CAMMA-public / rendezvous

A transformer-inspired neural network for surgical action triplet recognition from laparoscopic videos.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Cannot training

Ving2k2 opened this issue · comments

C:\Users\ADMIN\anaconda3\envs\myenv\lib\site-packages\torchvision\io\image.py:13: UserWarning: Failed to load image Python extension: [WinError 127] The specified procedure could not be found
warn(f"Failed to load image Python extension: {e}")
Configuring network ...
Traceback (most recent call last):
File "C:\Users\ADMIN\PycharmProjects\rendezvous\pytorch\run.py", line 304, in
dataset = dataloader.CholecT50(
File "C:\Users\ADMIN\PycharmProjects\rendezvous\pytorch\dataloader.py", line 102, in init
self.build_train_dataset(trainform)
File "C:\Users\ADMIN\PycharmProjects\rendezvous\pytorch\dataloader.py", line 172, in build_train_dataset
target_transform=self.target_transform)
AttributeError: 'CholecT50' object has no attribute 'target_transform'

Hi,
I have some problem when training the model. I use the dataloader.py in the repo CholecT50 of you. Do you have any suggest ? Thank you

You should use the dataloader_pth.py in cholect50 repository.