# Standardize data to have feature values between 0 and 1.
train_x = train_x_flatten / 255.
test_x = test_x_flatten / 255.
return train_x, test_x, train_y, test_y, classes, num_px
if __name__ == "__main__":
layers_dims = [12288, 20, 10, 1] # 4-layer model
m = Main(layers_dims)
train_x, test_x, train_y, test_y, classes, num_px = preprocessing()
parameters = m.L_layer_model(train_x,
train_y,
layers_dims,
num_epochs=5000,
print_cost=True,
lambd=0,
learning_rate=0.001)
pred_train = m.predict(train_x, train_y, parameters)
pred_test = m.predict(test_x, test_y, parameters)
my_image = "cat.jpg"
my_label_y = [1] # the true class of your image (1 -> cat, 0 -> non-cat)
fname = "images/" + my_image
image = np.array(plt.imread(fname))
my_image = ((np.array(
Image.fromarray(image).resize((num_px, num_px),
Image.ANTIALIAS)).reshape(
(1, num_px * num_px * 3)))).T
test_x_flatten = test_x_orig.reshape(test_x_orig.shape[0], -1).T
num_px = train_x_orig.shape[1]
# Standardize data to have feature values between 0 and 1.
train_x = train_x_flatten / 255.
test_x = test_x_flatten / 255.
return train_x, test_x, train_y, test_y, classes, num_px
if __name__ == "__main__":
layers_dims = [12288, 20, 7, 5, 1] # 5-layer model
m = Main(layers_dims)
train_x, test_x, train_y, test_y, classes, num_px = preprocessing()
parameters = m.L_layer_model(train_x,
train_y,
layers_dims,
num_iterations=2500,
print_cost=True)
pred_train = m.predict(train_x, train_y, parameters)
pred_test = m.predict(test_x, test_y, parameters)
my_image = "cat.jpg"
my_label_y = [1] # the true class of your image (1 -> cat, 0 -> non-cat)
fname = "images/" + my_image
image = np.array(plt.imread(fname))
my_image = ((np.array(
Image.fromarray(image).resize((num_px, num_px),
Image.ANTIALIAS)).reshape(
(1, num_px * num_px * 3)))).T
