validation_images = scaler.transform(validation_images)
# Set target values in our labels matrix to 0.15 and 0.85
for i in range(len(train_labels[:, 0])):
for j in range(len(train_labels[0, :])):
if train_labels[i, j] < 0.5:
train_labels[i, j] = 0.1
else:
train_labels[i, j] = 0.9
# CREATE NeuralNet Object
NN = NeuralNet(train_images, train_labels)
# TRAIN NeuralNet Object
for i in range(1):
x_plot, y_plot = NN.trainPlot(v_learning_rate=0.01, w_learning_rate=0.001)
# Plot of cost function vs number of iterations.
plt.plot(x_plot, y_plot, 'r-')
plt.xlabel('Number of Iterations')
plt.ylabel('J(y, z; x, V, W)')
plt.title('Cost Function vs. Number of Iterations')
plt.savefig('images/Cost_Function.png', bbox_inches='tight')
# TRAINING ACCURACY
y_hat = NN.classifyAll(train_images)
test_correct = 0
test_size = len(NN.images)
for i in range(test_size):
if (y_hat[i] == np.argmax(NN.labels[i]) + 1):
test_correct += 1
else:
