我们从Python开源项目中，提取了以下10个代码示例，用于说明如何使用keras.backend.set_image_data_format()。
def test_DSSIM_channels_last(): prev_data = K.image_data_format() K.set_image_data_format('channels_last') for input_dim, kernel_size in zip([32, 33], [2, 3]): input_shape = [input_dim, input_dim, 3] X = np.random.random_sample(4 * input_dim * input_dim * 3).reshape([4] + input_shape) y = np.random.random_sample(4 * input_dim * input_dim * 3).reshape([4] + input_shape) model = Sequential() model.add(Conv2D(32, (3, 3), padding='same', input_shape=input_shape, activation='relu')) model.add(Conv2D(3, (3, 3), padding='same', input_shape=input_shape, activation='relu')) adam = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-8) model.compile(loss=DSSIMObjective(kernel_size=kernel_size), metrics=['mse'], optimizer=adam) model.fit(X, y, batch_size=2, epochs=1, shuffle='batch') # Test same x1 = K.constant(X, 'float32') x2 = K.constant(X, 'float32') dssim = DSSIMObjective(kernel_size=kernel_size) assert_allclose(0.0, K.eval(dssim(x1, x2)), atol=1e-4) # Test opposite x1 = K.zeros([4] + input_shape) x2 = K.ones([4] + input_shape) dssim = DSSIMObjective(kernel_size=kernel_size) assert_allclose(0.5, K.eval(dssim(x1, x2)), atol=1e-4) K.set_image_data_format(prev_data)
def test_DSSIM_channels_first(): prev_data = K.image_data_format() K.set_image_data_format('channels_first') for input_dim, kernel_size in zip([32, 33], [2, 3]): input_shape = [3, input_dim, input_dim] X = np.random.random_sample(4 * input_dim * input_dim * 3).reshape([4] + input_shape) y = np.random.random_sample(4 * input_dim * input_dim * 3).reshape([4] + input_shape) model = Sequential() model.add(Conv2D(32, (3, 3), padding='same', input_shape=input_shape, activation='relu')) model.add(Conv2D(3, (3, 3), padding='same', input_shape=input_shape, activation='relu')) adam = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-8) model.compile(loss=DSSIMObjective(kernel_size=kernel_size), metrics=['mse'], optimizer=adam) model.fit(X, y, batch_size=2, epochs=1, shuffle='batch') # Test same x1 = K.constant(X, 'float32') x2 = K.constant(X, 'float32') dssim = DSSIMObjective(kernel_size=kernel_size) assert_allclose(0.0, K.eval(dssim(x1, x2)), atol=1e-4) # Test opposite x1 = K.zeros([4] + input_shape) x2 = K.ones([4] + input_shape) dssim = DSSIMObjective(kernel_size=kernel_size) assert_allclose(0.5, K.eval(dssim(x1, x2)), atol=1e-4) K.set_image_data_format(prev_data)
def test_smoke_channels_first(): K.set_image_data_format('channels_first') _test_smoke('channels_first')
def test_smoke_channels_last(): K.set_image_data_format('channels_last') _test_smoke('channels_last')
def test_equivalence_channels_first(): K.set_image_data_format('channels_first') _test_equivalence('channels_first')
def test_equivalence_channels_last(): K.set_image_data_format('channels_last') _test_equivalence('channels_last')
def MyCNN_Keras2(X, nb_classes, nb_layers=4): from keras import backend as K K.set_image_data_format('channels_first') nb_filters = 32 # number of convolutional filters = "feature maps" kernel_size = (3, 3) # convolution kernel size pool_size = (2, 2) # size of pooling area for max pooling cl_dropout = 0.5 # conv. layer dropout dl_dropout = 0.8 # dense layer dropout channels = X.shape[1] # channels = 1 for mono, 2 for stereo print(" MyCNN_Keras2: X.shape = ",X.shape,", channels = ",channels) input_shape = (channels, X.shape[2], X.shape[3]) model = Sequential() #model.add(Conv2D(nb_filters, kernel_size, border_mode='valid', input_shape=input_shape)) model.add(Conv2D(nb_filters, kernel_size, border_mode='valid', input_shape=input_shape)) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')) for layer in range(nb_layers-1): # add more layers than just the first model.add(Conv2D(nb_filters, kernel_size)) model.add(BatchNormalization(axis=1)) model.add(ELU(alpha=1.0)) model.add(MaxPooling2D(pool_size=pool_size)) model.add(Dropout(cl_dropout)) model.add(Flatten()) model.add(Dense(128)) model.add(Activation('relu')) model.add(Dropout(dl_dropout)) model.add(Dense(nb_classes)) model.add(Activation("softmax")) model.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=['accuracy']) return model
