def ResNet50(input_tensor=None, pooling=None, **kwargs): """Instantiates the ResNet50 architecture. # Arguments # Returns A Keras model instance. """ # Input arguments include_top = get_varargin(kwargs, 'include_top', True) nb_classes = get_varargin(kwargs, 'nb_classes', 1000) default_input_shape = _obtain_input_shape(None, default_size=224, min_size=197, data_format=K.image_data_format(), require_flatten=include_top) input_shape = get_varargin(kwargs, 'input_shape', default_input_shape) if input_tensor is None: img_input = KL.Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = KL.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if K.image_data_format() == 'channels_last' else 1 x = KL.ZeroPadding2D((3, 3))(img_input) x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x) x = KL.BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = KL.Activation('relu')(x) x = KL.MaxPooling2D((3, 3), strides=(2, 2))(x) for stage, nb_block in zip([2,3,4,5], [3,4,6,3]): for blk in range(nb_block): conv_block = True if blk == 0 else False strides = (2,2) if stage>2 and blk==0 else (1,1) x = identity_block(x, stage = stage, block_id = blk + 1, conv_block = conv_block, strides = strides) x = KL.AveragePooling2D((7, 7), name='avg_pool')(x) if include_top: x = KL.Flatten()(x) x = KL.Dense(nb_classes, activation='softmax', name='fc1000')(x) else: if pooling == 'avg': x = KL.GlobalAveragePooling2D()(x) elif pooling == 'max': x = KL.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='resnet50') return model
def assemble_layers(self): from tensorflow.python.keras import backend, layers from tensorflow.python.keras.applications import imagenet_utils include_top = True weights = None pooling = None classes = 1 if nnstate.FLAGS.PRED_SIZE != 2: err('bad') classifier_activation = 'sigmoid' x = conv2d_bn(self.inputs, 32, 3, strides=2, padding='valid') x = conv2d_bn(x, 32, 3, padding='valid') x = conv2d_bn(x, 64, 3) x = layers.MaxPooling2D(3, strides=2)(x) x = conv2d_bn(x, 80, 1, padding='valid') x = conv2d_bn(x, 192, 3, padding='valid') x = layers.MaxPooling2D(3, strides=2)(x) # Mixed 5b (Inception-A block): 35 x 35 x 320 branch_0 = conv2d_bn(x, 96, 1) branch_1 = conv2d_bn(x, 48, 1) branch_1 = conv2d_bn(branch_1, 64, 5) branch_2 = conv2d_bn(x, 64, 1) branch_2 = conv2d_bn(branch_2, 96, 3) branch_2 = conv2d_bn(branch_2, 96, 3) branch_pool = layers.AveragePooling2D(3, strides=1, padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1) branches = [branch_0, branch_1, branch_2, branch_pool] channel_axis = 1 if backend.image_data_format( ) == 'channels_first' else 3 x = layers.Concatenate(axis=channel_axis, name='mixed_5b')(branches) # 10x block35 (Inception-ResNet-A block): 35 x 35 x 320 for block_idx in range(1, 11): x = inception_resnet_block(x, scale=0.17, block_type='block35', block_idx=block_idx) # Mixed 6a (Reduction-A block): 17 x 17 x 1088 branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid') branch_1 = conv2d_bn(x, 256, 1) branch_1 = conv2d_bn(branch_1, 256, 3) branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_6a')(branches) # 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088 for block_idx in range(1, 21): x = inception_resnet_block(x, scale=0.1, block_type='block17', block_idx=block_idx) # Mixed 7a (Reduction-B block): 8 x 8 x 2080 branch_0 = conv2d_bn(x, 256, 1) branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid') branch_1 = conv2d_bn(x, 256, 1) branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid') branch_2 = conv2d_bn(x, 256, 1) branch_2 = conv2d_bn(branch_2, 288, 3) branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_2, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_7a')(branches) # 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080 for block_idx in range(1, 10): x = inception_resnet_block(x, scale=0.2, block_type='block8', block_idx=block_idx) x = inception_resnet_block(x, scale=1., activation=None, block_type='block8', block_idx=10) # Final convolution block: 8 x 8 x 1536 x = conv2d_bn(x, 1536, 1, name='conv_7b') if include_top: # Classification block x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) return x
def Xception( include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', ): """Instantiates the Xception architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Note that the default input image size for this model is 299x299. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.xception.preprocess_input` for an example. Arguments: include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(299, 299, 3)`. It should have exactly 3 inputs channels, and width and height should be no smaller than 71. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=299, min_size=71, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1 x = layers.Conv2D(32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(img_input) x = layers.BatchNormalization(axis=channel_axis, name='block1_conv1_bn')(x) x = layers.Activation('relu', name='block1_conv1_act')(x) x = layers.Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block1_conv2_bn')(x) x = layers.Activation('relu', name='block1_conv2_act')(x) residual = layers.Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block2_sepconv1_bn')(x) x = layers.Activation('relu', name='block2_sepconv2_act')(x) x = layers.SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block2_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block2_pool')(x) x = layers.add([x, residual]) residual = layers.Conv2D(256, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block3_sepconv1_act')(x) x = layers.SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block3_sepconv1_bn')(x) x = layers.Activation('relu', name='block3_sepconv2_act')(x) x = layers.SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block3_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block3_pool')(x) x = layers.add([x, residual]) residual = layers.Conv2D(728, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block4_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block4_sepconv1_bn')(x) x = layers.Activation('relu', name='block4_sepconv2_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block4_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block4_pool')(x) x = layers.add([x, residual]) for i in range(8): residual = x prefix = 'block' + str(i + 5) x = layers.Activation('relu', name=prefix + '_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv1_bn')(x) x = layers.Activation('relu', name=prefix + '_sepconv2_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv2_bn')(x) x = layers.Activation('relu', name=prefix + '_sepconv3_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv3_bn')(x) x = layers.add([x, residual]) residual = layers.Conv2D(1024, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block13_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block13_sepconv1_bn')(x) x = layers.Activation('relu', name='block13_sepconv2_act')(x) x = layers.SeparableConv2D(1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block13_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block13_pool')(x) x = layers.add([x, residual]) x = layers.SeparableConv2D(1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block14_sepconv1_bn')(x) x = layers.Activation('relu', name='block14_sepconv1_act')(x) x = layers.SeparableConv2D(2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block14_sepconv2_bn')(x) x = layers.Activation('relu', name='block14_sepconv2_act')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='xception') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'xception_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models', file_hash='0a58e3b7378bc2990ea3b43d5981f1f6') else: weights_path = data_utils.get_file( 'xception_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='b0042744bf5b25fce3cb969f33bebb97') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def EfficientNet(width_coefficient, depth_coefficient, default_size, dropout_rate=0.2, drop_connect_rate=0.2, depth_divisor=8, activation='swish', blocks_args='default', model_name='efficientnet', include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the EfficientNet architecture using given scaling coefficients. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Arguments: width_coefficient: float, scaling coefficient for network width. depth_coefficient: float, scaling coefficient for network depth. default_size: integer, default input image size. dropout_rate: float, dropout rate before final classifier layer. drop_connect_rate: float, dropout rate at skip connections. depth_divisor: integer, a unit of network width. activation: activation function. blocks_args: list of dicts, parameters to construct block modules. model_name: string, model name. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False. It should have exactly 3 inputs channels. pooling: optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Returns: A Keras model instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if blocks_args == 'default': blocks_args = DEFAULT_BLOCKS_ARGS if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 def round_filters(filters, divisor=depth_divisor): """Round number of filters based on depth multiplier.""" filters *= width_coefficient new_filters = max(divisor, int(filters + divisor / 2) // divisor * divisor) # Make sure that round down does not go down by more than 10%. if new_filters < 0.9 * filters: new_filters += divisor return int(new_filters) def round_repeats(repeats): """Round number of repeats based on depth multiplier.""" return int(math.ceil(depth_coefficient * repeats)) # Build stem x = img_input x = layers.Rescaling(1. / 255.)(x) x = layers.Normalization(axis=bn_axis)(x) x = layers.ZeroPadding2D( padding=imagenet_utils.correct_pad(x, 3), name='stem_conv_pad')(x) x = layers.Conv2D( round_filters(32), 3, strides=2, padding='valid', use_bias=False, kernel_initializer=CONV_KERNEL_INITIALIZER, name='stem_conv')(x) x = layers.BatchNormalization(axis=bn_axis, name='stem_bn')(x) x = layers.Activation(activation, name='stem_activation')(x) # Build blocks blocks_args = copy.deepcopy(blocks_args) b = 0 blocks = float(sum(args['repeats'] for args in blocks_args)) for (i, args) in enumerate(blocks_args): assert args['repeats'] > 0 # Update block input and output filters based on depth multiplier. args['filters_in'] = round_filters(args['filters_in']) args['filters_out'] = round_filters(args['filters_out']) for j in range(round_repeats(args.pop('repeats'))): # The first block needs to take care of stride and filter size increase. if j > 0: args['strides'] = 1 args['filters_in'] = args['filters_out'] x = block( x, activation, drop_connect_rate * b / blocks, name='block{}{}_'.format(i + 1, chr(j + 97)), **args) b += 1 # Build top x = layers.Conv2D( round_filters(1280), 1, padding='same', use_bias=False, kernel_initializer=CONV_KERNEL_INITIALIZER, name='top_conv')(x) x = layers.BatchNormalization(axis=bn_axis, name='top_bn')(x) x = layers.Activation(activation, name='top_activation')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) if dropout_rate > 0: x = layers.Dropout(dropout_rate, name='top_dropout')(x) x = layers.Dense( classes, activation='softmax', kernel_initializer=DENSE_KERNEL_INITIALIZER, name='probs')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name=model_name) # Load weights. if weights == 'imagenet': if include_top: file_suffix = '.h5' file_hash = WEIGHTS_HASHES[model_name[-2:]][0] else: file_suffix = '_notop.h5' file_hash = WEIGHTS_HASHES[model_name[-2:]][1] file_name = model_name + file_suffix weights_path = data_utils.get_file( file_name, BASE_WEIGHTS_PATH + file_name, cache_subdir='models', file_hash=file_hash) model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def NASNet( input_shape=None, penultimate_filters=4032, num_blocks=6, stem_block_filters=96, skip_reduction=True, filter_multiplier=2, include_top=True, weights=None, input_tensor=None, pooling=None, classes=1000, default_size=None, classifier_activation='softmax', ): """Instantiates a NASNet model. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.nasnet.preprocess_input` for an example. Arguments: input_shape: Optional shape tuple, the input shape is by default `(331, 331, 3)` for NASNetLarge and `(224, 224, 3)` for NASNetMobile. It should have exactly 3 input channels, and width and height should be no smaller than 32. E.g. `(224, 224, 3)` would be one valid value. penultimate_filters: Number of filters in the penultimate layer. NASNet models use the notation `NASNet (N @ P)`, where: - N is the number of blocks - P is the number of penultimate filters num_blocks: Number of repeated blocks of the NASNet model. NASNet models use the notation `NASNet (N @ P)`, where: - N is the number of blocks - P is the number of penultimate filters stem_block_filters: Number of filters in the initial stem block skip_reduction: Whether to skip the reduction step at the tail end of the network. filter_multiplier: Controls the width of the network. - If `filter_multiplier` < 1.0, proportionally decreases the number of filters in each layer. - If `filter_multiplier` > 1.0, proportionally increases the number of filters in each layer. - If `filter_multiplier` = 1, default number of filters from the paper are used at each layer. include_top: Whether to include the fully-connected layer at the top of the network. weights: `None` (random initialization) or `imagenet` (ImageNet weights) input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: Optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. default_size: Specifies the default image size of the model classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: In case of invalid argument for `weights`, invalid input shape or invalid `penultimate_filters` value. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') if (isinstance(input_shape, tuple) and None in input_shape and weights == 'imagenet'): raise ValueError('When specifying the input shape of a NASNet' ' and loading `ImageNet` weights, ' 'the input_shape argument must be static ' '(no None entries). Got: `input_shape=' + str(input_shape) + '`.') if default_size is None: default_size = 331 # Determine proper input shape and default size. input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=True, weights=weights) if backend.image_data_format() != 'channels_last': logging.warning( 'The NASNet family of models is only available ' 'for the input data format "channels_last" ' '(width, height, channels). ' 'However your settings specify the default ' 'data format "channels_first" (channels, width, height).' ' You should set `image_data_format="channels_last"` ' 'in your Keras config located at ~/.keras/keras.json. ' 'The model being returned right now will expect inputs ' 'to follow the "channels_last" data format.') backend.set_image_data_format('channels_last') old_data_format = 'channels_first' else: old_data_format = None if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if penultimate_filters % (24 * (filter_multiplier**2)) != 0: raise ValueError( 'For NASNet-A models, the `penultimate_filters` must be a multiple ' 'of 24 * (`filter_multiplier` ** 2). Current value: %d' % penultimate_filters) channel_dim = 1 if backend.image_data_format() == 'channels_first' else -1 filters = penultimate_filters // 24 x = layers.Conv2D(stem_block_filters, (3, 3), strides=(2, 2), padding='valid', use_bias=False, name='stem_conv1', kernel_initializer='he_normal')(img_input) x = layers.BatchNormalization(axis=channel_dim, momentum=0.9997, epsilon=1e-3, name='stem_bn1')(x) p = None x, p = _reduction_a_cell(x, p, filters // (filter_multiplier**2), block_id='stem_1') x, p = _reduction_a_cell(x, p, filters // filter_multiplier, block_id='stem_2') for i in range(num_blocks): x, p = _normal_a_cell(x, p, filters, block_id='%d' % (i)) x, p0 = _reduction_a_cell(x, p, filters * filter_multiplier, block_id='reduce_%d' % (num_blocks)) p = p0 if not skip_reduction else p for i in range(num_blocks): x, p = _normal_a_cell(x, p, filters * filter_multiplier, block_id='%d' % (num_blocks + i + 1)) x, p0 = _reduction_a_cell(x, p, filters * filter_multiplier**2, block_id='reduce_%d' % (2 * num_blocks)) p = p0 if not skip_reduction else p for i in range(num_blocks): x, p = _normal_a_cell(x, p, filters * filter_multiplier**2, block_id='%d' % (2 * num_blocks + i + 1)) x = layers.Activation('relu')(x) if include_top: x = layers.GlobalAveragePooling2D()(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input model = training.Model(inputs, x, name='NASNet') # Load weights. if weights == 'imagenet': if default_size == 224: # mobile version if include_top: weights_path = data_utils.get_file( 'nasnet_mobile.h5', NASNET_MOBILE_WEIGHT_PATH, cache_subdir='models', file_hash='020fb642bf7360b370c678b08e0adf61') else: weights_path = data_utils.get_file( 'nasnet_mobile_no_top.h5', NASNET_MOBILE_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='1ed92395b5b598bdda52abe5c0dbfd63') model.load_weights(weights_path) elif default_size == 331: # large version if include_top: weights_path = data_utils.get_file( 'nasnet_large.h5', NASNET_LARGE_WEIGHT_PATH, cache_subdir='models', file_hash='11577c9a518f0070763c2b964a382f17') else: weights_path = data_utils.get_file( 'nasnet_large_no_top.h5', NASNET_LARGE_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='d81d89dc07e6e56530c4e77faddd61b5') model.load_weights(weights_path) else: raise ValueError( 'ImageNet weights can only be loaded with NASNetLarge' ' or NASNetMobile') elif weights is not None: model.load_weights(weights) if old_data_format: backend.set_image_data_format(old_data_format) return model
def MobileNetV3(stack_fn, last_point_ch, input_shape=None, alpha=1.0, model_type='large', minimalistic=False, include_top=True, weights='imagenet', input_tensor=None, classes=1000, pooling=None, dropout_rate=0.2, classifier_activation='softmax'): if not (weights in {'imagenet', None} or file_io.file_exists_v2(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') # Determine proper input shape and default size. # If both input_shape and input_tensor are used, they should match if input_shape is not None and input_tensor is not None: try: is_input_t_tensor = backend.is_keras_tensor(input_tensor) except ValueError: try: is_input_t_tensor = backend.is_keras_tensor( layer_utils.get_source_inputs(input_tensor)) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is not type input_tensor') if is_input_t_tensor: if backend.image_data_format == 'channels_first': if backend.int_shape(input_tensor)[1] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: if backend.int_shape(input_tensor)[2] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: raise ValueError('input_tensor specified: ', input_tensor, 'is not a keras tensor') # If input_shape is None, infer shape from input_tensor if input_shape is None and input_tensor is not None: try: backend.is_keras_tensor(input_tensor) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is type: ', type(input_tensor), 'which is not a valid type') if backend.is_keras_tensor(input_tensor): if backend.image_data_format() == 'channels_first': rows = backend.int_shape(input_tensor)[2] cols = backend.int_shape(input_tensor)[3] input_shape = (3, cols, rows) else: rows = backend.int_shape(input_tensor)[1] cols = backend.int_shape(input_tensor)[2] input_shape = (cols, rows, 3) # If input_shape is None and input_tensor is None using standart shape if input_shape is None and input_tensor is None: input_shape = (None, None, 3) if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if rows and cols and (rows < 32 or cols < 32): raise ValueError( 'Input size must be at least 32x32; got `input_shape=' + str(input_shape) + '`') if weights == 'imagenet': if (not minimalistic and alpha not in [0.75, 1.0] or minimalistic and alpha != 1.0): raise ValueError( 'If imagenet weights are being loaded, ' 'alpha can be one of `0.75`, `1.0` for non minimalistic' ' or `1.0` for minimalistic only.') if rows != cols or rows != 224: logging.warning('`input_shape` is undefined or non-square, ' 'or `rows` is not 224.' ' Weights for input shape (224, 224) will be' ' loaded as the default.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1 if minimalistic: kernel = 3 activation = relu se_ratio = None else: kernel = 5 activation = hard_swish se_ratio = 0.25 x = img_input x = layers.Rescaling(1. / 255.)(x) x = layers.Conv2D(16, kernel_size=3, strides=(2, 2), padding='same', use_bias=False, name='Conv')(x) x = layers.BatchNormalization(axis=channel_axis, epsilon=1e-3, momentum=0.999, name='Conv/BatchNorm')(x) x = activation(x) x = stack_fn(x, kernel, activation, se_ratio) last_conv_ch = _depth(backend.int_shape(x)[channel_axis] * 6) # if the width multiplier is greater than 1 we # increase the number of output channels if alpha > 1.0: last_point_ch = _depth(last_point_ch * alpha) x = layers.Conv2D(last_conv_ch, kernel_size=1, padding='same', use_bias=False, name='Conv_1')(x) x = layers.BatchNormalization(axis=channel_axis, epsilon=1e-3, momentum=0.999, name='Conv_1/BatchNorm')(x) x = activation(x) x = layers.Conv2D(last_point_ch, kernel_size=1, padding='same', use_bias=True, name='Conv_2')(x) x = activation(x) if include_top: x = layers.GlobalAveragePooling2D()(x) if channel_axis == 1: x = layers.Reshape((last_point_ch, 1, 1))(x) else: x = layers.Reshape((1, 1, last_point_ch))(x) if dropout_rate > 0: x = layers.Dropout(dropout_rate)(x) x = layers.Conv2D(classes, kernel_size=1, padding='same', name='Logits')(x) x = layers.Flatten()(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Activation(activation=classifier_activation, name='Predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name='MobilenetV3' + model_type) # Load weights. if weights == 'imagenet': model_name = '{}{}_224_{}_float'.format( model_type, '_minimalistic' if minimalistic else '', str(alpha)) if include_top: file_name = 'weights_mobilenet_v3_' + model_name + '.h5' file_hash = WEIGHTS_HASHES[model_name][0] else: file_name = 'weights_mobilenet_v3_' + model_name + '_no_top.h5' file_hash = WEIGHTS_HASHES[model_name][1] weights_path = data_utils.get_file(file_name, BASE_WEIGHT_PATH + file_name, cache_subdir='models', file_hash=file_hash) model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def VGG16(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the VGG16 model. By default, it loads weights pre-trained on ImageNet. Check 'weights' for other options. This model can be built both with 'channels_first' data format (channels, height, width) or 'channels_last' data format (height, width, channels). The default input size for this model is 224x224. Arguments: include_top: whether to include the 3 fully-connected layers at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 input channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Returns: A Keras model instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input) x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x) x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # Classification block x = layers.Flatten(name='flatten')(x) x = layers.Dense(4096, activation='relu', name='fc1')(x) x = layers.Dense(4096, activation='relu', name='fc2')(x) x = layers.Dense(classes, activation='softmax', name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='vgg16') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', file_hash='64373286793e3c8b2b4e3219cbf3544b') else: weights_path = data_utils.get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='6d6bbae143d832006294945121d1f1fc') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def WideResNet( stack_fn, preact=True, model_name='resnet', head='one_head', head_mlp='', input_shape=None, pooling=None, activation='leaky_relu', bn_sync=BN_SYNC, num_class=1000, **kwargs): # Input layer. inputs = img_input = layers.Input(shape=input_shape) # Conv1 block. # CIFAR (32x32) or STL-10 (96x96) use small input; otherwise use large input if input_shape[0] == 256: kernel_size, stride, maxpool = 7, 2, True elif input_shape[0] in [96, 128]: kernel_size, stride, maxpool = 3, 1, False elif input_shape[0] == 32: kernel_size, stride, maxpool = 3, 1, False else: raise NotImplementedError x = convnxn(img_input, filters=16, kernel_size=kernel_size, strides=stride, use_bias=False, name='conv1_conv') if not preact: x = batchnorm(x, bn_mom=0.999, bn_eps=0.001, bn_sync=bn_sync, name='conv1_bn') x = nonlinearity(x, layer_activation=activation, name='conv1_'+activation) if maxpool: x = layers.MaxPooling2D(3, strides=2, padding='SAME', name='pool1_pool')(x) # Conv2 to Conv5 blocks x = stack_fn(x) if preact: x = batchnorm(x, bn_mom=0.999, bn_eps=0.001, bn_sync=bn_sync, name='post_bn') x = nonlinearity(x, layer_activation=activation, name='post_'+activation) # Pooling layer if pooling in ['avg', None]: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Classifier and/or embedding head outputs = get_head( x, arch=head, dims=head_mlp, num_class=num_class, bn_mom=0.999, bn_eps=0.001, bn_sync=bn_sync, classifier_activation='linear') # Create model. if bn_sync: model_name += '_sbn' if not head in ['linear', None, False]: model_name += '_{}'.format(head) if head_mlp is not None and len(head_mlp) > 0: model_name += '_mlp' + '_'.join(['%d'%d for d in head_mlp]) return training.Model(inputs, outputs, name=model_name)
def MobileNetV2(input_shape=None, alpha=1.0, include_top=True, input_tensor=None, pooling=None, classes=1000): """Instantiates the MobileNetV2 architecture. Args: input_shape: optional shape tuple, to be specified if you would like to use a model with an input img resolution that is not (224, 224, 3). It should have exactly 3 inputs channels (224, 224, 3). You can also omit this option if you would like to infer input_shape from an input_tensor. If you choose to include both input_tensor and input_shape then input_shape will be used if they match, if the shapes do not match then we will throw an error. E.g. `(160, 160, 3)` would be one valid value. alpha: controls the width of the network. This is known as the width multiplier in the MobileNetV2 paper, but the name is kept for consistency with MobileNetV1 in Keras. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. include_top: whether to include the fully-connected layer at the top of the network. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Returns: A Keras model instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape or invalid alpha, rows when weights='imagenet' """ if classes == 1000: raise ValueError('If use dataset is `imagenet`, please use it,' 'otherwise please use classifier images classes.') if input_shape == (32, 32, 1): raise ValueError( 'If use input shape is `32 * 32 * 1`, please don`t use it! ' 'So you should change network architecture ' 'or use input shape is `224 * 224 * 3`.') # Determine proper input shape and default size. # If both input_shape and input_tensor are used, they should match if input_shape is not None and input_tensor is not None: try: is_input_t_tensor = backend.is_keras_tensor(input_tensor) except ValueError: try: is_input_t_tensor = backend.is_keras_tensor( utils.get_source_inputs(input_tensor)) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is not type input_tensor') if