adaydl / easycnn Goto Github PK

Easy convolution neural network framework.

small, clean, easy to understand!

QQ群：603891505

blog about EasyCNN in Chinese.

port tensorflow model to easycnn model

• All in one: without any dependency, pure c++ implemented.
• Basic layer: data layer, convolution layer, pooling layer, full connect layer, softmax layer, activation layers(sigmod, tanh, RELU)
• Loss function: Cross Entropy, MSE.
• Optimize method: SGD, SGDWithMomentum.
• Multi-thread parallel optimized.
• Tensorflow model support (traditional CNN only now).(link)

• mnist demo, with ConvNet and MLP net, examples/mnist/mnist_train_test.cpp
  

• fix train error when batch > 1 issue.
• add load & save model function.
• add more layer, such as batch normalization layer, dropout layer, etc.
• add weight regular.
• port to other platforms, such as linux, mac, android, iOS, etc.
• optimize network train/test speed, use cuBLAS/OpenBLAS etc.
• add more optimize method.
• add unit test.
• add license.

Use github issues please.

Pull request is welcome.

This project is released under the WTFPL LICENSE.