Closed Dhan800 closed 2 months ago
Hi! You can change the txt
into csv
.
Hi! You can change the
txt
intocsv
.
Thanks for your response. It didn't quite work. So I download the annotation file from uniformer's google drive and rename somesomev2_rgb_train_split.txt as train.csv. Then I encountered an error: TypeError: Caught TypeError in DataLoader worker process 0. mba/video_sm/datasets/ssv2.py", line 408, in getitem buffer = self.loadvideo_decord(sample, sample_rate_scale=scale_t) # T H W C File "/Downloads/VideoMamba/videomamba/video_sm/datasets/ssv2.py", line 543, in loadvideo_decord fname = os.path.join(self.prefix, fname) File "/anaconda3/envs/mamba/lib/python3.10/posixpath.py", line 90, in join genericpath._check_arg_types('join', a, *p) File "/anaconda3/envs/mamba/lib/python3.10/genericpath.py", line 152, in _check_arg_types raise TypeError(f'{funcname}() argument must be str, bytes, or ' TypeError: join() argument must be str, bytes, or os.PathLike object, not 'int64'. What I do is putting all video file in a folder and pass it as PREFIX and putting all annotations in a folder and passing it as DATA_PATH. Sorry if the question seems stupid. Thanks for your help.
Hi! You need to change the data format. Please check Google Drive.
Hello, I download the official data from the ssv2 data set official website. How should I organize the data for model training and evaluation?
I got this error when decompressing the data. How to solve it?
Dear author,
Uniformer doesn't provide train.csv file and the original annotation is json file. I am new to video so can you please provide more details about ssV2?
Thank you for your help.