forked from open-mmlab/mmsegmentation
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #10 from open-mmlab/main
merge
- Loading branch information
Showing
134 changed files
with
9,979 additions
and
398 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,10 +1,14 @@ | ||
| version: 2 | ||
|
|
||
| build: | ||
| os: ubuntu-22.04 | ||
| tools: | ||
| python: "3.7" | ||
|
|
||
| formats: | ||
| - epub | ||
|
|
||
| python: | ||
| version: 3.7 | ||
| install: | ||
| - requirements: requirements/docs.txt | ||
| - requirements: requirements/readthedocs.txt |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,67 @@ | ||
| # dataset settings | ||
| dataset_type = 'NYUDataset' | ||
| data_root = 'data/nyu' | ||
|
|
||
| train_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='LoadDepthAnnotation', depth_rescale_factor=1e-3), | ||
| dict(type='RandomDepthMix', prob=0.25), | ||
| dict(type='RandomFlip', prob=0.5), | ||
| dict(type='RandomCrop', crop_size=(480, 480)), | ||
| dict( | ||
| type='Albu', | ||
| transforms=[ | ||
| dict(type='RandomBrightnessContrast'), | ||
| dict(type='RandomGamma'), | ||
| dict(type='HueSaturationValue'), | ||
| ]), | ||
| dict( | ||
| type='PackSegInputs', | ||
| meta_keys=('img_path', 'depth_map_path', 'ori_shape', 'img_shape', | ||
| 'pad_shape', 'scale_factor', 'flip', 'flip_direction', | ||
| 'category_id')), | ||
| ] | ||
|
|
||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='Resize', scale=(2000, 480), keep_ratio=True), | ||
| dict(dict(type='LoadDepthAnnotation', depth_rescale_factor=1e-3)), | ||
| dict( | ||
| type='PackSegInputs', | ||
| meta_keys=('img_path', 'depth_map_path', 'ori_shape', 'img_shape', | ||
| 'pad_shape', 'scale_factor', 'flip', 'flip_direction', | ||
| 'category_id')) | ||
| ] | ||
|
|
||
| train_dataloader = dict( | ||
| batch_size=8, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='InfiniteSampler', shuffle=True), | ||
| dataset=dict( | ||
| type=dataset_type, | ||
| data_root=data_root, | ||
| data_prefix=dict( | ||
| img_path='images/train', depth_map_path='annotations/train'), | ||
| pipeline=train_pipeline)) | ||
|
|
||
| val_dataloader = dict( | ||
| batch_size=1, | ||
| num_workers=4, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=dict( | ||
| type=dataset_type, | ||
| data_root=data_root, | ||
| test_mode=True, | ||
| data_prefix=dict( | ||
| img_path='images/test', depth_map_path='annotations/test'), | ||
| pipeline=test_pipeline)) | ||
| test_dataloader = val_dataloader | ||
|
|
||
| val_evaluator = dict( | ||
| type='DepthMetric', | ||
| min_depth_eval=0.001, | ||
| max_depth_eval=10.0, | ||
| crop_type='nyu_crop') | ||
| test_evaluator = val_evaluator |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| # dataset settings | ||
| dataset_type = 'NYUDataset' | ||
| data_root = 'data/nyu' | ||
|
|
||
| train_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='LoadDepthAnnotation', depth_rescale_factor=1e-3), | ||
| dict(type='RandomDepthMix', prob=0.25), | ||
| dict(type='RandomFlip', prob=0.5), | ||
| dict( | ||
| type='RandomResize', | ||
| scale=(768, 512), | ||
| ratio_range=(0.8, 1.5), | ||
| keep_ratio=True), | ||
| dict(type='RandomCrop', crop_size=(512, 512)), | ||
| dict( | ||
| type='Albu', | ||
| transforms=[ | ||
| dict(type='RandomBrightnessContrast'), | ||
| dict(type='RandomGamma'), | ||
| dict(type='HueSaturationValue'), | ||
| ]), | ||
| dict( | ||
| type='PackSegInputs', | ||
| meta_keys=('img_path', 'depth_map_path', 'ori_shape', 'img_shape', | ||
| 'pad_shape', 'scale_factor', 'flip', 'flip_direction', | ||
| 'category_id')), | ||
| ] | ||
|
|
||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='Resize', scale=(2048, 512), keep_ratio=True), | ||
| dict(dict(type='LoadDepthAnnotation', depth_rescale_factor=1e-3)), | ||
