| library_name: tf-keras | |
| license: mit | |
| ## Model description | |
| A very simple model that converts an image into a number! | |
| ### the hepler function | |
| (requirements: `numpy Pillow`) | |
| ```python | |
| import numpy as np | |
| from PIL import Image | |
| def predict(model, img): | |
| pil_image = img | |
| pil_image = pil_image.resize((64, 64)) | |
| image_array = np.array(pil_image) / 255.0 | |
| image_array = np.expand_dims(image_array, axis=0) | |
| input_shape = (64, 64, pil_image.mode == 'RGB' and 3 or 1) | |
| decimal_prediction = model.predict(image_array)[0][0] | |
| return decimal_prediction | |
| ``` | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| | Hyperparameters | Value | | |
| | :-- | :-- | | |
| | name | Adam | | |
| | weight_decay | None | | |
| | clipnorm | None | | |
| | global_clipnorm | None | | |
| | clipvalue | None | | |
| | use_ema | False | | |
| | ema_momentum | 0.99 | | |
| | ema_overwrite_frequency | None | | |
| | jit_compile | False | | |
| | is_legacy_optimizer | False | | |
| | learning_rate | 0.0010000000474974513 | | |
| | beta_1 | 0.9 | | |
| | beta_2 | 0.999 | | |
| | epsilon | 1e-07 | | |
| | amsgrad | False | | |
| | training_precision | float32 | | |
| ## Model Plot | |
| <details> | |
| <summary>View Model Plot</summary> | |
|  | |
| </details> |