Easy convolution network.
- 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.
- 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,gradient momentum.
- 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.