https://github.com/daviddao/pytorch-neural-search-optimizer
PyTorch implementation of Neural Optimizer Search's Optimizer_1
https://github.com/daviddao/pytorch-neural-search-optimizer
deep-learning neural-architecture-search neural-optimizer-search optimizer pytorch
Last synced: 4 months ago
JSON representation
PyTorch implementation of Neural Optimizer Search's Optimizer_1
- Host: GitHub
- URL: https://github.com/daviddao/pytorch-neural-search-optimizer
- Owner: daviddao
- License: mit
- Created: 2017-04-07T22:17:52.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-08-21T19:27:38.000Z (over 8 years ago)
- Last Synced: 2025-04-13T04:32:33.470Z (8 months ago)
- Topics: deep-learning, neural-architecture-search, neural-optimizer-search, optimizer, pytorch
- Language: Python
- Homepage:
- Size: 711 KB
- Stars: 8
- Watchers: 1
- Forks: 6
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Neural Optimizer Search - Optimizer_1
PyTorch implementation of Neural Optimizer Search's Optimizer_1
## Usage
Import _Optimizer_1_ like any torch.optim Optimizer:
```python
from optimizer_1 import Optimizer_1
optimizer = Optimizer_1(model.parameters(), lr=1e-3, momentum=0.99)
loss.backward()
optimizer.step()
```
--------------------------------------------------------------------------------
## Results
--------------------------------------------------------------------------------
## Own results
### MNIST (PyTorch/examples)
_Optimizer_1_
Test set: Average loss: 0.0525, Accuracy: 9820/10000 (98%)
_SGD with Momentum_
Test set: Average loss: 0.0542, Accuracy: 9825/10000 (98%)
### VAE (PyTorch/examples)
_Optimizer_1_
Test set: Average loss: 111.2389
_Adam_
Test set: Average loss: 105.5995