Python keras.backend.image_dim_ordering() Examples

def deprocess_image(x):
    """ Same normalization as in:
    https://github.com/fchollet/keras/blob/master/examples/conv_filter_visualization.py
    """
    if np.ndim(x) > 3:
        x = np.squeeze(x)
    # normalize tensor: center on 0., ensure std is 0.1
    x = x - x.mean()
    x = x / (x.std() + 1e-5)
    x = x * 0.1

    # clip to [0, 1]
    x = x + 0.5
    x = np.clip(x, 0, 1)

    # convert to RGB array
    x = x * 255
    if K.image_dim_ordering() == 'th':
        x = x.transpose((1, 2, 0))
    x = np.clip(x, 0, 255).astype('uint8')
    return x 

def conv2d_bn(x, nb_filter, nb_row, nb_col,
              border_mode='same', subsample=(1, 1), bias=False):
    """
    Utility function to apply conv + BN. 
    (Slightly modified from https://github.com/fchollet/keras/blob/master/keras/applications/inception_v3.py)
    """
    if K.image_dim_ordering() == "th":
        channel_axis = 1
    else:
        channel_axis = -1
    x = Convolution2D(nb_filter, nb_row, nb_col,
                      subsample=subsample,
                      border_mode=border_mode,
                      bias=bias)(x)
    x = BatchNormalization(axis=channel_axis)(x)
    x = Activation('relu')(x)
    return x 

def _load_features(self, audio_filename):
        features = list()
        for feature_filename in self.feature_filenames:
            if audio_filename in feature_filename:
                filename_full_path = os.path.join(IRMAS_TEST_FEATURE_BASEPATH,
                                                  self.model_module.BASE_NAME,
                                                  feature_filename)
                feature = np.load(filename_full_path)
                feature -= self.dataset_mean
                features.append(feature)

        if K.image_dim_ordering() == "th":
            features = np.array(features).reshape(-1, 1, self.model_module.N_MEL_BANDS, self.model_module.SEGMENT_DUR)
        else:
            features = np.array(features).reshape(-1, self.model_module.N_MEL_BANDS, self.model_module.SEGMENT_DUR, 1)
        return features 

def block_inception_a(input):
    if K.image_dim_ordering() == "th":
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 96, 1, 1)

    branch_1 = conv2d_bn(input, 64, 1, 1)
    branch_1 = conv2d_bn(branch_1, 96, 3, 3)

    branch_2 = conv2d_bn(input, 64, 1, 1)
    branch_2 = conv2d_bn(branch_2, 96, 3, 3)
    branch_2 = conv2d_bn(branch_2, 96, 3, 3)

    branch_3 = AveragePooling2D((3,3), strides=(1,1), border_mode='same')(input)
    branch_3 = conv2d_bn(branch_3, 96, 1, 1)

    x = merge([branch_0, branch_1, branch_2, branch_3], mode='concat', concat_axis=channel_axis)
    return x 

def get_conv_image_descriptor_for_image(image, model):
    im = cv2.resize(image, (224, 224)).astype(np.float32)
    dim_ordering = K.image_dim_ordering()
    if dim_ordering == 'th':
        # 'RGB'->'BGR'
        im = im[::-1, :, :]
        # Zero-center by mean pixel
        im[0, :, :] -= 103.939
        im[1, :, :] -= 116.779
        im[2, :, :] -= 123.68
    else:
        # 'RGB'->'BGR'
        im = im[:, :, ::-1]
        # Zero-center by mean pixel
        im[:, :, 0] -= 103.939
        im[:, :, 1] -= 116.779
        im[:, :, 2] -= 123.68
    im = im.transpose((2, 0, 1))
    im = np.expand_dims(im, axis=0)
    inputs = [K.learning_phase()] + model.inputs
    _convout1_f = K.function(inputs, [model.layers[31].output])
    return _convout1_f([0] + [im]) 

def block_reduction_a(input):
    if K.image_dim_ordering() == "th":
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 384, 3, 3, subsample=(2,2), border_mode='valid')

    branch_1 = conv2d_bn(input, 192, 1, 1)
    branch_1 = conv2d_bn(branch_1, 224, 3, 3)
    branch_1 = conv2d_bn(branch_1, 256, 3, 3, subsample=(2,2), border_mode='valid')

    branch_2 = MaxPooling2D((3,3), strides=(2,2), border_mode='valid')(input)

    x = merge([branch_0, branch_1, branch_2], mode='concat', concat_axis=channel_axis)
    return x 

def block_inception_b(input):
    if K.image_dim_ordering() == "th":
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 384, 1, 1)

    branch_1 = conv2d_bn(input, 192, 1, 1)
    branch_1 = conv2d_bn(branch_1, 224, 1, 7)
    branch_1 = conv2d_bn(branch_1, 256, 7, 1)

    branch_2 = conv2d_bn(input, 192, 1, 1)
    branch_2 = conv2d_bn(branch_2, 192, 7, 1)
    branch_2 = conv2d_bn(branch_2, 224, 1, 7)
    branch_2 = conv2d_bn(branch_2, 224, 7, 1)
    branch_2 = conv2d_bn(branch_2, 256, 1, 7)

    branch_3 = AveragePooling2D((3,3), strides=(1,1), border_mode='same')(input)
    branch_3 = conv2d_bn(branch_3, 128, 1, 1)

    x = merge([branch_0, branch_1, branch_2, branch_3], mode='concat', concat_axis=channel_axis)
    return x 

def get_image_descriptor_for_image(image, model):
    im = cv2.resize(image, (224, 224)).astype(np.float32)
    dim_ordering = K.image_dim_ordering()
    if dim_ordering == 'th':
        # 'RGB'->'BGR'
        im = im[::-1, :, :]
        # Zero-center by mean pixel
        im[0, :, :] -= 103.939
        im[1, :, :] -= 116.779
        im[2, :, :] -= 123.68
    else:
        # 'RGB'->'BGR'
        im = im[:, :, ::-1]
        # Zero-center by mean pixel
        im[:, :, 0] -= 103.939
        im[:, :, 1] -= 116.779
        im[:, :, 2] -= 123.68
    im = im.transpose((2, 0, 1))
    im = np.expand_dims(im, axis=0)
    inputs = [K.learning_phase()] + model.inputs
    _convout1_f = K.function(inputs, [model.layers[33].output])
    return _convout1_f([0] + [im]) 

def get_feature_map_4(model, im):
    im = im.astype(np.float32)
    dim_ordering = K.image_dim_ordering()
    if dim_ordering == 'th':
        # 'RGB'->'BGR'
        im = im[::-1, :, :]
        # Zero-center by mean pixel
        im[0, :, :] -= 103.939
        im[1, :, :] -= 116.779
        im[2, :, :] -= 123.68
    else:
        # 'RGB'->'BGR'
        im = im[:, :, ::-1]
        # Zero-center by mean pixel
        im[:, :, 0] -= 103.939
        im[:, :, 1] -= 116.779
        im[:, :, 2] -= 123.68
    im = im.transpose((2, 0, 1))
    im = np.expand_dims(im, axis=0)
    inputs = [K.learning_phase()] + model.inputs
    _convout1_f = K.function(inputs, [model.layers[23].output])
    feature_map = _convout1_f([0] + [im])
    feature_map = np.array([feature_map])
    feature_map = feature_map[0, 0, 0, :, :, :]
    return feature_map 

def block_reduction_b(input):
    if K.image_dim_ordering() == "th":
        channel_axis = 1
    else:
        channel_axis = -1

    branch_0 = conv2d_bn(input, 192, 1, 1)
    branch_0 = conv2d_bn(branch_0, 192, 3, 3, subsample=(2, 2), border_mode='valid')

    branch_1 = conv2d_bn(input, 256, 1, 1)
    branch_1 = conv2d_bn(branch_1, 256, 1, 7)
    branch_1 = conv2d_bn(branch_1, 320, 7, 1)
    branch_1 = conv2d_bn(branch_1, 320, 3, 3, subsample=(2,2), border_mode='valid')

    branch_2 = MaxPooling2D((3, 3), strides=(2, 2), border_mode='valid')(input)

    x = merge([branch_0, branch_1, branch_2], mode='concat', concat_axis=channel_axis)
    return x 

def rpn_loss_regr(num_anchors):
	def rpn_loss_regr_fixed_num(y_true, y_pred):
		if K.image_dim_ordering() == 'th':
			x = y_true[:, 4 * num_anchors:, :, :] - y_pred
			x_abs = K.abs(x)
			x_bool = K.less_equal(x_abs, 1.0)
			return lambda_rpn_regr * K.sum(
				y_true[:, :4 * num_anchors, :, :] * (x_bool * (0.5 * x * x) + (1 - x_bool) * (x_abs - 0.5))) / K.sum(epsilon + y_true[:, :4 * num_anchors, :, :])
		else:
			x = y_true[:, :, :, 4 * num_anchors:] - y_pred
			x_abs = K.abs(x)
			x_bool = K.cast(K.less_equal(x_abs, 1.0), tf.float32)

			return lambda_rpn_regr * K.sum(
				y_true[:, :, :, :4 * num_anchors] * (x_bool * (0.5 * x * x) + (1 - x_bool) * (x_abs - 0.5))) / K.sum(epsilon + y_true[:, :, :, :4 * num_anchors])

	return rpn_loss_regr_fixed_num 

def deprocess_image(x):
    """ Same normalization as in:
    https://github.com/fchollet/keras/blob/master/examples/conv_filter_visualization.py
    """
    if np.ndim(x) > 3:
        x = np.squeeze(x)
    # normalize tensor: center on 0., ensure std is 0.1
    x = x - x.mean()
    x = x / (x.std() + 1e-5)
    x = x * 0.1

    # clip to [0, 1]
    x = x + 0.5
    x = np.clip(x, 0, 1)

    # convert to RGB array
    x = x * 255
    if K.image_dim_ordering() == 'th':
        x = x.transpose((1, 2, 0))
    x = np.clip(x, 0, 255).astype('uint8')
    return x 

def preprocess_input(x, dim_ordering='default'):
    if dim_ordering == 'default':
        dim_ordering = K.image_dim_ordering()
    assert dim_ordering in {'tf', 'th'}

    if dim_ordering == 'th':
        x[:, 0, :, :] -= 103.939
        x[:, 1, :, :] -= 116.779
        x[:, 2, :, :] -= 123.68
        # 'RGB'->'BGR'
        x = x[:, ::-1, :, :]
    else:
        x[:, :, :, 0] -= 103.939
        x[:, :, :, 1] -= 116.779
        x[:, :, :, 2] -= 123.68
        # 'RGB'->'BGR'
        x = x[:, :, :, ::-1]
    return x 

def conv2d_bn(x, nb_filter, nb_row, nb_col,
              border_mode='same', subsample=(1, 1),
              name=None):
    '''Utility function to apply conv + BN.
    '''
    if name is not None:
        bn_name = name + '_bn'
        conv_name = name + '_conv'
    else:
        bn_name = None
        conv_name = None
    if K.image_dim_ordering() == 'th':
        bn_axis = 1
    else:
        bn_axis = 3
    x = Convolution2D(nb_filter, nb_row, nb_col,
                      subsample=subsample,
                      activation='relu',
                      border_mode=border_mode,
                      name=conv_name)(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name)(x)
    return x 

def build_vgg16(image_size=None):
	image_size = image_size or (240, 240)
	if K.image_dim_ordering() == 'th':
	    input_shape = (3,) + image_size
	else:
	    input_shape = image_size + (3, )
	bottleneck_model = vgg16.VGG16(include_top=False, 
	                               input_tensor=Input(input_shape))
	#bottleneck_model.trainable = False
	for layer in bottleneck_model.layers:
	    layer.trainable = False

	x = bottleneck_model.input
	y = bottleneck_model.output
	y = Flatten()(y)
	y = BatchNormalization()(y)
	y = Dense(2048, activation='relu')(y)
	y = Dropout(.5)(y)
	y = Dense(1024, activation='relu')(y)
	y = Dropout(.5)(y)
	y = Dense(1)(y)

	model = Model(input=x, output=y)
	model.compile(optimizer=Adam(lr=1e-4), loss = 'mse')
	return model 

def array_to_img(x, dim_ordering='default', scale=True):
    from PIL import Image
    if dim_ordering == 'default':
        dim_ordering = K.image_dim_ordering()
    if dim_ordering == 'th':
        x = x.transpose(1, 2, 0)
    if scale:
        x += max(-np.min(x), 0)
        x_max = np.max(x)
        if x_max != 0:
            x /= x_max
        x *= 255
    if x.shape[2] == 3:
        # RGB
        return Image.fromarray(x.astype('uint8'), 'RGB')
    elif x.shape[2] == 1:
        # grayscale
        return Image.fromarray(x[:, :, 0].astype('uint8'), 'L')
    else:
        raise Exception('Unsupported channel number: ', x.shape[2]) 

def img_to_array(img, dim_ordering='default'):
    if dim_ordering == 'default':
        dim_ordering = K.image_dim_ordering()
    if dim_ordering not in ['th', 'tf']:
        raise Exception('Unknown dim_ordering: ', dim_ordering)
    # image has dim_ordering (height, width, channel)
    x = np.asarray(img, dtype='float32')
    if len(x.shape) == 3:
        if dim_ordering == 'th':
            x = x.transpose(2, 0, 1)
    elif len(x.shape) == 2:
        if dim_ordering == 'th':
            x = x.reshape((1, x.shape[0], x.shape[1]))
        else:
            x = x.reshape((x.shape[0], x.shape[1], 1))
    else:
        raise Exception('Unsupported image shape: ', x.shape)
    return x 

def __init__(self, X, y, image_data_generator,
                 batch_size=32, shuffle=False, seed=None,
                 dim_ordering='default',
                 save_to_dir=None, save_prefix='', save_format='jpeg'):
        if y is not None and len(X) != len(y):
            raise Exception('X (images tensor) and y (labels) '
                            'should have the same length. '
                            'Found: X.shape = %s, y.shape = %s' % (np.asarray(X).shape, np.asarray(y).shape))
        if dim_ordering == 'default':
            dim_ordering = K.image_dim_ordering()
        self.X = X
        self.y = y
        self.image_data_generator = image_data_generator
        self.dim_ordering = dim_ordering
        self.save_to_dir = save_to_dir
        self.save_prefix = save_prefix
        self.save_format = save_format
        super(NumpyArrayIterator, self).__init__(X.shape[0], batch_size, shuffle, seed) 

def rpn_loss_regr(num_anchors):
	def rpn_loss_regr_fixed_num(y_true, y_pred):
		if K.image_dim_ordering() == 'th':
			x = y_true[:, 4 * num_anchors:, :, :] - y_pred
			x_abs = K.abs(x)
			x_bool = K.less_equal(x_abs, 1.0)
			return lambda_rpn_regr * K.sum(
				y_true[:, :4 * num_anchors, :, :] * (x_bool * (0.5 * x * x) + (1 - x_bool) * (x_abs - 0.5))) / K.sum(epsilon + y_true[:, :4 * num_anchors, :, :])
		else:
			x = y_true[:, :, :, 4 * num_anchors:] - y_pred
			x_abs = K.abs(x)
			x_bool = K.cast(K.less_equal(x_abs, 1.0), tf.float32)

			return lambda_rpn_regr * K.sum(
				y_true[:, :, :, :4 * num_anchors] * (x_bool * (0.5 * x * x) + (1 - x_bool) * (x_abs - 0.5))) / K.sum(epsilon + y_true[:, :, :, :4 * num_anchors])

	return rpn_loss_regr_fixed_num 

def rpn_loss_regr(num_anchors):
    def rpn_loss_regr_fixed_num(y_true, y_pred):
        if K.image_dim_ordering() == 'th':
            x = y_true[:, 4 * num_anchors:, :, :] - y_pred
            x_abs = K.abs(x)
            x_bool = K.less_equal(x_abs, 1.0)
            return lambda_rpn_regr * K.sum(
                y_true[:, :4 * num_anchors, :, :] * (x_bool * (0.5 * x * x) + (1 - x_bool) * (x_abs - 0.5))) / K.sum(epsilon + y_true[:, :4 * num_anchors, :, :])
        else:
            x = y_true[:, :, :, 4 * num_anchors:] - y_pred
            x_abs = K.abs(x)
            x_bool = K.cast(K.less_equal(x_abs, 1.0), tf.float32)

            return lambda_rpn_regr * K.sum(
                y_true[:, :, :, :4 * num_anchors] * (x_bool * (0.5 * x * x) + (1 - x_bool) * (x_abs - 0.5))) / K.sum(epsilon + y_true[:, :, :, :4 * num_anchors])

    return rpn_loss_regr_fixed_num 

def predict(self, image, img_channels=3):
        if K.image_dim_ordering() == 'th' and image.shape != (1,img_channels, IMAGE_SIZE, IMAGE_SIZE):
            image = resize_with_pad(image)
            image = image.reshape((1, img_channels, IMAGE_SIZE, IMAGE_SIZE))
        elif K.image_dim_ordering() == 'tf' and image.shape != (1, IMAGE_SIZE, IMAGE_SIZE, img_channels):
            image = resize_with_pad(image)
            image = image.reshape((1, IMAGE_SIZE, IMAGE_SIZE, img_channels))
        image = image.astype('float32')
        image /= 255
        if DEBUG_MUTE:
            result = self.model.predict_proba(image, verbose=0)
            result = self.model.predict_classes(image, verbose=0)
        else:
            result = self.model.predict_proba(image)
            print(result)
            result = self.model.predict_classes(image)
            print(result)

        return result[0] 

def transition_block(ip, nb_filter, dropout_rate=None, weight_decay=1E-4):
    ''' Apply BatchNorm, Relu 1x1, Conv2D, optional dropout and Maxpooling2D

    Args:
        ip: keras tensor
        nb_filter: number of filters
        dropout_rate: dropout rate
        weight_decay: weight decay factor

    Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool

    '''

    concat_axis = 1 if K.image_dim_ordering() == "th" else -1

    x = Convolution2D(nb_filter, 1, 1, init="he_uniform", border_mode="same", bias=False,
                      W_regularizer=l2(weight_decay))(ip)
    if dropout_rate:
        x = Dropout(dropout_rate)(x)
    x = AveragePooling2D((2, 2), strides=(2, 2))(x)

    x = BatchNormalization(mode=0, axis=concat_axis, gamma_regularizer=l2(weight_decay),
                           beta_regularizer=l2(weight_decay))(x)

    return x 

def deprocess_image(x):
    """ Same normalization as in:
    https://github.com/fchollet/keras/blob/master/examples/conv_filter_visualization.py
    """
    if np.ndim(x) > 3:
        x = np.squeeze(x)
    # normalize tensor: center on 0., ensure std is 0.1
    x = x - x.mean()
    x = x / (x.std() + 1e-5)
    x = x * 0.1

    # clip to [0, 1]
    x = x + 0.5
    x = np.clip(x, 0, 1)

    # convert to RGB array
    x = x * 255
    if K.image_dim_ordering() == 'th':
        x = x.transpose((1, 2, 0))
    x = np.clip(x, 0, 255).astype('uint8')
    return x 

def call(self, x, mask=None):
        if K.image_dim_ordering == "th":
            _, f, r, c = self.shape
        else:
            _, r, c, f = self.shape
        squared = K.square(x)
        pooled = K.pool2d(squared, (self.n, self.n), strides=(1, 1),
            padding="same", pool_mode="avg")
        if K.image_dim_ordering == "th":
            summed = K.sum(pooled, axis=1, keepdims=True)
            averaged = self.alpha * K.repeat_elements(summed, f, axis=1)
        else:
            summed = K.sum(pooled, axis=3, keepdims=True)
            averaged = self.alpha * K.repeat_elements(summed, f, axis=3)
        denom = K.pow(self.k + averaged, self.beta)
        return x / denom 

def loss(self, x):
		# reshape
		if K.image_dim_ordering() == 'th':
			x = x.reshape((1, 3, self.img_nrows, self.img_ncols))
		else:
			x = x.reshape((1, self.img_nrows, self.img_ncols, 3))

		outs = self.loss_and_grads([x])
		loss_value = outs[0]
		return loss_value 

def grads(self, x):
		# reshape
		if K.image_dim_ordering() == 'th':
			x = x.reshape((1, 3, self.img_nrows, self.img_ncols))
		else:
			x = x.reshape((1, self.img_nrows, self.img_ncols, 3))

		outs = self.loss_and_grads([x])

		if len(outs[1:]) == 1:
			grad_values = outs[1].flatten().astype('float64')
		else:
			grad_values = np.array(outs[1:]).flatten().astype('float64')
		return grad_values 

def __init__(self, image_size,num_classes,stage_num,lambda_d):
        
        if K.image_dim_ordering() == "th":
            logging.debug("image_dim_ordering = 'th'")
            self._channel_axis = 1
            self._input_shape = (3, image_size, image_size)
        else:
            logging.debug("image_dim_ordering = 'tf'")
            self._channel_axis = -1
            self._input_shape = (image_size, image_size, 3)

        self.num_classes = num_classes
        self.stage_num = stage_num
        self.lambda_d = lambda_d 

def dense_block(x, nb_layers, nb_filter, growth_rate, dropout_rate=None, weight_decay=1E-4):
    ''' Build a dense_block where the output of each conv_block is fed to subsequent ones

    Args:
        x: keras tensor
        nb_layers: the number of layers of conv_block to append to the model.
        nb_filter: number of filters
        growth_rate: growth rate
        dropout_rate: dropout rate
        weight_decay: weight decay factor

    Returns: keras tensor with nb_layers of conv_block appended

    '''

    concat_axis = 1 if K.image_dim_ordering() == "th" else -1

    feature_list = [x]

    for i in range(nb_layers):
        x = conv_block(x, growth_rate, dropout_rate, weight_decay)
        feature_list.append(x)
        x = merge(feature_list, mode='concat', concat_axis=concat_axis)
        nb_filter += growth_rate

    return x, nb_filter 

def dense_block(x, nb_layers, nb_filter, growth_rate, dropout_rate=None, weight_decay=1E-4):
    concat_axis = 1 if K.image_dim_ordering() == "th" else -1
    feature_list = [x]

    for i in range(nb_layers):
        x = conv_block(x, growth_rate, dropout_rate, weight_decay)
        feature_list.append(x)
        x = Concatenate(axis=concat_axis)(feature_list)
        nb_filter += growth_rate

    return x, nb_filter 

def __init__(self, pool_list, pool_type, **kwargs):

        self.dim_ordering = K.image_dim_ordering()
        assert self.dim_ordering in {'tf', 'th'}, 'dim_ordering must be in {tf, th}'

        self.pool_list = pool_list
        self.pool_type = pool_type
        self.num_outputs_per_channel = sum([i * i for i in pool_list])

        super(SpatialPyramidPooling, self).__init__(**kwargs)