| dict( | ||
| type='PackSegInputs', | ||
| meta_keys=('img_path', 'depth_map_path', 'ori_shape', 'img_shape', | ||
| 'pad_shape', 'scale_factor', 'flip', 'flip_direction', | ||
| 'category_id')) | ||
| ] | ||
|
|
||
| train_dataloader = dict( | ||
| batch_size=8, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='InfiniteSampler', shuffle=True), | ||
| dataset=dict( | ||
| type=dataset_type, | ||
| data_root=data_root, | ||
| data_prefix=dict( | ||
| img_path='images/train', depth_map_path='annotations/train'), | ||
| pipeline=train_pipeline)) | ||
|
|
||
| val_dataloader = dict( | ||
| batch_size=1, | ||
| num_workers=4, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=dict( | ||
| type=dataset_type, | ||
| data_root=data_root, | ||
| test_mode=True, | ||
| data_prefix=dict( | ||
| img_path='images/test', depth_map_path='annotations/test'), | ||
| pipeline=test_pipeline)) | ||
| test_dataloader = val_dataloader | ||
|
|
||
| val_evaluator = dict( | ||
| type='DepthMetric', | ||
| min_depth_eval=0.001, | ||
| max_depth_eval=10.0, | ||
| crop_type='nyu_crop') | ||
| test_evaluator = val_evaluator |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,86 @@ | ||
| # model settings | ||
| data_preprocessor = dict( | ||
| type='SegDataPreProcessor', | ||
| mean=[127.5, 127.5, 127.5], | ||
| std=[127.5, 127.5, 127.5], | ||
| bgr_to_rgb=True, | ||
| pad_val=0, | ||
| seg_pad_val=0) | ||
|
|
||
| # adapted from stable-diffusion/configs/stable-diffusion/v1-inference.yaml | ||
| stable_diffusion_cfg = dict( | ||
| base_learning_rate=0.0001, | ||
| target='ldm.models.diffusion.ddpm.LatentDiffusion', | ||
| checkpoint='https://download.openmmlab.com/mmsegmentation/v0.5/' | ||
| 'vpd/stable_diffusion_v1-5_pretrain_third_party.pth', | ||
| params=dict( | ||
| linear_start=0.00085, | ||
| linear_end=0.012, | ||
| num_timesteps_cond=1, | ||
| log_every_t=200, | ||
| timesteps=1000, | ||
| first_stage_key='jpg', | ||
| cond_stage_key='txt', | ||
| image_size=64, | ||
| channels=4, | ||
| cond_stage_trainable=False, | ||
| conditioning_key='crossattn', | ||
| monitor='val/loss_simple_ema', | ||
| scale_factor=0.18215, | ||
| use_ema=False, | ||
| scheduler_config=dict( | ||
| target='ldm.lr_scheduler.LambdaLinearScheduler', | ||
| params=dict( | ||
| warm_up_steps=[10000], | ||
| cycle_lengths=[10000000000000], | ||
| f_start=[1e-06], | ||
| f_max=[1.0], | ||
| f_min=[1.0])), | ||
| unet_config=dict( | ||
| target='ldm.modules.diffusionmodules.openaimodel.UNetModel', | ||
| params=dict( | ||
| image_size=32, | ||
| in_channels=4, | ||
| out_channels=4, | ||
| model_channels=320, | ||
| attention_resolutions=[4, 2, 1], | ||
| num_res_blocks=2, | ||
| channel_mult=[1, 2, 4, 4], | ||
| num_heads=8, | ||
| use_spatial_transformer=True, | ||
| transformer_depth=1, | ||
| context_dim=768, | ||
| use_checkpoint=True, | ||
| legacy=False)), | ||
| first_stage_config=dict( | ||
| target='ldm.models.autoencoder.AutoencoderKL', | ||
| params=dict( | ||
| embed_dim=4, | ||
| monitor='val/rec_loss', | ||
| ddconfig=dict( | ||
| double_z=True, | ||
| z_channels=4, | ||
| resolution=256, | ||
| in_channels=3, | ||
| out_ch=3, | ||
| ch=128, | ||
| ch_mult=[1, 2, 4, 4], | ||
| num_res_blocks=2, | ||
| attn_resolutions=[], | ||
| dropout=0.0), | ||
| lossconfig=dict(target='torch.nn.Identity'))), | ||
| cond_stage_config=dict( | ||
| target='ldm.modules.encoders.modules.AbstractEncoder'))) | ||
|
|
||
| model = dict( | ||
| type='DepthEstimator', | ||
| data_preprocessor=data_preprocessor, | ||
| backbone=dict( | ||
| type='VPD', | ||
| diffusion_cfg=stable_diffusion_cfg, | ||
| ), | ||
| ) | ||
|
|
||
| # some of the parameters in stable-diffusion model will not be updated | ||
| # during training | ||
| find_unused_parameters = True |
Oops, something went wrong.