Python Deep Learning Projects

Module 1 – train_mnist.py

This Python file contains the train_mnist() function that we have used previously to train a CNN classifier on MNIST digits:

"""This module is used to train a CNN on mnist."""from keras.layers import Conv2Dfrom keras.layers import Flatten, Activationfrom keras.models import Sequentialfrom keras.layers.core import Dense, Dropoutdef train_mnist(input_shape, X_train, y_train):    """Train CNN on mnist data."""    model = Sequential()    model.add(Conv2D(32, (3, 3), strides=2, padding='same',                     input_shape=input_shape))    model.add(Activation('relu'))    model.add(Dropout(0.2))    model.add(Conv2D(64, (3, 3), strides=2, padding='same'))    model.add(Activation('relu'))    model.add(Dropout(0.2)) model.add(Conv2D(128, (3, 3), padding='same')) ...