Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[CodeCamp2023-533] Migration Deepfashion topdown heatmap algorithms to 1.x #2597

Merged
merged 10 commits into from
Aug 10, 2023
Merged

[CodeCamp2023-533] Migration Deepfashion topdown heatmap algorithms to 1.x #2597

merged 10 commits into from
Aug 10, 2023

Conversation

xin-li-67
Copy link
Contributor

Motivation

[OpenMMLab Camp Task]open-mmlab/OpenMMLabCamp#533

Modification

configs/fashion_2d_keypoint/topdown_heatmap/deepfashion/

BC-breaking (Optional)

Use cases (Optional)

Checklist

Before PR:

  • I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
  • Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
  • Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
  • New functionalities are covered by complete unit tests. If not, please add more unit tests to ensure correctness.
  • The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

  • CLA has been signed and all committers have signed the CLA in this PR.

@xin-li-67 xin-li-67 changed the title [WIP][Camp] Migration Deepfashion topdown heatmap algorithms to 1.x [WIP][CodeCamp2023-533] Migration Deepfashion topdown heatmap algorithms to 1.x Aug 3, 2023
@xin-li-67 xin-li-67 changed the title [WIP][CodeCamp2023-533] Migration Deepfashion topdown heatmap algorithms to 1.x [CodeCamp2023-533] Migration Deepfashion topdown heatmap algorithms to 1.x Aug 4, 2023
@xin-li-67
Copy link
Contributor Author

Question about this pr: only three res_50 chkpts were provided in the original 0.x branch. Do I need to train everything out and benchmark them by myself??

@Tau-J
Copy link
Collaborator

Tau-J commented Aug 4, 2023 •
edited
Loading

Question about this pr: only three res_50 chkpts were provided in the original 0.x branch. Do I need to train everything out and benchmark them by myself??

Thanks for your feedback. I think it is okay if you only migrate the existed 3 ckpts. If you have time, I think training a strong baseline such as hrnet48+udp will be much appreciated.

@xin-li-67
Copy link
Contributor Author

the test result of td-hm_hrnet-w48_udp_8xb32-210e_deepfashion_full-256x192:

