Image Classification
Keras
LiteRT
English
mobilenet-v2-035
food-classification
efficientnet
tensorflow
tfjs
transfer-learning
Eval Results (legacy)
Instructions to use zeyuai/efficientnet-food-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use zeyuai/efficientnet-food-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://zeyuai/efficientnet-food-classifier") - Notebooks
- Google Colab
- Kaggle
| { | |
| "Keras": { | |
| "accuracy": 0.8558091286307054, | |
| "precision_weighted": 0.8666526359435469, | |
| "recall_weighted": 0.8558091286307054, | |
| "f1_weighted": 0.85640806010382, | |
| "f1_macro": 0.8434107272000173, | |
| "elapsed_seconds": 5.364844799041748, | |
| "images_per_second": 179.6883295062304, | |
| "file_size_mb": "5.3" | |
| }, | |
| "TFLite": { | |
| "accuracy": 0.8475103734439834, | |
| "precision_weighted": 0.8580648419239739, | |
| "recall_weighted": 0.8475103734439834, | |
| "f1_weighted": 0.8476776513487304, | |
| "f1_macro": 0.835230981636299, | |
| "elapsed_seconds": 3.749859094619751, | |
| "images_per_second": 257.0763262500009, | |
| "file_size_mb": "0.5" | |
| }, | |
| "TFLite-fp16": { | |
| "accuracy": 0.8537344398340249, | |
| "precision_weighted": 0.8644842534922317, | |
| "recall_weighted": 0.8537344398340249, | |
| "f1_weighted": 0.8542669093485433, | |
| "f1_macro": 0.8415336585341004, | |
| "elapsed_seconds": 2.708963394165039, | |
| "images_per_second": 355.85567604065966, | |
| "file_size_mb": "0.8" | |
| }, | |
| "agreement_Keras_vs_TFLite": "96.27%", | |
| "agreement_Keras_vs_TFLite-fp16": "99.69%", | |
| "agreement_TFLite_vs_TFLite-fp16": "96.16%" | |
| } |