Instructions to use 360TechEnv/waste-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use 360TechEnv/waste-classifier with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://360TechEnv/waste-classifier") - Notebooks
- Google Colab
- Kaggle
Download docker-compose.yml from 360TechEnv/waste-classifier: direct link, hf CLI and curl.
- Browser
- Download file 874 Bytes
-
https://huggingface.co/360TechEnv/waste-classifier/resolve/main/docker-compose.yml
- Command line
-
hf download hf://360TechEnv/waste-classifier/docker-compose.yml
-
curl -L -o docker-compose.yml https://huggingface.co/360TechEnv/waste-classifier/resolve/main/docker-compose.yml
874 Bytes
| version: '3.8' | |
| services: | |
| waste-classifier: | |
| build: | |
| context: . | |
| dockerfile: Dockerfile | |
| container_name: waste-classifier-app | |
| ports: | |
| - "8501:8501" | |
| volumes: | |
| # Volume pour persister les modèles téléchargés | |
| - model_cache:/app/models | |
| # Volume pour les logs (optionnel) | |
| - ./logs:/app/logs | |
| environment: | |
| - STREAMLIT_SERVER_PORT=8501 | |
| - STREAMLIT_SERVER_ADDRESS=0.0.0.0 | |
| - STREAMLIT_SERVER_HEADLESS=true | |
| - STREAMLIT_BROWSER_GATHER_USAGE_STATS=false | |
| restart: unless-stopped | |
| healthcheck: | |
| test: ["CMD", "curl", "-f", "http://localhost:8501/_stcore/health"] | |
| interval: 30s | |
| timeout: 10s | |
| retries: 3 | |
| start_period: 40s | |
| networks: | |
| - waste-classifier-network | |
| volumes: | |
| model_cache: | |
| driver: local | |
| networks: | |
| waste-classifier-network: | |
| driver: bridge | |