https://github.com/collaborative-ai/multimodal-llm

https://github.com/collaborative-ai/multimodal-llm

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/collaborative-ai/multimodal-llm
• Owner: Collaborative-AI
• License: mit
• Created: 2024-05-28T05:46:36.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-06-03T07:01:42.000Z (7 months ago)
• Last Synced: 2024-06-03T09:57:51.490Z (7 months ago)
• Language: Python
• Size: 524 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# RPipe

Research Pipeline

 

## Requirements

See `requirements.txt`

## Instructions

- Use `make.sh` to generate run script

- Use `make.py` to generate exp script

- Use `process.py` to process exp results

- Hyperparameters can be found in `config.yml` and `process_control()` in `module/hyper.py`

## Examples

 - Generate run script

    ```ruby

    bash make.sh

    ```

 - Generate run script

    ```ruby

    python make.py --mode base

    ```

 - Train with MNIST and linear model

    ```ruby

    python train_model.py --control_name MNIST_linear

    ```

 - Test with CIFAR10 and resnet18 model

    ```ruby

    python test_model.py --control_name CIFAR10_resnet18

    ```

 - Process exp results

    ```ruby

    python process.py

    ```

## Results

- Learning curves of MNIST







- Learning curves of CIFAR10







## Acknowledgements

*Enmao Diao*