layumi / layumi/Image-Text-Embedding
The loss on COCO dataset of training stage1 dosen't decrease
Nobody has claimed this yet.
- Dominant language
- MATLAB
- Stars
- 296
- Forks
- 72
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I run the train_coco_word2_1_pool.m, but after more than 10 epochs, I found the train result is still bad(as below). I didn't change any hyper parameters but I don't know why it doesn't work.
Can you tell me what make this result happen? And I found the learning rate in your code is 0.1, but it's reported as 0.001 in the paper. Which lr is correct and better in this task?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with train_coco_word2_1_pool.m and reproduce the reported training behavior for more than 10 epochs without changing hyperparameters. Compare the code's learning rate of 0.1 with the 0.001 value reported in the paper, and use the training output and attached result to determine whether the loss behavior or learning-rate discrepancy needs correction. Done means identifying the cause and documenting the correct setting.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- matlab
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100