Day #303 - Model Training Guidelines - Part II

Here we will look at two more additions on top of the previous post 

• Save model h5 file after every run/epoch 
• Add Data batching to run in smaller iterations, Leverage Sequencer

	from __future__ import print_function
	import keras
	from keras.datasets import mnist
	from keras.models import Sequential
	from keras.layers import Dense, Dropout, Flatten
	from keras.layers import Conv2D, MaxPooling2D
	from keras import backend as K
	from keras.callbacks import ModelCheckpoint, CSVLogger, EarlyStopping
	import os
	import numpy as np
	import math
	batch_size = 128
	num_classes = 10
	epochs = 5
	log_file_path = r'E:\Landmark\mnist_training_log.log'
	model_checkpoint_path = r"E:\Landmark\\mnist.h5"
	model_save_path = r"E:\Landmark\\mnist_model_{}.hd5.h5"
	weights_filepath="E:\\Landmark\\mnist-weights-improvement-{epoch:02d}.hdf5"
	# input image dimensions
	img_rows, img_cols = 28, 28
	# the data, split between train and test sets
	(x_train, y_train), (x_test, y_test) = mnist.load_data()
	if K.image_data_format() == 'channels_first':
	x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
	x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
	input_shape = (1, img_rows, img_cols)
	else:
	x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
	x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
	input_shape = (img_rows, img_cols, 1)
	x_train = x_train.astype('float32')
	x_test = x_test.astype('float32')
	x_train /= 255
	x_test /= 255
	print('x_train shape:', x_train.shape)
	print(x_train.shape[0], 'train samples')
	print(x_test.shape[0], 'test samples')
	# convert class vectors to binary class matrices
	y_train = keras.utils.to_categorical(y_train, num_classes)
	y_test = keras.utils.to_categorical(y_test, num_classes)
	#Data Batching
	class Generator(keras.utils.Sequence):
	# Class is a dataset wrapper for better training performance
	def __init__(self, x_set, y_set, batch_size, datacount):
	self.x = x_set
	self.y = y_set
	self.batch_size = batch_size
	self.indices = np.arange(self.x.shape[0])
	self.idx = 0
	self.datacount = datacount
	def __len__(self):
	print('length')
	print(math.ceil(self.datacount/ self.batch_size))
	return math.ceil(self.datacount/ self.batch_size)
	def __getitem__(self, idx):
	print('idx')
	print(idx)
	i1 = idx*self.batch_size
	i2 = (idx+1)*self.batch_size
	print('Start-' + str(i1) + '- End-' + str(i2))
	if(i2 > self.datacount):
	i2 = self.datacount
	batch_x = self.x[i1:i2]
	batch_y = self.y[i1:i2]
	return batch_x, batch_y
	def on_epoch_end(self):
	np.random.shuffle(self.indices)
	#Save Model after every Epoch
	#https://stackoverflow.com/questions/54323960/save-keras-model-at-specific-epochs
	class CustomSaver(keras.callbacks.Callback):
	def on_epoch_end(self, epoch, logs={}):
	#if epoch == 2: # or save after some epoch, each k-th epoch etc.
	self.model.save(model_save_path.format(epoch))
	batch_size = 500
	print('x_train')
	print(len(x_train))
	print('x_test')
	print(len(x_test))
	training_generator = Generator(x_train, y_train, batch_size, len(x_train))
	validation_generator = Generator(x_test, y_test, batch_size, len(x_test))
	from keras.models import load_model
	#Load and Continue Training
	# load weights if it exists
	if os.path.exists(model_checkpoint_path):
	print('Loading Definitions')
	model = load_model(model_checkpoint_path)
	else:
	model = Sequential()
	model.add(Conv2D(32, kernel_size=(3, 3),
	activation='relu',
	input_shape=input_shape))
	model.add(Conv2D(64, (3, 3), activation='relu'))
	model.add(MaxPooling2D(pool_size=(2, 2)))
	model.add(Dropout(0.25))
	model.add(Flatten())
	model.add(Dense(128, activation='relu'))
	model.add(Dropout(0.5))
	model.add(Dense(num_classes, activation='softmax'))
	model.compile(loss=keras.losses.categorical_crossentropy,
	optimizer=keras.optimizers.Adadelta(),
	metrics=['accuracy'])
	#Add Early Stop and Checkpoint
	early_stop = EarlyStopping(monitor='val_loss', patience=5, verbose=1)
	checkpoint = ModelCheckpoint(weights_filepath, monitor='val_loss', verbose=1, save_best_only=True, mode='auto')
	csv_logger = CSVLogger(log_file_path, append=False)
	saver = CustomSaver()
	callbacks_list = [checkpoint,early_stop,csv_logger,saver]
	model.fit_generator(training_generator, validation_data = validation_generator, epochs = 10, callbacks=callbacks_list)
	score = model.evaluate(x_test, y_test, verbose=0)
	print('Test loss:', score[0])
	print('Test accuracy:', score[1])
	model.save(model_save_path)
	import pandas as pd
	import matplotlib.pyplot as plt
	# Plot the Loss
	file_name = log_file_path
	df = pd.DataFrame.from_csv(file_name)
	print(df.head())
	training_loss = df['loss']
	test_loss = df['val_loss']
	print(training_loss)
	print(test_loss)
	epoch_count = range(1, len(training_loss) + 1)
	plt.plot(epoch_count, training_loss, 'r--')
	plt.plot(epoch_count, test_loss, 'b-')
	plt.legend(['Training Loss', 'Test Loss'])
	plt.xlabel('Epoch')
	plt.ylabel('Loss')
	plt.show();

view raw Mnist_Guidelines.py hosted with ❤ by GitHub

This is a template code. This can be customized for larger datasets

Happy Learning!!!