https://github.com/apm5/tensorflow_2.0_example

tensorflow 2.0alpha版本。停止更新，更多资料请移步我的另一个项目
https://github.com/apm5/tensorflow_2.0_example

tensorflow tensorflow-2 tensorflow-examples

Last synced: 6 days ago
JSON representation

tensorflow 2.0alpha版本。停止更新，更多资料请移步我的另一个项目

• Host: GitHub
• URL: https://github.com/apm5/tensorflow_2.0_example
• Owner: Apm5
• Created: 2019-04-15T06:15:57.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-05-12T09:10:45.000Z (over 5 years ago)
• Last Synced: 2024-10-27T18:58:44.460Z (17 days ago)
• Topics: tensorflow, tensorflow-2, tensorflow-examples
• Language: Python
• Homepage:
• Size: 46.9 KB
• Stars: 5
• Watchers: 0
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
### This is an example for tensorflow 2.0-alpha

In version 2.0, many features of tensorflow are deleted or changed, such as `tf.Session`. And in new version, Keras became the core function, which makes the code style quite different from before.

In this project, I will implement various layers and models. And I will try not to rely on advanced APIs to make it easy to change the details of the model.

Models and layers are as follows:

#### DONE:

[Reimplement fully connected layer](https://github.com/Apm5/tensorflow_2.0_example/blob/master/CNN/CNN_keras_reimplement.py)

[Reimplement convolution layer](https://github.com/Apm5/tensorflow_2.0_example/blob/master/CNN/CNN_keras_reimplement.py)

[Use unofficial evaluation and loss function](https://github.com/Apm5/tensorflow_2.0_example/blob/master/CNN/CNN_train_reimplement.py)

[Use unofficial train function](https://github.com/Apm5/tensorflow_2.0_example/blob/master/CNN/CNN_train_reimplement.py)

[Batch normalization](https://github.com/Apm5/tensorflow_2.0_example/blob/master/CNN/BatchNormalization.py)

[VGG-16](https://github.com/Apm5/tensorflow_2.0_example/blob/master/CNN/VGG.py)

[LSTM](https://github.com/Apm5/tensorflow_2.0_example/blob/master/RNN/LSTM.py)

#### TODO:

tf.data

Gabor convolution

ResNet

RCNN series

......