
+    eval_bsize=30000,
+    pixel_loss=dict(type='L1Loss', loss_weight=1.0, reduction='mean'))
+# model training and testing settings
+train_cfg = None
+test_cfg = dict(metrics=['PSNR', 'SSIM'], crop_border=scale_max)
+
+# dataset settings
+scale_min, scale_max = 1, 4
+# dataset settings
+train_dataset_type = 'SRFolderGTDataset'
+val_dataset_type = 'SRFolderGTDataset'
+test_dataset_type = 'SRFolderDataset'
+train_pipeline = [
+    dict(
+        type='LoadImageFromFile',
+        io_backend='disk',
+        key='gt',
+        flag='color',
+        channel_order='rgb'),
+    dict(
+        type='RandomDownSampling',
+        scale_min=scale_min,
+        scale_max=scale_max,
+        inp_size=48),
+    dict(type='RescaleToZeroOne', keys=['lq', 'gt']),
+    dict(
+        type='Flip', keys=['lq', 'gt'], flip_ratio=0.5,
+        direction='horizontal'),
+    dict(type='Flip', keys=['lq', 'gt'], flip_ratio=0.5, direction='vertical'),
+    dict(type='RandomTransposeHW', keys=['lq', 'gt'], transpose_ratio=0.5),
+    dict(type='ImageToTensor', keys=['lq', 'gt']),
+    dict(type='GenerateCoordinateAndCell', sample_q=2304),
+    dict(
+        type='Collect',
+        keys=['lq', 'gt', 'coord', 'cell'],
+        meta_keys=['gt_path'])
+]
+valid_pipeline = [
+    dict(
+        type='LoadImageFromFile',
+        io_backend='disk',
+        key='gt',
+        flag='color',
+        channel_order='rgb'),
+    dict(type='RandomDownSampling', scale_min=scale_max, scale_max=scale_max),
+    dict(type='RescaleToZeroOne', keys=['lq', 'gt']),
+    dict(type='ImageToTensor', keys=['lq', 'gt']),
+    dict(type='GenerateCoordinateAndCell'),
+    dict(
+        type='Collect',
+        keys=['lq', 'gt', 'coord', 'cell'],
+        meta_keys=['gt_path'])
+]
+test_pipeline = [
+    dict(
+        type='LoadImageFromFile',
+        io_backend='disk',
+        key='gt',
+        flag='color',
+        channel_order='rgb'),
+    dict(
+        type='LoadImageFromFile',
+        io_backend='disk',
+        key='lq',
+        flag='color',
+        channel_order='rgb'),
+    dict(type='RescaleToZeroOne', keys=['lq', 'gt']),
+    dict(type='ImageToTensor', keys=['lq', 'gt']),
+    dict(type='GenerateCoordinateAndCell', scale=scale_max),
+    dict(
+        type='Collect',
+        keys=['lq', 'gt', 'coord', 'cell'],
+        meta_keys=['gt_path'])
+]
+
+data = dict(
+    workers_per_gpu=8,
+    train_dataloader=dict(samples_per_gpu=16, drop_last=True),
+    val_dataloader=dict(samples_per_gpu=1),
+    test_dataloader=dict(samples_per_gpu=1),
+    train=dict(
+        type='RepeatDataset',
+        times=20,
+        dataset=dict(
+            type=train_dataset_type,
+            gt_folder='data/DIV2K/DIV2K_train_HR',
+            pipeline=train_pipeline,
+            scale=scale_max)),
+    val=dict(
+        type=val_dataset_type,
+        gt_folder='data/val_set5/Set5',
+        pipeline=valid_pipeline,
+        scale=scale_max),
+    test=dict(
+        type=test_dataset_type,
+        lq_folder='data/val_set5/Set5_bicLRx{:d}'.format(scale_max),
+        gt_folder='data/val_set5/Set5',
+        pipeline=test_pipeline,
+        scale=scale_max,
+        filename_tmpl='{}'))
+
+# optimizer
+optimizers = dict(type='Adam', lr=1.e-4)
+
+# learning policy
+iter_per_epoch = 1000
+total_iters = 1000 * iter_per_epoch
+lr_config = dict(
+    policy='Step',
+    by_epoch=False,
+    step=[200000, 400000, 600000, 800000],
+    gamma=0.5)
+
+checkpoint_config = dict(
+    interval=iter_per_epoch, save_optimizer=True, by_epoch=False)
+evaluation = dict(interval=iter_per_epoch, save_image=True, gpu_collect=True)
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook', by_epoch=False),
+        dict(type='TensorboardLoggerHook')
+    ])
+visual_config = None
+
+# runtime settings
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = f'./work_dirs/{exp_name}'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]