Instructions to use InuriDinethma/black-tea-powder-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use InuriDinethma/black-tea-powder-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://InuriDinethma/black-tea-powder-classifier") - Notebooks
- Google Colab
- Kaggle
Download preprocessing_config.json from InuriDinethma/black-tea-powder-classifier: direct link, hf CLI and curl.
- Browser
- Download file 638 Bytes
-
https://huggingface.co/InuriDinethma/black-tea-powder-classifier/resolve/main/preprocessing_config.json
- Command line
-
hf download hf://InuriDinethma/black-tea-powder-classifier/preprocessing_config.json
-
curl -L -o preprocessing_config.json https://huggingface.co/InuriDinethma/black-tea-powder-classifier/resolve/main/preprocessing_config.json
638 Bytes
| { | |
| "architecture": "EfficientNetV2S", | |
| "image_size": 384, | |
| "load_size": 432, | |
| "training_min_load_size": 432, | |
| "training_max_load_size": 480, | |
| "central_crop_fraction": 0.68, | |
| "head_initial_learning_rate": 0.0003, | |
| "fine_tune_initial_learning_rate": 1e-05, | |
| "minimum_learning_rate": 1e-08, | |
| "sequence_group_size": 10, | |
| "near_duplicate_hash_distance": 4, | |
| "tta_passes": 10, | |
| "not_tea_class_name": "NOT_TEA", | |
| "not_tea_target_images": 1800, | |
| "negative_dataset_primary": "Open Images V7", | |
| "negative_dataset_source": "Caltech-101 direct official download", | |
| "deployment_min_confidence": 0.0 | |
| } |