Repository files navigation

• Code explanation in Chinese.http://shamangary.logdown.com/posts/6424093

• Remove the one-hot inputs for Embedding layer and replace it by single value labels.
• There are two kinds labels: single value for center loss, and one-hot vector labels for softmax term.
• Every classes are visually seperated now :)

• Step.1Change the flag of center loss inside TYY_mnist.py

isCenterloss = True#isCenterloss = False

• Step.2Run the file

KERAS_BACKEND=tensorflow python TYY_mnist.py

• Anaconda
• Keras
• Tensorflow
• Others: (install with anaconda)

conda install -c anaconda scikit-learn conda install -c conda-forge matplotlib

• https://github.com/fchollet/keras/blob/master/examples/mnist_cnn.py
• https://github.com/keunwoochoi/keras_callbacks_example
• https://github.com/jxgu1016/MNIST_center_loss_pytorch
• http://kexue.fm/archives/4493/