from keras.layers import Conv2D, MaxPooling2D import pandas as pd from sklearn.preprocessing import OneHotEncoder import numpy as np from keras.optimizers import Adam from TestTools import plot_results, load_data from keras import regularizers batch_size = 128 num_classes = 10 epochs = 15 # input image dimensions img_rows, img_cols = 16, 16 x_train, y_train, x_test, y_test = load_data(img_rows, img_cols) 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) loss_results = [] accuracy_results = [] for i in range(0, 10): model = Sequential() model.add( Conv2D(32, kernel_size=(3, 3), activation='relu',
from keras.optimizers import Adam from sklearn.preprocessing import OneHotEncoder import pandas as pd from sklearn.metrics import confusion_matrix import itertools from TestTools import load_data, plot_results if __name__ == "__main__": loss_results = [] accuracy_results = [] img_rows, img_cols = 16, 16 for i in range(0, 1): trainData, trainLabels, testData, testLabels = load_data( img_rows, img_cols) batch_size = 1 num_classes = 10 epochs = 15 model = Sequential() model.add(Dense(128, activation='relu', input_shape=(256, ))) model.add(Dense(128, activation='sigmoid')) model.add(Dense(128, activation='tanh')) model.add(Dense(num_classes, activation='softmax')) model.summary() model.compile(loss='categorical_crossentropy', optimizer=Adam(),