pytorch-video-recognition
pytorch-video-recognition copied to clipboard
jfzhang95
PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
Hi! I wonder if we should download the dataset from the Internet by ourselves, and it doesn't offer the dataset. If it does, could you tell me where I can...
Anybody knows the database which the pretrained model was trained from?
what's the meaning of normalize?where the [98 100 102] comes from？ what's more C3D_model is different from the paper C3D,like the dropout there are many wrong in this code,please check...
This error shows after running python train.py and after counting train/val/test videos. ``` Traceback (most recent call last): File "train.py", line 202, in train_model() File "train.py", line 123, in train_model...
---> 32 model.load_state_dict(checkpoint['state_dict']) 33 # model.load_state_dict(torch.load("C:\\Users\####\pytorch-video-recognition\c3d-pretrained.pth.tar", map_location=lambda storage, loc: storage)) 34 KeyError: 'state_dict'
视频转换图片转换不出来，错误提示：os.listdir(os.path.join(self.output_dir, 'train', video_class, video)))[0]) IndexError: list index out of range。不知道是什么原因，有人不知道吗，谢谢。 英文：Video conversion image can’t be converted, error prompt: os.listdir(os.path.join(self.output_dir,'train', video_class, video)))[0]) IndexError: list index out of range. I don’t know...
clip_len (int): Determines how many frames are there in each clip. Defaults to 16. But when I open the folder of the preprocessed video I see more than 16 images,...
I tested the videos in UCF101 on the trained VGG19 network (the training accuracy rate has reached 85%), but the results I got were all wrong classification. May I ask...
Did anyone run dataset.py? I try to run the file, but it seems that it doesn't run. When I run the following code ``` for i, sample in enumerate(train_loader): inputs...