08/10 08:33:01 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used.
08/10 08:33:01 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook                    
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
before_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) DistSamplerSeedHook                
 -------------------- 
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SyncBuffersHook                    
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_val_epoch:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SyncBuffersHook                    
 -------------------- 
before_val_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) PoseVisualizationHook              
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_test_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_test_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_test_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) PoseVisualizationHook              
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_run:
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
loading annotations into memory...
Done (t=0.03s)
creating index...
index created!
08/10 08:33:02 - mmengine - WARNING - The prefix is not set in metric class PCKAccuracy.
08/10 08:33:02 - mmengine - WARNING - The prefix is not set in metric class AUC.
08/10 08:33:02 - mmengine - WARNING - The prefix is not set in metric class EPE.
Loads checkpoint by local backend from path: work_dirs/td-hm_hrnet-w48_udp_8xb32-210e_deepfashion_full-256x192/best_AUC_epoch_180.pth
08/10 08:33:02 - mmengine - INFO - Load checkpoint from work_dirs/td-hm_hrnet-w48_udp_8xb32-210e_deepfashion_full-256x192/best_AUC_epoch_180.pth
08/10 08:33:04 - mmengine - INFO - Epoch(test) [ 10/253]    eta: 0:00:51  time: 0.211292  data_time: 0.030820  memory: 653  
08/10 08:33:05 - mmengine - INFO - Epoch(test) [ 20/253]    eta: 0:00:34  time: 0.146591  data_time: 0.017448  memory: 653  
08/10 08:33:06 - mmengine - INFO - Epoch(test) [ 30/253]    eta: 0:00:27  time: 0.125057  data_time: 0.012981  memory: 653  
08/10 08:33:07 - mmengine - INFO - Epoch(test) [ 40/253]    eta: 0:00:24  time: 0.115417  data_time: 0.010754  memory: 653  
08/10 08:33:08 - mmengine - INFO - Epoch(test) [ 50/253]    eta: 0:00:22  time: 0.109029  data_time: 0.009393  memory: 653  
08/10 08:33:09 - mmengine - INFO - Epoch(test) [ 60/253]    eta: 0:00:20  time: 0.083486  data_time: 0.004045  memory: 653  
08/10 08:33:09 - mmengine - INFO - Epoch(test) [ 70/253]    eta: 0:00:18  time: 0.085211  data_time: 0.004387  memory: 653  
08/10 08:33:10 - mmengine - INFO - Epoch(test) [ 80/253]    eta: 0:00:17  time: 0.086349  data_time: 0.004658  memory: 653  
08/10 08:33:11 - mmengine - INFO - Epoch(test) [ 90/253]    eta: 0:00:16  time: 0.086256  data_time: 0.004794  memory: 653  
08/10 08:33:12 - mmengine - INFO - Epoch(test) [100/253]    eta: 0:00:15  time: 0.087241  data_time: 0.004888  memory: 653  
08/10 08:33:13 - mmengine - INFO - Epoch(test) [110/253]    eta: 0:00:13  time: 0.088057  data_time: 0.004906  memory: 653  
08/10 08:33:14 - mmengine - INFO - Epoch(test) [120/253]    eta: 0:00:12  time: 0.086754  data_time: 0.004561  memory: 653  
08/10 08:33:15 - mmengine - INFO - Epoch(test) [130/253]    eta: 0:00:11  time: 0.085763  data_time: 0.004334  memory: 653  
08/10 08:33:16 - mmengine - INFO - Epoch(test) [140/253]    eta: 0:00:10  time: 0.086398  data_time: 0.004415  memory: 653  
08/10 08:33:16 - mmengine - INFO - Epoch(test) [150/253]    eta: 0:00:09  time: 0.086403  data_time: 0.004521  memory: 653  
08/10 08:33:17 - mmengine - INFO - Epoch(test) [160/253]    eta: 0:00:08  time: 0.086215  data_time: 0.004490  memory: 653  
08/10 08:33:18 - mmengine - INFO - Epoch(test) [170/253]    eta: 0:00:07  time: 0.086407  data_time: 0.004515  memory: 653  
08/10 08:33:19 - mmengine - INFO - Epoch(test) [180/253]    eta: 0:00:06  time: 0.087085  data_time: 0.004479  memory: 653  
08/10 08:33:20 - mmengine - INFO - Epoch(test) [190/253]    eta: 0:00:05  time: 0.086751  data_time: 0.004288  memory: 653  
08/10 08:33:21 - mmengine - INFO - Epoch(test) [200/253]    eta: 0:00:04  time: 0.086298  data_time: 0.004152  memory: 653  
08/10 08:33:22 - mmengine - INFO - Epoch(test) [210/253]    eta: 0:00:03  time: 0.086564  data_time: 0.004263  memory: 653  
08/10 08:33:22 - mmengine - INFO - Epoch(test) [220/253]    eta: 0:00:03  time: 0.087083  data_time: 0.004284  memory: 653  
08/10 08:33:23 - mmengine - INFO - Epoch(test) [230/253]    eta: 0:00:02  time: 0.087400  data_time: 0.004343  memory: 653  
08/10 08:33:24 - mmengine - INFO - Epoch(test) [240/253]    eta: 0:00:01  time: 0.087517  data_time: 0.004494  memory: 653  
08/10 08:33:25 - mmengine - INFO - Epoch(test) [250/253]    eta: 0:00:00  time: 0.087768  data_time: 0.004497  memory: 653  
08/10 08:33:25 - mmengine - INFO - Evaluating PCKAccuracy (normalized by ``"bbox_size"``)...
08/10 08:33:25 - mmengine - INFO - Evaluating AUC...
08/10 08:33:25 - mmengine - INFO - Evaluating EPE...
08/10 08:33:25 - mmengine - INFO - Epoch(test) [253/253]    PCK: 0.982517  AUC: 0.673234  EPE: 11.708903  data_time: 0.005471  time: 0.091295

@xin-li-67
Copy link
Contributor Author

the test result of td-hm_hrnet-w48_udp_8xb32-210e_deepfashion_lower-256x192.py:

08/10 08:28:40 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used.
08/10 08:28:40 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook                    
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
before_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) DistSamplerSeedHook                
 -------------------- 
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SyncBuffersHook                    
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_val_epoch:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SyncBuffersHook                    
 -------------------- 
before_val_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) PoseVisualizationHook              
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_test_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_test_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_test_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) PoseVisualizationHook              
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_run:
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
loading annotations into memory...
Done (t=0.02s)
creating index...
index created!
08/10 08:28:41 - mmengine - WARNING - The prefix is not set in metric class PCKAccuracy.
08/10 08:28:41 - mmengine - WARNING - The prefix is not set in metric class AUC.
08/10 08:28:41 - mmengine - WARNING - The prefix is not set in metric class EPE.
Loads checkpoint by local backend from path: work_dirs/td-hm_hrnet-w48_udp_8xb32-210e_deepfashion_lower-256x192/best_AUC_epoch_180.pth
08/10 08:28:42 - mmengine - INFO - Load checkpoint from work_dirs/td-hm_hrnet-w48_udp_8xb32-210e_deepfashion_lower-256x192/best_AUC_epoch_180.pth
08/10 08:28:44 - mmengine - INFO - Epoch(test) [ 10/157]    eta: 0:00:29  time: 0.198109  data_time: 0.024492  memory: 653  
08/10 08:28:45 - mmengine - INFO - Epoch(test) [ 20/157]    eta: 0:00:19  time: 0.143357  data_time: 0.014357  memory: 653  
08/10 08:28:46 - mmengine - INFO - Epoch(test) [ 30/157]    eta: 0:00:15  time: 0.123881  data_time: 0.011017  memory: 653  
08/10 08:28:46 - mmengine - INFO - Epoch(test) [ 40/157]    eta: 0:00:13  time: 0.114912  data_time: 0.009298  memory: 653  
08/10 08:28:47 - mmengine - INFO - Epoch(test) [ 50/157]    eta: 0:00:11  time: 0.109820  data_time: 0.008227  memory: 653  
08/10 08:28:48 - mmengine - INFO - Epoch(test) [ 60/157]    eta: 0:00:10  time: 0.087698  data_time: 0.004204  memory: 653  
08/10 08:28:49 - mmengine - INFO - Epoch(test) [ 70/157]    eta: 0:00:08  time: 0.087339  data_time: 0.004148  memory: 653  
08/10 08:28:50 - mmengine - INFO - Epoch(test) [ 80/157]    eta: 0:00:07  time: 0.087805  data_time: 0.004094  memory: 653  
08/10 08:28:51 - mmengine - INFO - Epoch(test) [ 90/157]    eta: 0:00:06  time: 0.087564  data_time: 0.004048  memory: 653  
08/10 08:28:52 - mmengine - INFO - Epoch(test) [100/157]    eta: 0:00:05  time: 0.087191  data_time: 0.004163  memory: 653  
08/10 08:28:53 - mmengine - INFO - Epoch(test) [110/157]    eta: 0:00:04  time: 0.087060  data_time: 0.004085  memory: 653  
08/10 08:28:53 - mmengine - INFO - Epoch(test) [120/157]    eta: 0:00:03  time: 0.087025  data_time: 0.004102  memory: 653  
08/10 08:28:54 - mmengine - INFO - Epoch(test) [130/157]    eta: 0:00:02  time: 0.086341  data_time: 0.004104  memory: 653  
08/10 08:28:55 - mmengine - INFO - Epoch(test) [140/157]    eta: 0:00:01  time: 0.085424  data_time: 0.004195  memory: 653  
08/10 08:28:56 - mmengine - INFO - Epoch(test) [150/157]    eta: 0:00:00  time: 0.084366  data_time: 0.004150  memory: 653  
08/10 08:28:57 - mmengine - INFO - Evaluating PCKAccuracy (normalized by ``"bbox_size"``)...
08/10 08:28:57 - mmengine - INFO - Evaluating AUC...
08/10 08:28:57 - mmengine - INFO - Evaluating EPE...
08/10 08:28:57 - mmengine - INFO - Epoch(test) [157/157]    PCK: 0.977878  AUC: 0.761140  EPE: 8.928980  data_time: 0.005432  time: 0.093416

