done
Browse files
README.md
CHANGED
|
@@ -4,38 +4,8 @@ library_name: keras
|
|
| 4 |
|
| 5 |
## Model description
|
| 6 |
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
## Intended uses & limitations
|
| 10 |
-
|
| 11 |
-
More information needed
|
| 12 |
|
| 13 |
## Training and evaluation data
|
| 14 |
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
## Training procedure
|
| 18 |
-
|
| 19 |
-
### Training hyperparameters
|
| 20 |
-
|
| 21 |
-
The following hyperparameters were used during training:
|
| 22 |
-
|
| 23 |
-
| Hyperparameters | Value |
|
| 24 |
-
| :-- | :-- |
|
| 25 |
-
| name | Adam |
|
| 26 |
-
| weight_decay | None |
|
| 27 |
-
| clipnorm | None |
|
| 28 |
-
| global_clipnorm | None |
|
| 29 |
-
| clipvalue | None |
|
| 30 |
-
| use_ema | False |
|
| 31 |
-
| ema_momentum | 0.99 |
|
| 32 |
-
| ema_overwrite_frequency | None |
|
| 33 |
-
| jit_compile | False |
|
| 34 |
-
| is_legacy_optimizer | False |
|
| 35 |
-
| learning_rate | 0.0010000000474974513 |
|
| 36 |
-
| beta_1 | 0.9 |
|
| 37 |
-
| beta_2 | 0.999 |
|
| 38 |
-
| epsilon | 1e-07 |
|
| 39 |
-
| amsgrad | False |
|
| 40 |
-
| training_precision | float32 |
|
| 41 |
-
|
|
|
|
| 4 |
|
| 5 |
## Model description
|
| 6 |
|
| 7 |
+
OCR
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
## Training and evaluation data
|
| 10 |
|
| 11 |
+
Trained on EMNIST
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|