Instructions to use inviolus/InviolusOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use inviolus/InviolusOCR 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://inviolus/InviolusOCR") - Notebooks
- Google Colab
- Kaggle
Download benchmark_T.json from inviolus/InviolusOCR: direct link, hf CLI and curl.
- Browser
- Download file 1.29 kB
-
https://huggingface.co/inviolus/InviolusOCR/resolve/main/benchmark_T.json
- Command line
-
hf download hf://inviolus/InviolusOCR/benchmark_T.json
-
curl -L -o benchmark_T.json https://huggingface.co/inviolus/InviolusOCR/resolve/main/benchmark_T.json
1.29 kB
| { | |
| "T_tiny": { | |
| "params": 144330, | |
| "tflite_bytes": 171112, | |
| "tstr_test/float": { | |
| "samples": 2078, | |
| "exact": 0.3570741097208855, | |
| "cer": 0.2990055066984466 | |
| }, | |
| "tstr_test/int8": { | |
| "samples": 2078, | |
| "exact": 0.3262752646775746, | |
| "cer": 0.31256677899235635 | |
| }, | |
| "heldout/float": { | |
| "samples": 12093, | |
| "exact": 0.6626147357975688, | |
| "cer": 0.1309282828365609 | |
| }, | |
| "heldout/int8": { | |
| "samples": 12093, | |
| "exact": 0.6440916232531216, | |
| "cer": 0.14134452266413158 | |
| }, | |
| "plates/float": { | |
| "samples": 250, | |
| "exact": 0.004, | |
| "cer": 0.5796366708914238 | |
| }, | |
| "plates_nospace/float": { | |
| "samples": 250, | |
| "exact": 0.024, | |
| "cer": 0.5123126338329764 | |
| }, | |
| "plates/int8": { | |
| "samples": 250, | |
| "exact": 0.012, | |
| "cer": 0.5775242923531897 | |
| }, | |
| "plates_nospace/int8": { | |
| "samples": 250, | |
| "exact": 0.028, | |
| "cer": 0.5203426124197003 | |
| }, | |
| "donut_test/float": { | |
| "samples": 2563, | |
| "exact": 0.2298088177916504, | |
| "cer": 0.22396433786795789 | |
| }, | |
| "donut_test/int8": { | |
| "samples": 2563, | |
| "exact": 0.20132657042528287, | |
| "cer": 0.2414879717162401 | |
| } | |
| } | |
| } |