@xin-li-67
Copy link
Contributor Author

the test result of td-hm_hrnet-w48_udp_8xb32-210e_deepfashion_upper-256x192.py:

2023/08/10 08:26:19 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used.
2023/08/10 08:26:19 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook                    
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
before_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) DistSamplerSeedHook                
 -------------------- 
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SyncBuffersHook                    
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_val_epoch:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SyncBuffersHook                    
 -------------------- 
before_val_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) PoseVisualizationHook              
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_test_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_test_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_test_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) PoseVisualizationHook              
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_run:
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
2023/08/10 08:26:20 - mmengine - WARNING - The prefix is not set in metric class PCKAccuracy.
2023/08/10 08:26:20 - mmengine - WARNING - The prefix is not set in metric class AUC.
2023/08/10 08:26:20 - mmengine - WARNING - The prefix is not set in metric class EPE.
2023/08/10 08:26:20 - mmengine - INFO - Load checkpoint from work_dirs/td-hm_hrnet-w48_udp_8xb32-210e_deepfashion_upper-256x192/best_AUC_epoch_60.pth
2023/08/10 08:26:22 - mmengine - INFO - Epoch(test) [ 10/215]    eta: 0:00:39  time: 0.190953  data_time: 0.015054  memory: 653  
2023/08/10 08:26:23 - mmengine - INFO - Epoch(test) [ 20/215]    eta: 0:00:27  time: 0.138505  data_time: 0.009926  memory: 653  
2023/08/10 08:26:24 - mmengine - INFO - Epoch(test) [ 30/215]    eta: 0:00:22  time: 0.120908  data_time: 0.008126  memory: 653  
2023/08/10 08:26:25 - mmengine - INFO - Epoch(test) [ 40/215]    eta: 0:00:19  time: 0.112188  data_time: 0.007313  memory: 653  
2023/08/10 08:26:26 - mmengine - INFO - Epoch(test) [ 50/215]    eta: 0:00:17  time: 0.106884  data_time: 0.006735  memory: 653  
2023/08/10 08:26:26 - mmengine - INFO - Epoch(test) [ 60/215]    eta: 0:00:16  time: 0.085739  data_time: 0.004548  memory: 653  
2023/08/10 08:26:27 - mmengine - INFO - Epoch(test) [ 70/215]    eta: 0:00:14  time: 0.085564  data_time: 0.004462  memory: 653  
2023/08/10 08:26:28 - mmengine - INFO - Epoch(test) [ 80/215]    eta: 0:00:13  time: 0.086059  data_time: 0.004660  memory: 653  
2023/08/10 08:26:29 - mmengine - INFO - Epoch(test) [ 90/215]    eta: 0:00:12  time: 0.086533  data_time: 0.004638  memory: 653  
2023/08/10 08:26:30 - mmengine - INFO - Epoch(test) [100/215]    eta: 0:00:11  time: 0.086434  data_time: 0.004531  memory: 653  
2023/08/10 08:26:31 - mmengine - INFO - Epoch(test) [110/215]    eta: 0:00:10  time: 0.086373  data_time: 0.004481  memory: 653  
2023/08/10 08:26:32 - mmengine - INFO - Epoch(test) [120/215]    eta: 0:00:08  time: 0.086331  data_time: 0.004440  memory: 653  
2023/08/10 08:26:32 - mmengine - INFO - Epoch(test) [130/215]    eta: 0:00:07  time: 0.085773  data_time: 0.004187  memory: 653  
2023/08/10 08:26:33 - mmengine - INFO - Epoch(test) [140/215]    eta: 0:00:07  time: 0.085171  data_time: 0.004088  memory: 653  
2023/08/10 08:26:34 - mmengine - INFO - Epoch(test) [150/215]    eta: 0:00:06  time: 0.085129  data_time: 0.004148  memory: 653  
2023/08/10 08:26:35 - mmengine - INFO - Epoch(test) [160/215]    eta: 0:00:05  time: 0.085315  data_time: 0.004287  memory: 653  
2023/08/10 08:26:36 - mmengine - INFO - Epoch(test) [170/215]    eta: 0:00:04  time: 0.085467  data_time: 0.004382  memory: 653  
2023/08/10 08:26:37 - mmengine - INFO - Epoch(test) [180/215]    eta: 0:00:03  time: 0.085638  data_time: 0.004503  memory: 653  
2023/08/10 08:26:38 - mmengine - INFO - Epoch(test) [190/215]    eta: 0:00:02  time: 0.085708  data_time: 0.004574  memory: 653  
2023/08/10 08:26:38 - mmengine - INFO - Epoch(test) [200/215]    eta: 0:00:01  time: 0.085860  data_time: 0.004648  memory: 653  
2023/08/10 08:26:39 - mmengine - INFO - Epoch(test) [210/215]    eta: 0:00:00  time: 0.085802  data_time: 0.004645  memory: 653  
2023/08/10 08:26:40 - mmengine - INFO - Evaluating PCKAccuracy (normalized by ``"bbox_size"``)...
2023/08/10 08:26:40 - mmengine - INFO - Evaluating AUC...
2023/08/10 08:26:40 - mmengine - INFO - Evaluating EPE...
2023/08/10 08:26:40 - mmengine - INFO - Epoch(test) [215/215]    PCK: 0.961163  AUC: 0.608919  EPE: 15.125773  data_time: 0.004980  time: 0.090711