is_input_t_tensor: if backend.image_data_format == 'channels_first': if backend.int_shape(input_tensor)[1] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: if backend.int_shape(input_tensor)[2] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: raise ValueError('input_tensor specified: ', input_tensor, 'is not a keras tensor') # If input_shape is None, infer shape from input_tensor if input_shape is None and input_tensor is not None: try: backend.is_keras_tensor(input_tensor) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is type: ', type(input_tensor), 'which is not a valid type') if input_shape is None and not backend.is_keras_tensor(input_tensor): pass elif input_shape is None and backend.is_keras_tensor(input_tensor): if backend.image_data_format() == 'channels_first': rows = backend.int_shape(input_tensor)[2] cols = backend.int_shape(input_tensor)[3] else: rows = backend.int_shape(input_tensor)[1] cols = backend.int_shape(input_tensor)[2] if rows == cols and rows in [96, 128, 160, 192, 224]: pass else: pass # If input_shape is None and no input_tensor elif input_shape is None: pass # If input_shape is not None, assume default size else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [96, 128, 160, 192, 224]: pass else: pass if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor first_block_filters = _make_divisible(32 * alpha, 8) x = layers.ZeroPadding2D(padding=correct_pad(backend, img_input, 3), name='Conv1_pad')(img_input) x = layers.Conv2D(first_block_filters, kernel_size=3, strides=(2, 2), padding='valid', use_bias=False, name='Conv1')(x) x = layers.BatchNormalization(epsilon=1e-3, momentum=0.999, name='bn_Conv1')(x) x = layers.ReLU(6., name='Conv1_relu')(x) x = _inverted_res_block(x, filters=16, alpha=alpha, stride=1, expansion=1, block_id=0) x = _inverted_res_block(x, filters=24, alpha=alpha, stride=2, expansion=6, block_id=1) x = _inverted_res_block(x, filters=24, alpha=alpha, stride=1, expansion=6, block_id=2) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=2, expansion=6, block_id=3) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=4) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=5) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=2, expansion=6, block_id=6) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=7) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=8) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=9) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=10) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=11) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=12) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=2, expansion=6, block_id=13) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=14) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=15) x = _inverted_res_block(x, filters=320, alpha=alpha, stride=1, expansion=6, block_id=16) # no alpha applied to last conv as stated in the paper: # if the width multiplier is greater than 1 we # increase the number of output channels if alpha > 1.0: last_block_filters = _make_divisible(1280 * alpha, 8) else: last_block_filters = 1280 x = layers.Conv2D(last_block_filters, kernel_size=1, use_bias=False, name='Conv_1')(x) x = layers.BatchNormalization(epsilon=1e-3, momentum=0.999, name='Conv_1_bn')(x) x = layers.ReLU(6., name='out_relu')(x) if include_top: x = layers.GlobalAveragePooling2D()(x) x = layers.Dense(classes, activation='softmax', use_bias=True, name='Logits')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows)) return model
def efficientnetB0(width_coeff=1, depth_coeff=1, default_img_size=224, dropoutrate=0.2, drop_connect_rate=0.2, depth_divisor=8, activations='swish', block_args='default', include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax'): if block_args == 'default': block_args = DEFAULT_BLOCKS_ARGS if not (weights in {'imagenet', None} or file_io.file_exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # proper input shape check input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_img_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 def round_filters(filters, divisor=depth_divisor): """ round number of filters based on depth multiplier""" filters *= width_coeff new_filters = max(divisor, int(filters + divisor / 2) // divisor * divisor) #making sure round down does not go down by 10% if new_filters < 0.9 * filters: new_filters += divisor return int(new_filters) def round_repeats(repeats): """Round number of repeats based on depth multiplier.""" return int(math.ceil(depth_coeff * repeats)) #building stem x = img_input x = layers.Rescaling(1. / 255.)(x) x = layers.Normalization(axis=bn_axis)(x) x = layers.ZeroPadding2D(padding=imagenet_utils.correct_pad(x, 3))(x) x = layers.Conv2D(round_filters(32), kernel_size=3, strides=2, padding='valid', use_bias=False, kernel_initializer=CONV_KERNEL_INITIALIZER)(x) x = layers.BatchNormalization(axis=bn_axis)(x) x = layers.Activation(activations)(x) #building blocks block_args = copy.deepcopy(block_args) b = 0 blocks = float(sum(round_repeats(args['repeats']) for args in block_args)) for (i, args) in enumerate(block_args): assert args['repeats'] > 0 args['filters_in'] = round_filters(args['filters_in']) args['filters_out'] = round_filters(args['filters_out']) for j in range(round_repeats(args.pop('repeats'))): # The first block needs to take care of stride and filter size increase. if j > 0: args['strides'] = 1 args['filters_in'] = args['filters_out'] x = mbconvblock(inputs=x, activations=activations, droprate=drop_connect_rate * b / blocks, name=str(i), **args) b += 1 #build top x = layers.Conv2D(round_filters(1280), kernel_size=1, padding='same', use_bias=False, kernel_initializer=CONV_KERNEL_INITIALIZER)(x) x = layers.BatchNormalization(axis=bn_axis)(x) x = layers.Activation(activations)(x) if include_top: x = layers.GlobalAveragePooling2D()(x) if dropoutrate > 0: x = layers.Dropout(dropoutrate)(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, kernel_initializer=DENSE_KERNEL_INITIALIZER)(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input #creating model model = training.Model(inputs, x) return model
