https://github.com/supersecurehuman/selective-kernel-networks
https://github.com/supersecurehuman/selective-kernel-networks
Last synced: about 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/supersecurehuman/selective-kernel-networks
- Owner: SuperSecureHuman
- License: mit
- Created: 2022-12-24T15:33:24.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-03-13T12:43:15.000Z (over 3 years ago)
- Last Synced: 2024-04-17T23:55:46.987Z (about 2 years ago)
- Language: Jupyter Notebook
- Size: 3.17 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Selective Kernel Networks for Chest X-Ray Classification
This repository contains the code to evaluate the performance of the Selective Kernel Networks (SKN) on the Chest X-Ray dataset.
## Requirements
The code is written in Python 3.6. The required packages are listed in the requirements.txt file.
## Data
## Usage
timm_train.py deals with the training of the model using the TIMM library. This was used to get the final results.
Sample code to run the code:
```bash
python timm_train.py --learning_rate=0.00005 --epochs=30 --batch_size=32 --model="resnet18" --wandb=True --data="/Covid_Radiography_Project/Dataset/Balanced" --seed=10 --image_size=224
```