@xin-li-67
Copy link
Contributor Author

Wandb Traning logs are available here: https://api.wandb.ai/links/xinliritz80/awwme4nf

@codecov
Copy link

codecov bot commented Aug 10, 2023 •
edited
Loading

Codecov Report

Patch coverage: 60.97% and project coverage change: -0.27% ⚠️

Comparison is base (9d08e40) 80.78% compared to head (2070452) 80.51%.
Report is 11 commits behind head on dev-1.x.

❗ Current head 2070452 differs from pull request most recent head 9af47f8. Consider uploading reports for the commit 9af47f8 to get more accurate results

Additional details and impacted files 
@@             Coverage Diff             @@
##           dev-1.x    #2597      +/-   ##
===========================================
- Coverage    80.78%   80.51%   -0.27%     
===========================================
  Files          230      233       +3     
  Lines        14474    14660     +186     
  Branches      2508     2544      +36     
===========================================
+ Hits         11693    11804     +111     
- Misses        2135     2204      +69     
- Partials       646      652       +6
Flag Coverage Δ
unittests 80.51% <60.97%> (-0.27%) ⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files Changed Coverage Δ
mmpose/apis/inferencers/pose3d_inferencer.py 85.00% <0.00%> (+2.27%) ⬆️
...mpose/apis/inferencers/utils/default_det_models.py 100.00% <ø> (ø)
mmpose/datasets/transforms/formatting.py 79.76% <ø> (ø)
mmpose/evaluation/metrics/coco_wholebody_metric.py 96.62% <ø> (ø)
...s/heads/regression_heads/motion_regression_head.py 69.69% <0.00%> (+40.90%) ⬆️
...heads/regression_heads/temporal_regression_head.py 54.00% <0.00%> (-16.00%) ⬇️
mmpose/visualization/local_visualizer_3d.py 54.97% <ø> (ø)
mmpose/apis/inference_3d.py 30.92% <16.66%> (-14.72%) ⬇️
mmpose/visualization/opencv_backend_visualizer.py 41.34% <25.00%> (-0.82%) ⬇️
mmpose/apis/visualization.py 28.12% <28.12%> (ø)
... and 11 more

... and 3 files with indirect coverage changes

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Tau-J
Tau-J approved these changes Aug 10, 2023
View reviewed changes
Copy link
Collaborator

