def test_get_biases_2(): my_cnn = CNN() image_size=(np.random.randint(32,100),np.random.randint(20,100),np.random.randint(3,10)) number_of_conv_layers=np.random.randint(2,10) my_cnn.add_input_layer(shape=image_size,name="input") previous_depth=image_size[2] for k in range(number_of_conv_layers): number_of_filters = np.random.randint(3, 100) kernel_size= np.random.randint(3,9) my_cnn.append_conv2d_layer(num_of_filters=number_of_filters, kernel_size=(kernel_size,kernel_size), padding="same", activation='linear') actual = my_cnn.get_biases(layer_number=k+1) assert (actual.shape == (number_of_filters,)) or (actual.shape == (number_of_filters,1)) previous_depth=number_of_filters actual = my_cnn.get_biases(layer_number=0) assert actual is None
def test_get_biases_1(): my_cnn = CNN() input_size=np.random.randint(32,100) number_of_dense_layers=np.random.randint(2,10) my_cnn.add_input_layer(shape=input_size,name="input") previous_nodes=input_size for k in range(number_of_dense_layers): number_of_nodes = np.random.randint(3, 100) kernel_size= np.random.randint(3,9) my_cnn.append_dense_layer(num_nodes=number_of_nodes) actual = my_cnn.get_biases(layer_number=k+1) assert (actual.shape == (number_of_nodes,)) or (actual.shape == (number_of_nodes,1)) previous_nodes=number_of_nodes
def test_predict(): X = np.float32([[0.1, 0.2, 0.3, 0.4, 0.5, -0.1, -0.2, -0.3, -0.4, -0.5]]) X = np.float32([[0.1, 0.2, 0.3, 0.4, 0.5, 0, 0, 0, 0, 0]]) X = np.float32([np.linspace(0, 10, num=10)]) my_cnn = CNN() my_cnn.add_input_layer(shape=(10, ), name="input0") my_cnn.append_dense_layer(num_nodes=5, activation='linear', name="layer1") w = my_cnn.get_weights_without_biases(layer_name="layer1") w_set = np.full_like(w, 2) my_cnn.set_weights_without_biases(w_set, layer_name="layer1") b = my_cnn.get_biases(layer_name="layer1") b_set = np.full_like(b, 2) b_set[0] = b_set[0] * 2 my_cnn.set_biases(b_set, layer_name="layer1") actual = my_cnn.predict(X) assert np.array_equal(actual, np.array([[104., 102., 102., 102., 102.]]))