def set_img_format(): try: if K.backend() == 'theano': K.set_image_data_format('channels_first') else: K.set_image_data_format('channels_last') except AttributeError: if K._BACKEND == 'theano': K.set_image_dim_ordering('th') else: K.set_image_dim_ordering('tf')
def test_vgg16(): for data_format in ['channels_first', 'channels_last']: K.set_image_data_format(data_format) if K.image_data_format() == 'channels_first': x = Input(shape=(3, 500, 500)) pool1_shape = (None, 64, 250, 250) pool2_shape = (None, 128, 125, 125) pool3_shape = (None, 256, 63, 63) pool4_shape = (None, 512, 32, 32) drop7_shape = (None, 4096, 16, 16) conv1_weight = -0.35009676 else: x = Input(shape=(500, 500, 3)) pool1_shape = (None, 250, 250, 64) pool2_shape = (None, 125, 125, 128) pool3_shape = (None, 63, 63, 256) pool4_shape = (None, 32, 32, 512) drop7_shape = (None, 16, 16, 4096) conv1_weight = 0.429471 encoder = VGG16(x, weights='imagenet', trainable=False) feat_pyramid = encoder.outputs assert len(feat_pyramid) == 5 assert K.int_shape(feat_pyramid[0]) == drop7_shape assert K.int_shape(feat_pyramid[1]) == pool4_shape assert K.int_shape(feat_pyramid[2]) == pool3_shape assert K.int_shape(feat_pyramid[3]) == pool2_shape assert K.int_shape(feat_pyramid[4]) == pool1_shape for layer in encoder.layers: if layer.name == 'block1_conv1': assert layer.trainable is False weights = K.eval(layer.weights[0]) assert np.allclose(weights[0, 0, 0, 0], conv1_weight) encoder_from_scratch = VGG16(x, weights=None, trainable=True) for layer in encoder_from_scratch.layers: if layer.name == 'block1_conv1': assert layer.trainable is True weights = K.eval(layer.weights[0]) assert not np.allclose(weights[0, 0, 0, 0], conv1_weight)
def test_vgg19(): for data_format in ['channels_first', 'channels_last']: K.set_image_data_format(data_format) if K.image_data_format() == 'channels_first': x = Input(shape=(3, 500, 500)) pool1_shape = (None, 64, 250, 250) pool2_shape = (None, 128, 125, 125) pool3_shape = (None, 256, 63, 63) pool4_shape = (None, 512, 32, 32) drop7_shape = (None, 4096, 16, 16) conv1_weight = -0.35009676 else: x = Input(shape=(500, 500, 3)) pool1_shape = (None, 250, 250, 64) pool2_shape = (None, 125, 125, 128) pool3_shape = (None, 63, 63, 256) pool4_shape = (None, 32, 32, 512) drop7_shape = (None, 16, 16, 4096) conv1_weight = 0.429471 encoder = VGG19(x, weights='imagenet', trainable=False) feat_pyramid = encoder.outputs assert len(feat_pyramid) == 5 assert K.int_shape(feat_pyramid[0]) == drop7_shape assert K.int_shape(feat_pyramid[1]) == pool4_shape assert K.int_shape(feat_pyramid[2]) == pool3_shape assert K.int_shape(feat_pyramid[3]) == pool2_shape assert K.int_shape(feat_pyramid[4]) == pool1_shape for layer in encoder.layers: if layer.name == 'block1_conv1': assert layer.trainable is False weights = K.eval(layer.weights[0]) assert np.allclose(weights[0, 0, 0, 0], conv1_weight) encoder_from_scratch = VGG19(x, weights=None, trainable=True) for layer in encoder_from_scratch.layers: if layer.name == 'block1_conv1': assert layer.trainable is True weights = K.eval(layer.weights[0]) assert not np.allclose(weights[0, 0, 0, 0], conv1_weight)