@Tau-J Tau-J left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@Tau-J Tau-J merged commit 94d4f50 into open-mmlab:dev-1.x Aug 10, 2023
@xin-li-67 xin-li-67 deleted the deepfashion_tdhm branch August 10, 2023 08:19
Tau-J added a commit that referenced this pull request Oct 12, 2023
@Tau-J @Ben-Louis
@LareinaM @xin-li-67 @Indigo6 @xiexinch @tpoisonooo @crazysteeaam @yzd-v @chaodyna @lwttttt @k-yomo @LiuYi-Up @ZhaoQiiii @Yang-Changhui @juxuan27
Dev 1.x (#2752)
6d10b2e 
* update

* [Fix] Fix HRFormer log link

* [Feature] Add Application 'Just dance' (#2528)

* [Docs] Add advanced tutorial of implement new model. (#2539)

* [Doc] Update img (#2541)

* [Feature] Support MotionBERT (#2482)

* [Fix] Fix demo scripts (#2542)

* [Fix] Fix Pose3dInferencer keypoint shape bug (#2543)

* [Enhance] Add notifications when saving visualization results (#2545)

* [Fix] MotionBERT training and flip-test (#2548)

* [Docs] Enhance docs (#2555)

* [Docs] Fix links in doc (#2557)

* [Docs] add details (#2558)

* [Refactor] 3d human pose demo (#2554)

* [Docs] Update MotionBERT docs (#2559)

* [Refactor] Update the arguments of 3d inferencer to align with the demo script (#2561)

* [Enhance] Combined dataset supports custom sampling ratio (#2562)

* [Docs] Add MultiSourceSampler docs (#2563)

* [Doc] Refine docs (#2564)

* [Feature][MMSIG] Add UniFormer Pose Estimation to Projects folder (#2501)

* [Fix] Check the compatibility of inferencer's input/output  (#2567)

* [Fix]Fix 3d visualization (#2565)

* [Feature] Add bear example in just dance (#2568)

* [Doc] Add example and openxlab link for just dance (#2571)

* [Fix] Configs' paths of VideoPose3d (#2572)

* [Docs] update docs (#2573)

* [Fix] Fix new config bug in train.py (#2575)

* [Fix] Configs' of MotionBERT (#2574)

* [Enhance] Normalization option in 3d human pose demo and inferencer (#2576)

* [Fix] Fix the incorrect labels for training vis_head with combined datasets (#2550)

* [Enhance] Enhance 3dpose demo and docs (#2578)

* [Docs] Enhance Codecs documents (#2580)

* [Feature] Add DWPose distilled WholeBody RTMPose models (#2581)

* [Docs] Add deployment docs (#2582)

* [Fix] Refine 3dpose (#2583)

* [Fix] Fix config typo in rtmpose-x (#2585)

* [Fix] Fix 3d inferencer (#2593)

* [Feature] Add a simple visualize api (#2596)

* [Feature][MMSIG] Support badcase analyze in test (#2584)

* [Fix] fix bug in flip_bbox with xyxy format (#2598)

* [Feature] Support ubody dataset (2d keypoints) (#2588)

* [Fix] Fix visualization bug in 3d pose (#2594)

* [Fix] Remove use-multi-frames option (#2601)

* [Enhance] Update demos (#2602)

* [Enhance] wholebody support  openpose style visualization (#2609)

* [Docs] Documentation regarding 3d pose (#2599)

* [CodeCamp2023-533] Migration Deepfashion topdown heatmap algorithms to 1.x (#2597)

* [Fix] fix badcase hook (#2616)

* [Fix] Update dataset mim downloading source to OpenXLab (#2614)

* [Docs] Update docs structure (#2617)

* [Docs] Refine Docs (#2619)

* [Fix] Fix numpy error (#2626)

* [Docs] Update error info and docs (#2624)

* [Fix] Fix inferencer argument name (#2627)

* [Fix] fix links for coco+aic hrnet (#2630)

* [Fix] fix a bug when visualize keypoint indices (#2631)

* [Docs] Update rtmpose docs (#2642)

* [Docs] update README.md (#2647)

* [Docs] Add onnx of RTMPose models (#2656)

* [Docs] Fix mmengine link (#2655)

* [Docs] Update QR code (#2653)

* [Feature] Add DWPose (#2643)

* [Refactor] Reorganize distillers (#2658)

* [CodeCamp2023-259]Document Writing: Advanced Tutorial - Custom Data Augmentation (#2605)

* [Docs] Fix installation docs(#2668)

* [Fix] Fix expired links in README (#2673)

* [Feature] Support multi-dataset evaluation (#2674)

* [Refactor] Specify labels to pack in codecs (#2659)

* [Refactor] update mapping tables (#2676)

* [Fix] fix link (#2677)

* [Enhance] Enable CocoMetric to get ann_file from MessageHub (#2678)

* [Fix] fix vitpose pretrained ckpts (#2687)

* [Refactor] Refactor YOLOX-Pose into mmpose core package (#2620)

* [Fix] Fix typo in COCOMetric(#2691)

* [Fix] Fix bug raised by changing bbox_center to input_center (#2693)

* [Feature] Surpport EDPose for inference(#2688)

* [Refactor] Internet for 3d hand pose estimation (#2632)

* [Fix] Change test batch_size of edpose to 1 (#2701)

* [Docs] Add OpenXLab Badge (#2698)

* [Doc] fix inferencer doc (#2702)

* [Docs] Refine dataset config tutorial (#2707)

* [Fix] modify yoloxpose test settings (#2706)

* [Fix] add compatibility for argument `return_datasample` (#2708)

* [Feature] Support ubody3d dataset (#2699)

* [Fix] Fix 3d inferencer (#2709)

* [Fix] Move ubody3d dataset to wholebody3d (#2712)

* [Refactor] Refactor config and dataset file structures (#2711)

* [Fix] give more clues when loading img failed (#2714)

* [Feature] Add demo script for 3d hand pose  (#2710)

* [Fix] Fix Internet demo (#2717)

* [codecamp: mmpose-315] 300W-LP data set support (#2716)

* [Fix] Fix the typo in YOLOX-Pose (#2719)

* [Feature] Add detectors trained on humanart (#2724)

* [Feature] Add RTMPose-Wholebody (#2721)

* [Doc] Fix github action badge in README (#2727)

* [Fix] Fix bug of dwpose (#2728)

* [Feature] Support hand3d inferencer (#2729)

* [Fix] Fix new config of RTMW (#2731)

* [Fix] Align visualization color of 3d demo (#2734)

* [Fix] Refine h36m data loading and add head_size to PackPoseInputs (#2735)

* [Refactor] Align test accuracy for AE (#2737)

* [Refactor] Separate evaluation mappings from KeypointConverter (#2738)

* [Fix] MotionbertLabel codec (#2739)

* [Fix] Fix mask shape (#2740)

* [Feature] Add training datasets of RTMW (#2743)

* [Doc] update RTMPose README (#2744)

* [Fix] skip warnings in demo (#2746)

* Bump 1.2 (#2748)

* add comments in dekr configs (#2751)

---------

Co-authored-by: Peng Lu <penglu2097@gmail.com>
Co-authored-by: Yifan Lareina WU <mhsj16lareina@gmail.com>
Co-authored-by: Xin Li <7219519+xin-li-67@users.noreply.github.com>
Co-authored-by: Indigo6 <40358785+Indigo6@users.noreply.github.com>
Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
Co-authored-by: tpoisonooo <khj.application@aliyun.com>
Co-authored-by: zhengjie.xu <jerryxuzhengjie@gmail.com>
Co-authored-by: Mesopotamia <54797851+yzd-v@users.noreply.github.com>
Co-authored-by: chaodyna <li0331_1@163.com>
Co-authored-by: lwttttt <85999869+lwttttt@users.noreply.github.com>
Co-authored-by: Kanji Yomoda <Kanji.yy@gmail.com>
Co-authored-by: LiuYi-Up <73060646+LiuYi-Up@users.noreply.github.com>
Co-authored-by: ZhaoQiiii <102809799+ZhaoQiiii@users.noreply.github.com>
Co-authored-by: Yang-ChangHui <71805205+Yang-Changhui@users.noreply.github.com>
Co-authored-by: Xuan Ju <89566272+juxuan27@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Tau-J Tau-J Tau-J approved these changes

Assignees

@LareinaM LareinaM

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@xin-li-67 @Tau-J @LareinaM