%pylab inline import os import numpy as np import pandas as pd from scipy.misc import imread from sklearn.metrics import accuracy_score import keras from keras.models import Sequential, Model from keras.layers import Dense, Dropout, Flatten, Activation, Input from keras.layers import Conv2D, MaxPooling2D # To stop potential randomness seed = 128 rng = np.random.RandomState(seed) data_dir = "../../datasets/MNIST" train = pd.read_csv('../../datasets/MNIST/train.csv') test = pd.read_csv('../../datasets/MNIST/Test_fCbTej3.csv') img_name = rng.choice(train.filename) filepath = os.path.join(data_dir, 'train', img_name) img = imread(filepath, flatten=True) pylab.imshow(img, cmap='gray') pylab.axis('off') pylab.show() temp = [] for img_name in train['filename']: image_path = os.path.join(data_dir, 'train', img_name) img = imread(image_path, flatten=True) img = img.astype('float32') temp.append(img) train_x = np.stack(temp) train_x /= 255.0 train_x = train_x.reshape(-1, 28, 28, 1).astype('float32') temp = [] for img_name in test['filename']: image_path = os.path.join(data_dir, 'test', img_name) img = imread(image_path, flatten=True) img = img.astype('float32') temp.append(img) test_x = np.stack(temp) test_x /= 255.0 test_x = test_x.reshape(-1, 28, 28, 1).astype('float32') train_y = keras.utils.np_utils.to_categorical(train.label.values) split_size = int(train_x.shape[0]*0.7) train_x, val_x = train_x[:split_size], train_x[split_size:] train_y, val_y = train_y[:split_size], train_y[split_size:] # define vars epochs = 5 batch_size = 128 # import keras modules from keras.models import Sequential from keras.layers import Dense # create model model = Sequential() model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28,28, 1))) 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(10, activation='softmax', name='preds')) # compile the model with necessary attributes model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) trained_model = model.fit(train_x, train_y, nb_epoch=epochs, batch_size=batch_size, validation_data=(val_x, val_y)) pred = model.predict_classes(test_x) img_name = rng.choice(test.filename) filepath = os.path.join(data_dir, 'test', img_name) img = imread(filepath, flatten=True) test_index = int(img_name.split('.')[0]) - train.shape[0] print ("Prediction is: ", pred[test_index]) pylab.imshow(img, cmap='gray') pylab.axis('off') pylab.show()