Fix.

Minor.
open-mmlab · Nov 30, 2020 · c1e72e9 · c1e72e9
1 parent 6dc009b
commit c1e72e9
Show file tree

Hide file tree

Showing 4 changed files with 3 additions and 161 deletions.
diff --git a/configs/recognition_audio/audioonly/README.md b/configs/recognition_audio/audioonly/README.md
diff --git a/configs/recognition_audio/resnet/README.md b/configs/recognition_audio/resnet/README.md
@@ -17,7 +17,6 @@
 |config | n_fft | gpus | backbone |pretrain| top1 acc/delta| top5 acc/delta | inference_time(video/s) | gpu_mem(M)| ckpt | log| json|
 |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
 |[tsn_r18_64x1x1_100e_kinetics400_audio_feature](/configs/recognition_audio/resnet/tsn_r18_64x1x1_100e_kinetics400_audio_feature.py)|1024|8| ResNet18 | None |19.7|35.75|x|1897|[ckpt](https://download.openmmlab.com/mmaction/recognition/audio_recognition/tsn_r18_64x1x1_100e_kinetics400_audio_feature/tsn_r18_64x1x1_100e_kinetics400_audio_feature_20201012-bf34df6c.pth)|[log](https://download.openmmlab.com/mmaction/recognition/audio_recognition/tsn_r18_64x1x1_100e_kinetics400_audio_feature/20201010_144630.log)|[json](https://download.openmmlab.com/mmaction/recognition/audio_recognition/tsn_r18_64x1x1_100e_kinetics400_audio_feature/20201010_144630.log.json)|
-|[tsn_r50_64x1x1_100e_kinetics400_audio_feature](/configs/recognition_audio/resnet/tsn_r50_64x1x1_100e_kinetics400_audio_feature.py)|1024|8| ResNet50 | None |17.58|32.54|x|5811|[ckpt](https://download.openmmlab.com/mmaction/recognition_audio/tsn_r50_64x1x1_100e_kinetics400_audio_feature/tsn_r50_64x1x1_100e_kinetics400_audio_feature_20201127-b5df6b97.pth)|[log](https://download.openmmlab.com/mmaction/recognition_audio/tsn_r50_64x1x1_100e_kinetics400_audio_feature/20201123_175429.log)|[json](https://download.openmmlab.com/mmaction/recognition_audio/tsn_r50_64x1x1_100e_kinetics400_audio_feature/20201123_175429.log.json)|
 |[tsn_r18_64x1x1_100e_kinetics400_audio_feature](/configs/recognition_audio/resnet/tsn_r18_64x1x1_100e_kinetics400_audio_feature.py) + [tsn_r50_video_320p_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_320p_1x1x3_100e_kinetics400_rgb.py)|1024|8| ResNet(18+50) | None |71.50(+0.39)|90.18(+0.14)|x|x|x|x|x|
 
 Notes:

diff --git a/configs/recognition_audio/resnet/tsn_r50_64x1x1_100e_kinetics400_audio_feature.py b/configs/recognition_audio/resnet/tsn_r50_64x1x1_100e_kinetics400_audio_feature.py
diff --git a/mmaction/datasets/audio_visual_dataset.py b/mmaction/datasets/audio_visual_dataset.py
@@ -6,8 +6,9 @@
 
 @DATASETS.register_module
 class AudioVisualDataset(RawframeDataset):
-    """Dataset that read both audio and visual, supporting both rawframes and
-    videos. Annotation file can be that of the rawframe dataset, such as:
+    """Dataset that reads both audio and visual data, supporting both rawframes
+    and videos. The annotation file is same as that of the rawframe dataset,
+    such as:
 
     .. code-block:: txt