View Code? Open in Web Editor
NEW
solution for object detection problem in ChestXray-NIHCC dataset
Shell 0.15%
Python 8.83%
Jupyter Notebook 91.02%
chestxray-nihcc-detection's Introduction
- Clone the repository
- Run the following command in the terminal
bash install_requirements.sh
- For MLFLOW setup on aws instance do.
sudo apt-get update && \
sudo apt-get install -y python3-pip python3-venv unzip && \
python3 -m venv venv && \
source venv/bin/activate && \
pip install mlflow psycopg2-binary boto3 setuptools && \
curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip" && \
unzip awscliv2.zip && \
sudo ./aws/install && \
mlflow server -h 0.0.0.0 --default-artifact-root s3://<your-s3-bucket>
- BBox annotation data is in
data/ folder.
- Adjust configs
- To train
- on kaggle/colab you can use
EDA/nih-chestxray_kaggle.ipyb
- onpremiss
!cd ChestXrayCC-detection && MLFLOW_EXPERIMENT_NAME=chestxray_notebook AWS_ACCESS_KEY_ID=<AWS_ACCESS_KEY_ID> AWS_SECRET_ACCESS_KEY=<AWS_SECRET_ACCESS_KEY> bash scripts/dist_train.sh configs/yolox/yolox_tiny_8xb8-300e_coco_notebook.py 2 --run-name coco_pretrained
chestxray-nihcc-detection's People
Contributors
Watchers
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent