[New Algorithm] Support DG-STGCN (kennymckormick#110)

* remove test_mode in config files

* remove test_mode in data pipeline

* support dgstgcn

* add deperacate warning

* update file cache

* update dg-stgcn

* Add DG-STGCN configs

* update pre-commit

* fix pre-commit

.pre-commit-config.yaml

@@ -4,18 +4,14 @@ exclude: >
       ^configs/
   )$
 repos:
-  - repo: https://gitlab.com/pycqa/flake8.git
-    rev: 3.8.3
+  - repo: https://github.com/PyCQA/flake8
+    rev: 5.0.4
     hooks:
       - id: flake8
         args: ["--max-line-length=120"]
         exclude: ^configs/
-  - repo: https://github.com/asottile/seed-isort-config
-    rev: v2.2.0
-    hooks:
-      - id: seed-isort-config
-  - repo: https://github.com/timothycrosley/isort
-    rev: 4.3.21
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.10.1
     hooks:
       - id: isort
   - repo: https://github.com/pre-commit/mirrors-yapf

README.md

@@ -1,6 +1,8 @@
 # PYSKL
 
-[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/revisiting-skeleton-based-action-recognition/skeleton-based-action-recognition-on-ntu-rgbd)](https://paperswithcode.com/sota/skeleton-based-action-recognition-on-ntu-rgbd?p=revisiting-skeleton-based-action-recognition) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/pyskl-towards-good-practices-for-skeleton/skeleton-based-action-recognition-on-ntu-rgbd-1)](https://paperswithcode.com/sota/skeleton-based-action-recognition-on-ntu-rgbd-1?p=pyskl-towards-good-practices-for-skeleton) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/revisiting-skeleton-based-action-recognition/skeleton-based-action-recognition-on-kinetics)](https://paperswithcode.com/sota/skeleton-based-action-recognition-on-kinetics?p=revisiting-skeleton-based-action-recognition)
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/revisiting-skeleton-based-action-recognition/skeleton-based-action-recognition-on-ntu-rgbd)](https://paperswithcode.com/sota/skeleton-based-action-recognition-on-ntu-rgbd?p=revisiting-skeleton-based-action-recognition)
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dg-stgcn-dynamic-spatial-temporal-modeling/skeleton-based-action-recognition-on-ntu-rgbd-1)](https://paperswithcode.com/sota/skeleton-based-action-recognition-on-ntu-rgbd-1?p=dg-stgcn-dynamic-spatial-temporal-modeling)
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/revisiting-skeleton-based-action-recognition/skeleton-based-action-recognition-on-kinetics)](https://paperswithcode.com/sota/skeleton-based-action-recognition-on-kinetics?p=revisiting-skeleton-based-action-recognition)
 
 PYSKL is a toolbox focusing on action recognition based on **SK**e**L**eton data with **PY**Torch. Various algorithms will be supported for skeleton-based action recognition. We build this project based on the OpenSource Project [MMAction2](https://github.com/open-mmlab/mmaction2).
 
@@ -19,14 +21,15 @@ Any user can open a PR to contribute to PYSKL. The PR will be reviewed before be
 
 ## News
 
+- Support [DG-STGCN](https://arxiv.org/abs/2210.05895), which is a state-of-the-art skeleton action algorithm that doesn't rely on a pre-defined graph (**2022-12-12**).
 - The [tech report](https://arxiv.org/abs/2205.09443) of PYSKL is accepted by MM 2022 (**2022-06-28**).
 - Support spatial augmentations and provide a benchmark on ST-GCN++  (**2022-05-12**).
 - Support skeleton action recognition demo with GCN algorithms  (**2022-05-03**).
 - Release the skeleton annotations (HRNet 2D Pose), config files, and pre-trained ckpts for Kinetics-400. K400 is a large-scale dataset (even for skeleton), you should have `memcached` and `pymemcache` installed for efficient training & testing on K400 (**2022-05-01**).
-- Provide an example (diving48) for processing a custom video dataset, generating 2D skeleton annotations, and using PoseC3D for skeleton-based action recognition. The tutorial for skeleton extraction part is available in [diving48_example](/examples/extract_diving48_skeleton/diving48_example.ipynb)  (**2022-04-15**).
 
 ## Supported Algorithms
 
+- [x] DG-STGCN (Arxiv): https://arxiv.org/abs/2210.05895 [[MODELZOO](/configs/dgstgcn/README.md)]
 - [x] ST-GCN (AAAI 2018): https://arxiv.org/abs/1801.07455 [[MODELZOO](/configs/stgcn/README.md)]
 - [x] ST-GCN++ (PYSKL, Tech Report): https://arxiv.org/abs/2205.09443 [[MODELZOO](/configs/stgcn++/README.md)]
 - [x] PoseConv3D (CVPR 2022 Oral): https://arxiv.org/abs/2104.13586 [[MODELZOO](/configs/posec3d/README.md)]

configs/aagcn/aagcn_pyskl_ntu120_xset_3dkp/b.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xset_3dkp/bm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xset_3dkp/j.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xset_3dkp/jm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xset_hrnet/b.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xset_hrnet/bm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xset_hrnet/j.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xset_hrnet/jm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['jm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['jm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xsub_3dkp/b.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xsub_3dkp/bm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xsub_3dkp/j.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xsub_3dkp/jm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xsub_hrnet/b.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xsub_hrnet/bm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xsub_hrnet/j.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu120_xsub_hrnet/jm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['jm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize2D'),
     dict(type='GenSkeFeat', dataset='coco', feats=['jm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu60_xsub_3dkp/b.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu60_xsub_3dkp/bm.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),

configs/aagcn/aagcn_pyskl_ntu60_xsub_3dkp/j.py

@@ -19,7 +19,7 @@
 val_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=1, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=1),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),
@@ -28,7 +28,7 @@
 test_pipeline = [
     dict(type='PreNormalize3D'),
     dict(type='GenSkeFeat', dataset='nturgb+d', feats=['j']),
-    dict(type='UniformSample', clip_len=100, num_clips=10, test_mode=True),
+    dict(type='UniformSample', clip_len=100, num_clips=10),
     dict(type='PoseDecode'),
     dict(type='FormatGCNInput', num_person=2),
     dict(type='Collect', keys=['keypoint', 'label'], meta_keys=[]),