https://github.com/yoctol/talos
Neural Network Builder
https://github.com/yoctol/talos
tensorflow-models
Last synced: 2 months ago
JSON representation
Neural Network Builder
- Host: GitHub
- URL: https://github.com/yoctol/talos
- Owner: Yoctol
- License: other
- Created: 2018-10-26T07:41:38.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2022-10-18T19:21:39.000Z (over 3 years ago)
- Last Synced: 2025-11-22T07:17:00.504Z (7 months ago)
- Topics: tensorflow-models
- Language: Python
- Size: 390 KB
- Stars: 2
- Watchers: 4
- Forks: 1
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# talos
[![travis][travis-image]][travis-url]
[![pypi][pypi-image]][pypi-url]
![release][release-image]
[travis-image]: https://img.shields.io/travis/Yoctol/talos.svg?style=flat
[travis-url]: https://travis-ci.org/Yoctol/talos
[pypi-image]: https://img.shields.io/pypi/v/talos.svg?style=flat
[pypi-url]: https://pypi.python.org/pypi/talos
[release-image]: https://img.shields.io/github/release/Yoctol/talos.svg
About this project...
## Installation
``` shell
$ git clone https://github.com/Yoctol/talos.git
```
``` bash
$ pipenv install
```
## Usage
多個 Layers 組合串接
```python
def pre_activate_bn_dense(units):
return Sequential([
Dense(
units=units,
kernel_initialzer='lecun_normal',
activation=None,
),
BatchNormalization(),
Activation('relu'),
])
model = Sequential([
pre_activate_bn_dense(32),
pre_activate_bn_dense(16),
pre_activate_bn_dense(8),
])
outputs = model(inputs)
```
方便的 variables/updates scope collection
```python
with tf.control_dependencies(model.updates):
train_op = SGDOptimizer(loss, var_list=model.trainable_variables)
```
## Test
``` shell
$ pipenv install --dev
```
``` shell
$ pytest
```