Add folder for train.py and config the model to train on market's GPU, like RTX 3090 #40
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
bring-nirachornkul
commented
Jul 15, 2024
bring-nirachornkul
commented
- Add folder : interhuman_processed for train.py
- Add text file : ignore_list.txt, train.txt.
- Config the model to train on market's GPU, like RTX 3090
for taining.py
Reduced batch size from 32 to 16 Note : the original batch size require GPU VRAM 27 GBs which is uncommon for most GPU in the market. Reducing the batch size to 16 is allowed RTX 3090 (24 GBs Ram) run on it. You can change it to 32, in case you have more advance GPU.
Updated train.py to save only the latest checkpoint after each epoch using save_top_k=1, ensuring the previous checkpoint is deleted, and added a function to automatically resume from the latest checkpoint if available.
Author
|
Updated train.py to save only the latest checkpoint after each epoch using save_top_k=1, ensuring the previous checkpoint is deleted, and added a function to automatically resume from the latest checkpoint if available. |
This program will generate 1D tensor from CLIP output
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.