-
Notifications
You must be signed in to change notification settings - Fork 50
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Neural network arch displayed by Netron is wrong #22
Comments
Another question, refer to the paper for recommended input shapes, it's [b, t, h, w, c], but i have checked your input shapes when using HMDB51 datasets, it's [b, c, t, h, w]. why didn't you use the same input shapes? |
Dear @erwangccc i think u reapeated a basic mistake as i did it too. Never ever save torch model like save(model,/.pth) or like that do torch.save(model.state_dict(),/.pth) then see it in netron again .I wasted one month literally llike this. If u dont see difference let me know |
Hi, @papasanimohansrinivas Thanks for your reply. I've tried this way you mentioned before and just weights are displayed. But it's not an interconnected model. I think we can look through the model via tensorborad. I see you've used movites in your case, well done. I have just add training phase to this repo and want to do inference frame-by-frame via model trained by this repo, do u have some tips and inference code to share, i'll appreciate it! |
@erwangccc sorry ! being late to reply ,caught up with my project . Ok I have combined pytorchvideo framework ucf101 dataloader and the evaluate and training functions used in this repos jupyter notebook to train my own model , inferences are good for my very small dataset I could have shared the code but my partner insists code repo of my project to be private etc And write your own custom video sampler to suit your needs , just that Wish u good luck |
Hi, @papasanimohansrinivas thanks for your reply. Did you inference frame-by- frame based on evaluation code? |
Hi @erwangccc no I do use movinet a5 base model and I accumulate all frames from a video and use uniformtemporalsubsample function from pytorchvideo to pass it to ucf101 class arguments for choosing nframes of video I do get where u are coming from ,No issues Below these are the functions to transform videos Just go through ucf101 class and see what are the requirements of it and I would fill in the gaps for anyone , I myself had faced same issues Besides I am trying to write code for movinets a3,a4,a5 streams models by extending this repo . |
OK, i see.
This means you want to train your data based on a3-5? If so, i think u can refer to implementation details from paper. |
Hi, @Atze00
i saved MoViNtes-A0 model to 'pth' and look through model by Netron, but the structure is a little strange. maybe there is something wrong at '_forward_impl' at class 'class MoViNet(nn.Module)'.
My code is as follows:
Please let me know if i did something wrong.
The text was updated successfully, but these errors were encountered: