Python keras.utils.layer_utils.convert_all_kernels_in_model() Examples

The following are 8 code examples of keras.utils.layer_utils.convert_all_kernels_in_model(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module keras.utils.layer_utils , or try the search function .
Example #1
Source File: encoders.py    From keras-fcn with MIT License 5 votes vote down vote up 
def __init__(self, inputs, blocks, weights=None,
                 trainable=True, name='encoder'):
        inverse_pyramid = []

        # convolutional block
        conv_blocks = blocks[:-1]
        for i, block in enumerate(conv_blocks):
            if i == 0:
                x = block(inputs)
                inverse_pyramid.append(x)
            elif i < len(conv_blocks) - 1:
                x = block(x)
                inverse_pyramid.append(x)
            else:
                x = block(x)

        # fully convolutional block
        fc_block = blocks[-1]
        y = fc_block(x)
        inverse_pyramid.append(y)

        outputs = list(reversed(inverse_pyramid))

        super(Encoder, self).__init__(
            inputs=inputs, outputs=outputs)

        # load pre-trained weights
        if weights is not None:
            weights_path = get_file(
                '{}_weights_tf_dim_ordering_tf_kernels.h5'.format(name),
                weights,
                cache_subdir='models')
            layer_names = load_weights(self, weights_path)
            if K.image_data_format() == 'channels_first':
                layer_utils.convert_all_kernels_in_model(self)

        # Freezing basenet weights
        if trainable is False:
            for layer in self.layers:
                if layer.name in layer_names:
                    layer.trainable = False
Example #2
Source File: layer_utils_test.py    From DeepLearning_Wavelet-LSTM with MIT License 4 votes vote down vote up 
def test_convert_weights():
    def get_model(shape, data_format):
        model = Sequential()
        model.add(Conv2D(filters=2,
                         kernel_size=(4, 3),
                         input_shape=shape,
                         data_format=data_format))
        model.add(Flatten())
        model.add(Dense(5))
        return model

    for data_format in ['channels_first', 'channels_last']:
        if data_format == 'channels_first':
            shape = (3, 5, 5)
            target_shape = (5, 5, 3)
            prev_shape = (2, 3, 2)
            flip = lambda x: np.flip(np.flip(x, axis=2), axis=3)
            transpose = lambda x: np.transpose(x, (0, 2, 3, 1))
            target_data_format = 'channels_last'
        elif data_format == 'channels_last':
            shape = (5, 5, 3)
            target_shape = (3, 5, 5)
            prev_shape = (2, 2, 3)
            flip = lambda x: np.flip(np.flip(x, axis=1), axis=2)
            transpose = lambda x: np.transpose(x, (0, 3, 1, 2))
            target_data_format = 'channels_first'

        model1 = get_model(shape, data_format)
        model2 = get_model(target_shape, target_data_format)
        conv = K.function([model1.input], [model1.layers[0].output])

        x = np.random.random((1,) + shape)

        # Test equivalence of convert_all_kernels_in_model
        convout1 = conv([x])[0]
        layer_utils.convert_all_kernels_in_model(model1)
        convout2 = flip(conv([flip(x)])[0])

        assert_allclose(convout1, convout2, atol=1e-5)

        # Test equivalence of convert_dense_weights_data_format
        out1 = model1.predict(x)
        layer_utils.convert_dense_weights_data_format(model1.layers[2], prev_shape, target_data_format)
        for (src, dst) in zip(model1.layers, model2.layers):
            dst.set_weights(src.get_weights())
        out2 = model2.predict(transpose(x))

        assert_allclose(out1, out2, atol=1e-5)
Example #3
Source File: layer_utils_test.py    From DeepLearning_Wavelet-LSTM with MIT License 4 votes vote down vote up 
def test_convert_weights():
    def get_model(shape, data_format):
        model = Sequential()
        model.add(Conv2D(filters=2,
                         kernel_size=(4, 3),
                         input_shape=shape,
                         data_format=data_format))
        model.add(Flatten())
        model.add(Dense(5))
        return model

    for data_format in ['channels_first', 'channels_last']:
        if data_format == 'channels_first':
            shape = (3, 5, 5)
            target_shape = (5, 5, 3)
            prev_shape = (2, 3, 2)
            flip = lambda x: np.flip(np.flip(x, axis=2), axis=3)
            transpose = lambda x: np.transpose(x, (0, 2, 3, 1))
            target_data_format = 'channels_last'
        elif data_format == 'channels_last':
            shape = (5, 5, 3)
            target_shape = (3, 5, 5)
            prev_shape = (2, 2, 3)
            flip = lambda x: np.flip(np.flip(x, axis=1), axis=2)
            transpose = lambda x: np.transpose(x, (0, 3, 1, 2))
            target_data_format = 'channels_first'

        model1 = get_model(shape, data_format)
        model2 = get_model(target_shape, target_data_format)
        conv = K.function([model1.input], [model1.layers[0].output])

        x = np.random.random((1,) + shape)

        # Test equivalence of convert_all_kernels_in_model
        convout1 = conv([x])[0]
        layer_utils.convert_all_kernels_in_model(model1)
        convout2 = flip(conv([flip(x)])[0])

        assert_allclose(convout1, convout2, atol=1e-5)

        # Test equivalence of convert_dense_weights_data_format
        out1 = model1.predict(x)
        layer_utils.convert_dense_weights_data_format(model1.layers[2], prev_shape, target_data_format)
        for (src, dst) in zip(model1.layers, model2.layers):
            dst.set_weights(src.get_weights())
        out2 = model2.predict(transpose(x))

        assert_allclose(out1, out2, atol=1e-5)
Example #4
Source File: layer_utils_test.py    From DeepLearning_Wavelet-LSTM with MIT License 4 votes vote down vote up 
def test_convert_weights():
    def get_model(shape, data_format):
        model = Sequential()
        model.add(Conv2D(filters=2,
                         kernel_size=(4, 3),
                         input_shape=shape,
                         data_format=data_format))
        model.add(Flatten())
        model.add(Dense(5))
        return model

    for data_format in ['channels_first', 'channels_last']:
        if data_format == 'channels_first':
            shape = (3, 5, 5)
            target_shape = (5, 5, 3)
            prev_shape = (2, 3, 2)
            flip = lambda x: np.flip(np.flip(x, axis=2), axis=3)
            transpose = lambda x: np.transpose(x, (0, 2, 3, 1))
            target_data_format = 'channels_last'
        elif data_format == 'channels_last':
            shape = (5, 5, 3)
            target_shape = (3, 5, 5)
            prev_shape = (2, 2, 3)
            flip = lambda x: np.flip(np.flip(x, axis=1), axis=2)
            transpose = lambda x: np.transpose(x, (0, 3, 1, 2))
            target_data_format = 'channels_first'

        model1 = get_model(shape, data_format)
        model2 = get_model(target_shape, target_data_format)
        conv = K.function([model1.input], [model1.layers[0].output])

        x = np.random.random((1,) + shape)

        # Test equivalence of convert_all_kernels_in_model
        convout1 = conv([x])[0]
        layer_utils.convert_all_kernels_in_model(model1)
        convout2 = flip(conv([flip(x)])[0])

        assert_allclose(convout1, convout2, atol=1e-5)

        # Test equivalence of convert_dense_weights_data_format
        out1 = model1.predict(x)
        layer_utils.convert_dense_weights_data_format(model1.layers[2], prev_shape, target_data_format)
        for (src, dst) in zip(model1.layers, model2.layers):
            dst.set_weights(src.get_weights())
        out2 = model2.predict(transpose(x))

        assert_allclose(out1, out2, atol=1e-5)
Example #5
Source File: layer_utils_test.py    From DeepLearning_Wavelet-LSTM with MIT License 4 votes vote down vote up 
def test_convert_weights():
    def get_model(shape, data_format):
        model = Sequential()
        model.add(Conv2D(filters=2,
                         kernel_size=(4, 3),
                         input_shape=shape,
                         data_format=data_format))
        model.add(Flatten())
        model.add(Dense(5))
        return model

    for data_format in ['channels_first', 'channels_last']:
        if data_format == 'channels_first':
            shape = (3, 5, 5)
            target_shape = (5, 5, 3)
            prev_shape = (2, 3, 2)
            flip = lambda x: np.flip(np.flip(x, axis=2), axis=3)
            transpose = lambda x: np.transpose(x, (0, 2, 3, 1))
            target_data_format = 'channels_last'
        elif data_format == 'channels_last':
            shape = (5, 5, 3)
            target_shape = (3, 5, 5)
            prev_shape = (2, 2, 3)
            flip = lambda x: np.flip(np.flip(x, axis=1), axis=2)
            transpose = lambda x: np.transpose(x, (0, 3, 1, 2))
            target_data_format = 'channels_first'

        model1 = get_model(shape, data_format)
        model2 = get_model(target_shape, target_data_format)
        conv = K.function([model1.input], [model1.layers[0].output])

        x = np.random.random((1,) + shape)

        # Test equivalence of convert_all_kernels_in_model
        convout1 = conv([x])[0]
        layer_utils.convert_all_kernels_in_model(model1)
        convout2 = flip(conv([flip(x)])[0])

        assert_allclose(convout1, convout2, atol=1e-5)

        # Test equivalence of convert_dense_weights_data_format
        out1 = model1.predict(x)
        layer_utils.convert_dense_weights_data_format(model1.layers[2], prev_shape, target_data_format)
        for (src, dst) in zip(model1.layers, model2.layers):
            dst.set_weights(src.get_weights())
        out2 = model2.predict(transpose(x))

        assert_allclose(out1, out2, atol=1e-5)
Example #6
Source File: layer_utils_test.py    From DeepLearning_Wavelet-LSTM with MIT License 4 votes vote down vote up 
def test_convert_weights():
    def get_model(shape, data_format):
        model = Sequential()
        model.add(Conv2D(filters=2,
                         kernel_size=(4, 3),
                         input_shape=shape,
                         data_format=data_format))
        model.add(Flatten())
        model.add(Dense(5))
        return model

    for data_format in ['channels_first', 'channels_last']:
        if data_format == 'channels_first':
            shape = (3, 5, 5)
            target_shape = (5, 5, 3)
            prev_shape = (2, 3, 2)
            flip = lambda x: np.flip(np.flip(x, axis=2), axis=3)
            transpose = lambda x: np.transpose(x, (0, 2, 3, 1))
            target_data_format = 'channels_last'
        elif data_format == 'channels_last':
            shape = (5, 5, 3)
            target_shape = (3, 5, 5)
            prev_shape = (2, 2, 3)
            flip = lambda x: np.flip(np.flip(x, axis=1), axis=2)
            transpose = lambda x: np.transpose(x, (0, 3, 1, 2))
            target_data_format = 'channels_first'

        model1 = get_model(shape, data_format)
        model2 = get_model(target_shape, target_data_format)
        conv = K.function([model1.input], [model1.layers[0].output])

        x = np.random.random((1,) + shape)

        # Test equivalence of convert_all_kernels_in_model
        convout1 = conv([x])[0]
        layer_utils.convert_all_kernels_in_model(model1)
        convout2 = flip(conv([flip(x)])[0])

        assert_allclose(convout1, convout2, atol=1e-5)

        # Test equivalence of convert_dense_weights_data_format
        out1 = model1.predict(x)
        layer_utils.convert_dense_weights_data_format(model1.layers[2], prev_shape, target_data_format)
        for (src, dst) in zip(model1.layers, model2.layers):
            dst.set_weights(src.get_weights())
        out2 = model2.predict(transpose(x))

        assert_allclose(out1, out2, atol=1e-5)
Example #7
Source File: layer_utils_test.py    From DeepLearning_Wavelet-LSTM with MIT License 4 votes vote down vote up 
def test_convert_weights():
    def get_model(shape, data_format):
        model = Sequential()
        model.add(Conv2D(filters=2,
                         kernel_size=(4, 3),
                         input_shape=shape,
                         data_format=data_format))
        model.add(Flatten())
        model.add(Dense(5))
        return model

    for data_format in ['channels_first', 'channels_last']:
        if data_format == 'channels_first':
            shape = (3, 5, 5)
            target_shape = (5, 5, 3)
            prev_shape = (2, 3, 2)
            flip = lambda x: np.flip(np.flip(x, axis=2), axis=3)
            transpose = lambda x: np.transpose(x, (0, 2, 3, 1))
            target_data_format = 'channels_last'
        elif data_format == 'channels_last':
            shape = (5, 5, 3)
            target_shape = (3, 5, 5)
            prev_shape = (2, 2, 3)
            flip = lambda x: np.flip(np.flip(x, axis=1), axis=2)
            transpose = lambda x: np.transpose(x, (0, 3, 1, 2))
            target_data_format = 'channels_first'

        model1 = get_model(shape, data_format)
        model2 = get_model(target_shape, target_data_format)
        conv = K.function([model1.input], [model1.layers[0].output])

        x = np.random.random((1,) + shape)

        # Test equivalence of convert_all_kernels_in_model
        convout1 = conv([x])[0]
        layer_utils.convert_all_kernels_in_model(model1)
        convout2 = flip(conv([flip(x)])[0])

        assert_allclose(convout1, convout2, atol=1e-5)

        # Test equivalence of convert_dense_weights_data_format
        out1 = model1.predict(x)
        layer_utils.convert_dense_weights_data_format(model1.layers[2], prev_shape, target_data_format)
        for (src, dst) in zip(model1.layers, model2.layers):
            dst.set_weights(src.get_weights())
        out2 = model2.predict(transpose(x))

        assert_allclose(out1, out2, atol=1e-5)
Example #8
Source File: layer_utils_test.py    From DeepLearning_Wavelet-LSTM with MIT License 4 votes vote down vote up 
def test_convert_weights():
    def get_model(shape, data_format):
        model = Sequential()
        model.add(Conv2D(filters=2,
                         kernel_size=(4, 3),
                         input_shape=shape,
                         data_format=data_format))
        model.add(Flatten())
        model.add(Dense(5))
        return model

    for data_format in ['channels_first', 'channels_last']:
        if data_format == 'channels_first':
            shape = (3, 5, 5)
            target_shape = (5, 5, 3)
            prev_shape = (2, 3, 2)
            flip = lambda x: np.flip(np.flip(x, axis=2), axis=3)
            transpose = lambda x: np.transpose(x, (0, 2, 3, 1))
            target_data_format = 'channels_last'
        elif data_format == 'channels_last':
            shape = (5, 5, 3)
            target_shape = (3, 5, 5)
            prev_shape = (2, 2, 3)
            flip = lambda x: np.flip(np.flip(x, axis=1), axis=2)
            transpose = lambda x: np.transpose(x, (0, 3, 1, 2))
            target_data_format = 'channels_first'

        model1 = get_model(shape, data_format)
        model2 = get_model(target_shape, target_data_format)
        conv = K.function([model1.input], [model1.layers[0].output])

        x = np.random.random((1,) + shape)

        # Test equivalence of convert_all_kernels_in_model
        convout1 = conv([x])[0]
        layer_utils.convert_all_kernels_in_model(model1)
        convout2 = flip(conv([flip(x)])[0])

        assert_allclose(convout1, convout2, atol=1e-5)

        # Test equivalence of convert_dense_weights_data_format
        out1 = model1.predict(x)
        layer_utils.convert_dense_weights_data_format(model1.layers[2], prev_shape, target_data_format)
        for (src, dst) in zip(model1.layers, model2.layers):
            dst.set_weights(src.get_weights())
        out2 = model2.predict(transpose(x))

        assert_allclose(out1, out2, atol=1e-5)