keras：1)初体验-MLP神经网络实现MNIST手写识别

Keras是基于Theano和TensorFlow的深度学习库，具体介绍请参考
官方网：https://keras.io/
中文文档：http://keras-cn.readthedocs.io/en/latest/

先贴出官方在Git的源码例子minist_mlp，可以和之前对应的tensorflow博文tensorflow：1)简单的神经网络对比学习

'''Trains a simple deep NN on the MNIST dataset.Gets to 98.40% test accuracy after 20 epochs(there is *a lot* of margin for parameter tuning).2 seconds per epoch on a K520 GPU.'''from __future__ import print_functionimport kerasfrom keras.datasets import mnistfrom keras.models import Sequentialfrom keras.layers import Dense, Dropoutfrom keras.optimizers import RMSpropbatch_size = 128num_classes = 10epochs = 20# the data, shuffled and split between train and test sets(x_train, y_train), (x_test, y_test) = mnist.load_data()x_train = x_train.reshape(60000, 784)x_test = x_test.reshape(10000, 784)x_train = x_train.astype('float32')x_test = x_test.astype('float32')#除以255，把数据正则化到0~1之间x_train /= 255x_test /= 255print(x_train.shape[0], 'train samples')print(x_test.shape[0], 'test samples')# convert class vectors to binary class matricesy_train = keras.utils.to_categorical(y_train, num_classes)y_test = keras.utils.to_categorical(y_test, num_classes)model = Sequential()model.add(Dense(512, activation='relu', input_shape=(784,)))model.add(Dropout(0.2))model.add(Dense(512, activation='relu'))model.add(Dropout(0.2))model.add(Dense(10, activation='softmax'))model.summary()model.compile(loss='categorical_crossentropy',              optimizer=RMSprop(),              metrics=['accuracy'])#verbose=1可以显示每一步的信息history = model.fit(x_train, y_train,                    batch_size=batch_size,                    epochs=epochs,                    verbose=1)score = model.evaluate(x_test, y_test, verbose=0)print('Test loss:', score[0])print('Test accuracy:', score[1])

Q1:
源码需要下载10MB大小的MNIST数据集，但是国内好像下载不来(原因，你懂得) ，下面提供mnist.npz下载地址。但注意需放到~.keras\datasets目录下，比如win10的C:\Users\Javis.keras\datasets

Q2：

Dense(512, activation='relu', input_shape=(784,))

可以先看下这个类的注释说明：

"""Just your regular densely-connected NN layer.    `Dense` implements the operation:    `output = activation(dot(input, kernel) + bias)`    where `activation` is the element-wise activation function    passed as the `activation` argument, `kernel` is a weights matrix    created by the layer, and `bias` is a bias vector created by the layer    (only applicable if `use_bias` is `True`).    Note: if the input to the layer has a rank greater than 2, then    it is flattened prior to the initial dot product with `kernel`.    # Example    ```python        # as first layer in a sequential model:        model = Sequential()        model.add(Dense(32, input_shape=(16,)))        # now the model will take as input arrays of shape (*, 16)        # and output arrays of shape (*, 32)        # after the first layer, you don't need to specify        # the size of the input anymore:        model.add(Dense(32))

注释非常给力，densely-connected就是之前说是的全连接层

Q3:

model.summary()

可以显示网络的结构，很人性化有木有

_________________________________________________________________Layer (type)                 Output Shape              Param #   =================================================================dense_1 (Dense)              (None, 512)               401920    _________________________________________________________________dropout_1 (Dropout)          (None, 512)               0         _________________________________________________________________dense_2 (Dense)              (None, 512)               262656    _________________________________________________________________dropout_2 (Dropout)          (None, 512)               0         _________________________________________________________________dense_3 (Dense)              (None, 10)                5130      =================================================================