Tony Qian
Tony Qian
A similar problem using Windows ``` Collecting ffcv Using cached ffcv-0.0.3.tar.gz (53 kB) Preparing metadata (setup.py) ... error error: subprocess-exited-with-error × python setup.py egg_info did not run successfully. │ exit...
@woodenchild Hi, Thank you for the suggestion. I wonder if you are using the setting as ` conda create -y -n ffcv python=3.9 cupy pkg-config compilers libjpeg-turbo opencv pytorch torchvision...
similar issue, I'm using WSL2 with Ubuntu 20.04 error is ``` Collecting git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch Cloning https://github.com/NVlabs/tiny-cuda-nn/ to /tmp/pip-req-build-r_hre1hk Running command git clone --filter=blob:none --quiet https://github.com/NVlabs/tiny-cuda-nn/ /tmp/pip-req-build-r_hre1hk Resolved https://github.com/NVlabs/tiny-cuda-nn/ to commit a77dc53ed770dd8ea6f78951d5febe175d0045e9...
Could you please also provide the detailed linear classifier structure and related key parameters? I tried using a simple MLP (with just two linear layers) on the UCF dataset but...
Hi! Thanks for your quick response. The accuracy after 10 epochs I got is around 5%. So I guess there is probably something I didn't do right. I tried a...
code: ``` # Dataset Class class UCFDataset(torch.utils.data.Dataset): def __init__(self, dataset_dir, subset, video_list_file, frames_per_clip=16): super().__init__() self.dataset_dir = dataset_dir self.video_dir = video_dir self.subset=subset self.video_list_file = video_list_file self.video_list = [] self.labels = []...
> Thanks, I'll try to have a more thorough look at it in the following days. > > Some points that might cause the problem: > > * maybe try...
Problem solved, it was due to a bug in dataloader at val dataloader initialization. Thank you @pierrefdz and feel free to close this issue.
Hello @Enderfga, just wonder are you able to figure this out, or have any progress with this? @araistrick Since you mentioned there are "millions" of numbers, will you plan to...
I see, thank you both for sharing the info! A quick follow-up for @araistrick's comment, are those major random variables also user-interpretable or they are not? I believe it would...