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
Division by zero #4
Comments
Hi, @Michaelwhite34. Is Cuda available on your device? |
Yes,I have a gtx 1660Ti,by the way it's on windows 10. |
I've never tried running PyTorch on Windows. Or, you can just set |
After setting it to 0,(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch |
You will need to find a way to get cuda version in Windows (which is |
nvidia-smi |
I meant to find a way to replace this line for Windows, but, since your machine has cuda 11, try replacing these 4 lines to I hope the correlation layer needed for the lineFlowNet is installed without problem for Windows (I can't help with that). |
(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch Loading checkpoint 'PVDNet_large_nah.pytorch' on model 'PVDNet_large_nah': |
That means the evaluation has never gone through a loop. Make sure the test set is in the right place. |
My sequence structure is D:\PVDNet\datasets\video_deblur\random\1\ *.png ...Is this not right ? |
I believe it is right. Did you change data_offset? |
No,should I change it ? |
emm,should I just unmark the line "config.data_offset = 'datasets/video_deblur" ? |
Set it to |
(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch |
It says indentation error. Check the indentation. |
Still Loading checkpoint 'PVDNet_large_nah.pytorch' on model 'PVDNet_large_nah': |
Try to use '\' for I will be out for a few hours. I am pretty sure it is the path problem. |
I am using \ already |
Here, you are using '/'. |
I changed after that. |
Do I need to change the line "config.data = 'DVD' # 'nah'"? |
No, it is given in |
still (PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch Loading checkpoint 'PVDNet_large_nah.pytorch' on model 'PVDNet_large_nah': |
Would you replace this line to the following lines and print out the result?
|
Got it working,turns out I should use "/" |
Great! |
Can we deal with cuda out of memory? |
You may try smaller model e.g., |
(PVDNet) PS D:\PVDNet> python run.py --mode PVDNet_large_nah --config config_PVDNet_large --data random --ckpt_abs_name ckpt/PVDNet_large_nah.pytorch
Laoding Config for evaluation
Traceback (most recent call last):
File "run.py", line 311, in
config = config_lib.get_config(args.project, args.mode, args.config)
File "D:\PVDNet\configs\config_PVDNet_large.py", line 42, in get_config
IpE = math.ceil((len(list(range(0, total_frame_num - (config.frame_itr_num-1), config.frame_itr_num)))) / actual_batch_size) * config.frame_itr_num
ZeroDivisionError: division by zero
The text was updated successfully, but these errors were encountered: