Skip to content

issues Search Results · repo:sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning language:Python

Filter by

0 results
 (70 ms)

0 results

insgrvinod/a-PyTorch-Tutorial-to-Image-Captioning (press backspace or delete to remove)

Why are the BLEU scores from train.py different from those in eval.py? In my experiments, the BLEU scores computed in train.py were around 0.16, whereas those computed in eval.py were around 0.24.
  • ZhangYiyii
  • 1
  • Opened 
    on Apr 23
  • #206

Thanks for sharing the code I have a question since we use the cross entropy loss as the MAIN metric to determine the model performance on that train and validation my question is that do we use the TEACHER ...
  • ali4321143
  • Opened 
    on Dec 6, 2024
  • #205

While I am trying to get evaluation of the model through eval.py, BLEU 4 score is 0 for every beam. I noticed that no sequence is having end token even after 50 or 100 decoder iterations. What is the issue ...
  • BlackBeard009
  • Opened 
    on Nov 29, 2024
  • #204

can you explain that do we use the teacher forcing in the validation phase EVEN with no parmater update in order to compute the cross entropy loss like we do in training to measure model performance in ...
  • malikfahadsarwar
  • Opened 
    on Nov 21, 2024
  • #203

can you explain how you handle the pad token since in batches, we have to pad caption so that all have the same length then we feed that padded caption into the LSTM right? then how and where did you ignore ...
  • AyeshaSarwar
  • Opened 
    on Oct 20, 2024
  • #202

There are some issues with the code, including fatal errors, making it difficult to complete the experiment well.....
  • Le-up
  • 1
  • Opened 
    on May 15, 2024
  • #201

File F:\study\a-PyTorch-Tutorial-to-Image-Captioning-master\train.py , line 319, in validate _, preds = torch.max(scores, dim=2) IndexError: Dimension out of range (expected to be in range of [-2, 1], ...
  • Kevinskt
  • 1
  • Opened 
    on Feb 25, 2024
  • #200

Hello, can this model detect and recognize text in images containing text
  • qvqqa
  • 1
  • Opened 
    on Nov 24, 2023
  • #199

The model was trained on flicker8k, but the results achieved only half the BLEU-4 score mentioned by the authors (about 0.14-0.15). I have not modified any parameters in train.py. May I ask why such a ...
  • CallMeRabbit
  • 3
  • Opened 
    on Nov 24, 2023
  • #198

How to slove this problem in eval.py?
  • 19856100635
  • Opened 
    on Nov 8, 2023
  • #197
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub