double-fire-0 issues

Results 10 issues of


double-fire-0

Error when reading the IMAGENET-P videos

Error information: VIDIOC_REQBUFS: Inappropriate ioctl for device It seems to be a problem about FFmpeg video reader. It's wear that it occurs at some time, and sometimes won't

TypeError: endswith first arg must be str or a tuple of str, not list

`File"/mnt/lustre/share/spring/conda_envs/miniconda3/envs/s0.3.3/lib/python3.6/sitepackages/torchvision/datasets/folder.py", line 19, in has_file_allowed_extension return filename.lower().endswith(extensions) TypeError: endswith first arg must be str or a tuple of str, not list` I find this error and solve this error by...

Is there anybody do the experiment to see whether this code base align the accuracy with the BYOL paper?

Thanks for providing the excellent code for BYOL I just wander is there anybody do the experiment to see whether this code base align the accuracy with the BYOL paper?

Could you note where the code about ActionVLAD layer? Thanks!

Is the best model on GOPRO dataset is trained on 256x256 image size or 1280x720 ?

In the config.yaml file, your model seems like are trained on 256x256 image size. But the resolution in paper is 1280x720. Can you provided the config.yaml which is used to...

What's the resolution of videos when eval on GoPro dataset in your paper? And any advice about the resolution when doing video debluring?

In Table 2 of your paper, you report the result of your model on GoPro dataset. At what resolution did you get this result? And can you give some advice...

ResolvePackageNotFound:

From the Colab, I see the code `!conda install -q -y --prefix /usr/local -c pytorch -c tensorcomp tensor_comprehensions` And the package tensor_comprehensions only have a Linux version. And I can't...

Any one get any video result by training this project?

Will you try to align the accuracy to the paper based on the official tensorflow code ?

The offical code: https://github.com/google-research/pix2seq

Does this code support resume training

The training is break during my training process. Does this code support resume training? I notice that the code can resume model at https://github.com/ali-vilab/VGen/blob/7ad0f25df50b2c35d7eb95cbabdf772c5b9761c8/tools/train/train_t2v_enterance.py#L154 but it seems that the code...