Instructions to use squirelmail/model-BotDetect-CAPTCHA-Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use squirelmail/model-BotDetect-CAPTCHA-Generator with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://squirelmail/model-BotDetect-CAPTCHA-Generator") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -50,14 +50,14 @@ The tester script re-creates the training graph (CRNN+CTC), loads the selected c
|
|
| 50 |
|
| 51 |
### 1) Single image
|
| 52 |
|
| 53 |
-
python3
|
| 54 |
--weights /workspace/captcha_final.weights.h5 \
|
| 55 |
--image /workspace/dataset_500/style7/K9NO2.png
|
| 56 |
|
| 57 |
|
| 58 |
Optional ground truth override:
|
| 59 |
|
| 60 |
-
python3
|
| 61 |
--weights /workspace/captcha_final.weights.h5 \
|
| 62 |
--image /workspace/dataset_500/style7/K9NO2.png \
|
| 63 |
--gt K9NO2
|
|
@@ -65,7 +65,7 @@ Optional ground truth override:
|
|
| 65 |
|
| 66 |
### 2) Batch from a dataset
|
| 67 |
|
| 68 |
-
python3
|
| 69 |
--weights /home/infra/models/captcha_ep002.weights.h5 \
|
| 70 |
--data-root /datasets/dataset_500 \
|
| 71 |
--samples 64
|
|
|
|
| 50 |
|
| 51 |
### 1) Single image
|
| 52 |
|
| 53 |
+
python3 check_model.py \
|
| 54 |
--weights /workspace/captcha_final.weights.h5 \
|
| 55 |
--image /workspace/dataset_500/style7/K9NO2.png
|
| 56 |
|
| 57 |
|
| 58 |
Optional ground truth override:
|
| 59 |
|
| 60 |
+
python3 check_model.py \
|
| 61 |
--weights /workspace/captcha_final.weights.h5 \
|
| 62 |
--image /workspace/dataset_500/style7/K9NO2.png \
|
| 63 |
--gt K9NO2
|
|
|
|
| 65 |
|
| 66 |
### 2) Batch from a dataset
|
| 67 |
|
| 68 |
+
python3 check_model.py \
|
| 69 |
--weights /home/infra/models/captcha_ep002.weights.h5 \
|
| 70 |
--data-root /datasets/dataset_500 \
|
| 71 |
--samples 64
|