def DenseNet(blocks, classes, filters, dropout_rate, include_top=True, weights=None, input_tensor=None, input_shape=None, pooling=None, classifier_activation=None): # Determine proper input shape if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(x) x = layers.Conv2D(2 * filters, 3, strides=2, padding='same', name='conv1/conv')(img_input) # x = layers.BatchNormalization(axis=bn_axis, # epsilon=1.001e-5, # name='conv1/bn')(x) # x = layers.Activation('relu', name='conv1/relu')(x) # x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x) x = layers.MaxPooling2D(pool_size=(3, 3), strides=2, name='pool1')(x) # x = dense_block(x, # blocks=6, # filters=filters, # dropout_rate=dropout_rate, # name='dense_1') # x = transition_block(x, dropout_rate=dropout_rate, name='trans_2') # x = dense_block(x, # blocks=12, # filters=filters, # dropout_rate=dropout_rate, # name='dense_2') # x = transition_block(x, dropout_rate=dropout_rate, name='trans_3') # x = dense_block(x, # blocks=24, # filters=filters, # dropout_rate=dropout_rate, # name='dense_3') # x = transition_block(x, dropout_rate=dropout_rate, name='trans_4') # x = dense_block(x, # blocks=16, # filters=filters, # dropout_rate=dropout_rate, # name='dense_4') for i in range(blocks): x = dense_block(x, blocks=6, filters=filters, dropout_rate=dropout_rate, name='dense_' + str(i)) x = transition_block(x, dropout_rate=dropout_rate, name='trans_' + str(i)) x = dense_block(x, blocks=12, filters=filters, dropout_rate=dropout_rate, name='dense_final') x = layers.BatchNormalization()(x) x = layers.Activation('relu', name='relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) x = layers.Flatten()(x) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='NET.model') return model
def VGG19( include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', ): """Instantiates the VGG19 architecture. Reference: - [Very Deep Convolutional Networks for Large-Scale Image Recognition]( https://arxiv.org/abs/1409.1556) (ICLR 2015) By default, it loads weights pre-trained on ImageNet. Check 'weights' for other options. This model can be built both with 'channels_first' data format (channels, height, width) or 'channels_last' data format (height, width, channels). The default input size for this model is 224x224. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.vgg19.preprocess_input` for an example. Arguments: include_top: whether to include the 3 fully-connected layers at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input) x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x) x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv4')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv4')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv4')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # Classification block x = layers.Flatten(name='flatten')(x) x = layers.Dense(4096, activation='relu', name='fc1')(x) x = layers.Dense(4096, activation='relu', name='fc2')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='vgg19') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'vgg19_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', file_hash='cbe5617147190e668d6c5d5026f83318') else: weights_path = data_utils.get_file( 'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='253f8cb515780f3b799900260a226db6') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
In the functional API, models are created by specifying their inputs and outputs in a graph of layers. That means that a single graph of layers can be used to generate multiple models. In the example below, we use the same stack of layers to instantiate two models: an `encoder` model that turns image inputs into 16-dimensional vectors, and an end-to-end `autoencoder` model for training. """ encoder_input = keras.Input(shape=(28, 28, 1), name='img') x = layers.Conv2D(16, 3, activation='relu')(encoder_input) x = layers.Conv2D(32, 3, activation='relu')(x) x = layers.MaxPooling2D(3)(x) x = layers.Conv2D(32, 3, activation='relu')(x) x = layers.Conv2D(16, 3, activation='relu')(x) encoder_output = layers.GlobalMaxPooling2D()(x) encoder = keras.Model(encoder_input, encoder_output, name='encoder') encoder.summary() x = layers.Reshape((4, 4, 1))(encoder_output) x = layers.Conv2DTranspose(16, 3, activation='relu')(x) x = layers.Conv2DTranspose(32, 3, activation='relu')(x) x = layers.UpSampling2D(3)(x) x = layers.Conv2DTranspose(16, 3, activation='relu')(x) decoder_output = layers.Conv2DTranspose(1, 3, activation='relu')(x) autoencoder = keras.Model(encoder_input, decoder_output, name='autoencoder') autoencoder.summary() """Note that we make the decoding architecture strictly symmetrical to the encoding architecture, so that we get an output shape that is the same as the input shape `(28, 28, 1)`.
