Downloads · 30 days
0
0% of all-time downloads
autoencoder-keras-mnist-demo-with-card
nateraw/autoencoder-keras-mnist-demo-with-card
autoencoder-keras-mnist-demo-with-card is a machine learning model from nateraw. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for keras.
All-time downloads
73
Public
Repo size
312 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pb157 KB · 50%
At a glance
- Library
- keras
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Feb 24, 2022
- SHA
- a00ed647
Model card
From the Hugging Face model README
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training Metrics
| Epochs | Train Loss | Validation Loss |
|---|---|---|
| 1 | 0.184 | 0.105 |
| 2 | 0.101 | 0.097 |
| 3 | 0.096 | 0.094 |
| 4 | 0.094 | 0.092 |
| 5 | 0.092 | 0.091 |
| 6 | 0.091 | 0.09 |
| 7 | 0.09 | 0.089 |
| 8 | 0.09 | 0.089 |
| 9 | 0.089 | 0.089 |
| 10 | 0.089 | 0.088 |
Model Plot
<details> <summary>View Model Plot</summary>
- Library
- keras
- Created
- Mar 2, 2022
- Updated
- Feb 24, 2022