Giters
Cyanogenoid
/
pytorch-vqa
Strong baseline for visual question answering
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
239
Watchers:
9
Issues:
21
Forks:
97
Cyanogenoid/pytorch-vqa Issues
AttributeError: module ‘torchvision.transforms’ has no attribute ‘Scale’
Closed
2 years ago
Comments count
3
Preprocessed path and vocabulary path issue
Closed
6 years ago
Comments count
3
Test the model
Updated
3 years ago
Comments count
5
EOFError: Ran out of input when training
Closed
5 years ago
Comments count
5
Mismatch in Computing Accuracy
Updated
4 years ago
Comments count
1
About attention showing in the pic
Updated
5 years ago
Runtime error with preprocess-images
Updated
5 years ago
concat or sum?
Closed
5 years ago
Comments count
4
Metric computation in training phase
Closed
6 years ago
Comments count
2
why attention use '+' instead of '*'
Closed
6 years ago
Comments count
1
ssd create issue
Closed
6 years ago
Comments count
1
Issue with train_loader and val_loader in train.py
Closed
6 years ago
Comments count
2
Large memory consume
Updated
6 years ago
Comments count
1
Working with abstract scenes VQA v1
Closed
6 years ago
Comments count
1
when running preprocess_images.py, "size mismatch" occured
Closed
6 years ago
Comments count
1
run without CUDA
Closed
6 years ago
Comments count
7
Information regarding training time
Closed
6 years ago
Comments count
1
answer normalization
Closed
7 years ago
Comments count
3
maximum q len
Closed
7 years ago
Comments count
2
Training time
Closed
7 years ago
Comments count
4
expanded size of the tensor (2048) must match the existing size (128)
Closed
7 years ago
Comments count
1