jfzhang95 / pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
MIT License
1.16k stars 250 forks source link

Not running on official splits without validation #64

Open mbilalshaikh opened 2 years ago

mbilalshaikh commented 2 years ago

for ucf101 I have modified the preprocess code and generated official splits But this code is producing below error.

Need help.

pytorch-video-recognition/dataloaders/dataset.py", line 294, in crop time_index = np.random.randint(buffer.shape[0] - clip_len) File "mtrand.pyx", line 747, in numpy.random.mtrand.RandomState.randint File "_bounded_integers.pyx", line 1254, in numpy.random._bounded_integers._rand_int64 ValueError: low >= high

jacklove233 commented 2 years ago

对于 ucf101,我修改了预处理代码并生成了官方拆分 但此代码产生以下错误。

需要帮忙。

pytorch-video-recognition/dataloaders/dataset.py”,第 294 行,在裁剪 time_index = np.random.randint(buffer.shape[0] - clip_len) 文件“mtrand.pyx”,第 747 行,在 numpy.random 中。 mtrand.RandomState.randint 文件“_bounded_integers.pyx”,第 1254 行,在 numpy.random._bounded_integers._rand_int64 值错误 :低 >= 高

Have you solved this problem now? Can you tell me how to solve it?