open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
PythonApache-2.0
Pinned issues
Issues
- 1
[Bug] different performance about batch size on val pipeline and test pipeline
#2801 opened by rkdckddnjs9 - 1
[Bug] use tools/misc/clip_feature_extraction.py to extract feature from long video, dataloaders do not work
#2850 opened by fucker255 - 1
[Docs] Custom Models?
#2798 opened by SenmiaoORZ - 1
[Bug] demo.py does not work with MMCV2.2.0
#2852 opened by rmuraix - 0
Can adjust batch size on demo skeleton?
#2851 opened by spped2000 - 0
[Bug] In project "gesture recognition",the number of keypoints output by MMPOSE is inconsistent with the number of keypoints input by MMACTION
#2849 opened by wangbofei11 - 1
- 8
[Bug] long-video-demo raised AssertionError on assert crop_h == img_h or crop_w == img_w
#2783 opened by vba34520 - 0
[Bug]
#2848 opened by Sunshulong - 1
[Feature] How to get flops of the MMRecognizer3D?
#2794 opened by wukurua - 0
[Bug] Which demo supports reasoning rgbposec3d?
#2847 opened by aonihao1 - 0
- 1
- 0
GradCAM utils only support Recognizer2D & Recognizer3D.
#2840 opened by Ritatanz - 3
- 0
- 0
KeyError: 'ActionVisualizer is not in the mmengine::visualizer registry.[Bug]
#2837 opened by berengueradrian - 1
训练时空动作检测 ,如何处理类别不均衡的问题
#2797 opened by yuweiApp - 1
vis_cam.py not work in timesformer
#2835 opened by whiteswordLI - 0
[Bug] Training MVit with RawFrameDataset type
#2834 opened by maximefuchs - 0
[Bug] batch_size problem
#2832 opened by Sunshulong - 0
[Feature] Export the tsm_mobilnetv2 model to onnx format
#2829 opened by san-kou7 - 0
top1_acc is allways times 0f 0.5or0.00[Bug]
#2827 opened by Sunshulong - 0
train[Bug]
#2826 opened by Sunshulong - 0
train time[Bug]
#2825 opened by Sunshulong - 3
[Bug] File 'visualize_heatmap_volume' does not exist
#2796 opened by da13132 - 0
[Bug] VisualizationHook is not set in the `default_hooks` field of config. Please set `visualization=dict(type="VisualizationHook")`
#2824 opened by Qinziqi1996 - 2
Do we now support the method of Skeleton-based Spatio-Temporal Action Detection and Action Recognition
#2823 opened by SCsleepy - 3
[Bug] It is not possible to use "analysis_tools\get_flops.py" to get the number of parameters and calculations
#2822 opened by aonihao1 - 0
[Bug]
#2821 opened by maple0leaves - 0
- 3
[Bug] Fail to use confusion_matrix to RGBPoseC3D
#2815 opened by HoBeom - 1
- 1
[Docs] How to train a model with different inputs from different model feature and videos
#2805 opened by zeynepgokce - 1
[Docs]
#2809 opened by iamhamzahussain - 0
model zoo lost
#2804 opened by fengjingchehu - 0
[Bug] Use mmaction2 - main/configs/skeleton/posec3d/rgbpose_conv3d/rgbpose_conv3d py error for the demo
#2803 opened by aonihao1 - 2
[Docs] Custom Dataset Training with PoseC3D
#2800 opened by mohammed-alaa40123 - 0
[Docs]How to add YOLO target detection frame to frame people when reasoning in TimeSformer
#2799 opened by xqc-qc - 1
- 0
- 0
[Docs] Custom action localization dataset. anet_anno_train.json missing
#2787 opened by valentin-fngr - 0
[Docs] ACRN training on AVA dataset at 15 fps
#2785 opened by LorBordin - 0
Installation fails on macbook m2 [Docs]
#2784 opened by lizaibeim - 0
[Docs] 20分钟了解 MMAction2 框架设计,步骤2导入问题
#2779 opened by everglowgh - 0
[Docs] Fine-tuning ActionClip
#2778 opened by CarmelaCalabrese - 0
[Bug] How can I use clip_feature_extraction.py to input the rawframes , and then output the RGB features of each frame?
#2777 opened by Chenhongchang - 0
找不到rtmpose的ckpt[Bug]
#2775 opened by shiyuxin1999S - 0
[Feature] Rename the confusing argument 'format_shape' in ActionDataPreprocessor
#2773 opened by makecent - 0
get_flops.py[Bug]
#2772 opened by ChenZhenGui