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:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://360TechEnv/waste-classifier") - Notebooks
- Google Colab
- Kaggle
Upload requirements.txt with huggingface_hub
Browse files- requirements.txt +35 -0
requirements.txt
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Dépendances pour l'entraînement du modèle de classification de déchets
|
| 2 |
+
|
| 3 |
+
# Deep Learning
|
| 4 |
+
tensorflow>=2.16.0
|
| 5 |
+
keras>=3.0.0
|
| 6 |
+
|
| 7 |
+
# Data Science et Machine Learning
|
| 8 |
+
numpy>=1.24.0
|
| 9 |
+
pandas>=2.0.0
|
| 10 |
+
scikit-learn>=1.3.0
|
| 11 |
+
|
| 12 |
+
# Visualisation
|
| 13 |
+
matplotlib>=3.7.0
|
| 14 |
+
seaborn>=0.12.0
|
| 15 |
+
|
| 16 |
+
# Image Processing
|
| 17 |
+
Pillow>=10.0.0
|
| 18 |
+
|
| 19 |
+
# Utilitaires
|
| 20 |
+
requests>=2.31.0
|
| 21 |
+
pathlib2>=2.3.7
|
| 22 |
+
|
| 23 |
+
# Logging et Configuration
|
| 24 |
+
tqdm>=4.65.0
|
| 25 |
+
|
| 26 |
+
# Optional: Pour de meilleures performances
|
| 27 |
+
# tensorflow-gpu>=2.16.0 # Décommentez si vous avez un GPU NVIDIA
|
| 28 |
+
# tensorrt # Pour l'optimisation GPU NVIDIA
|
| 29 |
+
|
| 30 |
+
# Interface utilisateur
|
| 31 |
+
streamlit>=1.28.0
|
| 32 |
+
|
| 33 |
+
# Optional: Pour l'analyse avancée
|
| 34 |
+
# plotly>=5.15.0
|
| 35 |
+
# jupyter>=1.0.0
|