Image Recognition: The Fashion-MNIST Dataset

Keras comes bundled with the Fashion-MNIST database of fashion articles which, like the MNIST digits dataset, provides 28-by-28 grayscale images. Fashion-MNIST contains clothing-article images labeled in 10 categories—0 (T-shirt/top), 1 (Trouser), 2 (Pullover), 3 (Dress), 4 (Coat), 5 (Sandal), 6 (Shirt), 7 (Sneaker), 8 (Bag), 9 (Ankle boot)—with 60,000 training samples and 10,000 testing samples. Modify the convnet example to load and process Fashion-MNIST rather than MNIST—this requires simply importing the correct module, loading the data then running the model with these images and labels, then re-run the entire example. How well does the model perform on Fashion-MNIST compared to MNIST? How do the training times compare?


Import Libraries

# baseline cnn model for fashion mnist
from numpy import mean
from numpy import std
from matplotlib import pyplot
from sklearn.model_selection import KFold
from keras.datasets import fashion_mnist
from tensorflow.keras.utils import to_categorical

from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Dense
from keras.layers import Flatten
from tensorflow.keras.optimizers import SGD

Load Dataset

# load train and test dataset
def load_dataset():
	# load dataset
	(trainX, trainY), (testX, testY) = fashion_mnist.load_data()
	# reshape dataset to have a single channel
	trainX = trainX.reshape((trainX.shape[0], 28, 28, 1))
	testX = testX.reshape((testX.shape[0], 28, 28, 1))
	# one hot encode target values
	trainY = to_categorical(trainY)
	testY = to_categorical(testY)
	return trainX, trainY, testX, testY

Scale pixels or Resizing

# scale pixels
def prep_pixels(train, test):
	# convert from integers to floats
	train_norm = train.astype('float32')
	test_norm = test.astype('float32')
	# normalize to range 0-1
	train_norm = train_norm / 255.0
	test_norm = test_norm / 255.0
	# return normalized images
	return train_norm, test_norm

Defining Model

# define cnn model
def define_model():
	model = Sequential()
	model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', input_shape=(28, 28, 1)))
	model.add(MaxPooling2D((2, 2)))
	model.add(Flatten())
	model.add(Dense(100, activation='relu', kernel_initializer='he_uniform'))
	model.add(Dense(10, activation='softmax'))
	# compile model
	opt = SGD(lr=0.01, momentum=0.9)
	model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
	return model
 

Evaluating Model Using K-fold Cross Validation

# evaluate a model using k-fold cross-validation
def evaluate_model(dataX, dataY, n_folds=5):
	scores, histories = list(), list()
	# prepare cross validation
	kfold = KFold(n_folds, shuffle=True, random_state=1)
	# enumerate splits
	for train_ix, test_ix in kfold.split(dataX):
		# define model
		model = define_model()
		# select rows for train and test
		trainX, trainY, testX, testY = dataX[train_ix], dataY[train_ix], dataX[test_ix], dataY[test_ix]
		# fit model
		history = model.fit(trainX, trainY, epochs=5, batch_size=32, validation_data=(testX, testY), verbose=0)
		# evaluate model
		_, acc = model.evaluate(testX, testY, verbose=0)
		print('> %.3f' % (acc * 100.0))
		# append scores
		scores.append(acc)
		histories.append(history)
	return scores, histories

Plot the Learning Curve

# plot diagnostic learning curves
def summarize_diagnostics(histories):
	for i in range(len(histories)):
		# plot accuracy
		pyplot.subplot(212)
		pyplot.title('Classification Accuracy')
		pyplot.plot(histories[i].history['accuracy'], color='blue', label='train')
		pyplot.plot(histories[i].history['val_accuracy'], color='orange', label='test')
	pyplot.show()

Summarizing the Model Performance

# summarize model performance
def summarize_performance(scores):
	# print summary
	print('Accuracy: mean=%.3f std=%.3f, n=%d' % (mean(scores)*100, std(scores)*100, len(scores)))
	# box and whisker plots of results
	pyplot.show()

# run the test harness for evaluating a model
def run_test_harness():
	# load dataset
	trainX, trainY, testX, testY = load_dataset()
	# prepare pixel data
	trainX, testX = prep_pixels(trainX, testX)
	# evaluate model
	scores, histories = evaluate_model(trainX, trainY)
	# learning curves
	summarize_diagnostics(histories)
	# summarize estimated performance
	summarize_performance(scores)
# run the test harness for evaluating a model
def test_harness():
	# load dataset
	trainX, trainY, testX, testY = load_dataset()
	# prepare pixel data
	trainX, testX = prep_pixels(trainX, testX)
	# evaluate model
	scores, histories = evaluate_model(trainX, trainY)
	# learning curves
	summarize_diagnostics(histories)
	# summarize estimated performance
	summarize_performance(scores)
# entry point, run the test harness
test_harness()

Output:

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz 32768/29515 [=================================] - 0s 0us/step 40960/29515 [=========================================] - 0s 0us/step Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz 26427392/26421880 [==============================] - 0s 0us/step 26435584/26421880 [==============================] - 0s 0us/step Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz 16384/5148 [===============================================================================================] - 0s 0us/step Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz 4423680/4422102 [==============================] - 0s 0us/step 4431872/4422102 [==============================] - 0s 0us/step

/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/optimizer_v2.py:356: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead. "The `lr` argument is deprecated, use `learning_rate` instead.")

> 90.925

> 90.608

> 90.383

> 90.117

> 90.400

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:78: MatplotlibDeprecationWarning: Adding an axes using the same arguments as a previous axes currently reuses the earlier instance. In a future version, a new instance will always be created and returned. Meanwhile, this warning can be suppressed, and the future behavior ensured, by passing a unique label to each axes instance.


Output:










If you have any query related to this then comment in below comment section and if your need any other machine learning related help then send your requirement details at realcode4you@gmail.com and get instant help with an affordable price.

33 views0 comments