def DashNet(input_tensor=None, input_shape=None, pooling='avg', classes=2, classifier_activation='softmax'): if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if backend.image_data_format() == 'channels_first': channel_axis = 1 else: channel_axis = 3 # customize model structure x = conv2d_bn(img_input, 32, 15, 3, strides=(3, 1), padding='valid') x = conv2d_bn(x, 32, 15, 3, padding='same') x = conv2d_bn(x, 64, 15, 3, padding='same') x = layers.MaxPooling2D(pool_size=(15, 3), strides=(5, 1))(x) x = conv2d_bn(x, 80, 1, 1, padding='same') x = conv2d_bn(x, 192, 15, 3, padding='same') x = layers.MaxPooling2D(pool_size=(15, 3), strides=(5, 2))(x) # mixed 0: branch1x1 = conv2d_bn(x, 64, 1, 1) branch5x5 = conv2d_bn(x, 48, 1, 1) branch5x5 = conv2d_bn(branch5x5, 64, 5, 5) branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch_avg_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_avg_pool = conv2d_bn(branch_avg_pool, 32, 1, 1) x = layers.concatenate( [branch1x1, branch5x5, branch3x3dbl, branch_avg_pool], axis=channel_axis, name='mixed0') if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='dashnet') return model
def DenseNet(blocks, include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, **kwargs): """Instantiates the DenseNet architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. # Arguments blocks: numbers of building blocks for the four dense layers. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `'channels_last'` data format) or `(3, 224, 224)` (with `'channels_first'` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input) x = layers.Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x) x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x) x = layers.Activation('relu', name='conv1/relu')(x) x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x) x = layers.MaxPooling2D(3, strides=2, name='pool1')(x) x = dense_block(x, blocks[0], name='conv2') x = transition_block(x, 0.5, name='pool2') x = dense_block(x, blocks[1], name='conv3') x = transition_block(x, 0.5, name='pool3') x = dense_block(x, blocks[2], name='conv4') x = transition_block(x, 0.5, name='pool4') x = dense_block(x, blocks[3], name='conv5') x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x) x = layers.Activation('relu', name='relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) x = layers.Dense(classes, activation='softmax', name='fc1000')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = keras_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. if blocks == [6, 12, 24, 16]: model = models.Model(inputs, x, name='densenet121') else: model = models.Model(inputs, x, name='densenet') # Load weights. if weights == 'imagenet': if include_top or (blocks != [6, 12, 24, 16]): raise ValueError('Only DenseNet121 without top is available' ' pretrained') # NOTE: If your Hub Application has multiple configurations (e.g., # DenseNet {121, 169, 201} x {include_top=True, include_top=False}) # each of these would have their own weights_path/SavedModel. weights_path = 'densenet121_weights_tf_dim_ordering_tf_kernels_notop' # Download the SavedModel and use only the checkpoint (variables). path = resolve(('https://github.com/jharmsen/hub-application/' 'releases/download/v1/{}.tar.gz').format(weights_path)) path = os.path.join(path, 'variables/variables') model.load_weights(path) elif weights is not None: model.load_weights(weights) return model
def ResNet(stack_fn, preact, use_bias, model_name='resnet', include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, layers_fn=None): """Instantiates the ResNet, ResNetV2, and ResNeXt architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. # Arguments stack_fn: a function that returns output tensor for the stacked residual blocks. preact: whether to use pre-activation or not (True for ResNetV2, False for ResNet and ResNeXt). use_bias: whether to use biases for convolutional layers or not (True for ResNet and ResNetV2, False for ResNeXt). model_name: string, model name. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels. pooling: optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input) x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x) if preact is False: x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1_bn')(x) x = layers.Activation('relu', name='conv1_relu')(x) x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x) x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x) x = stack_fn(x) if preact is True: x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='post_bn')(x) x = layers.Activation('relu', name='post_relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) x = layers.Dense(classes, activation='softmax', name='probs')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) if layers_fn != None: x = layers_fn(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = keras.utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name=model_name) # Load weights. if weights is not None: model.load_weights(weights) return model
def ResNet( stack_fn, preact, model_name='resnet', head='one_head', head_mlp='', input_shape=None, pooling=None, activation='relu', bn_sync=BN_SYNC, num_class=1000, **kwargs): """Instantiates the ResNet, ResNetV2, and ResNeXt architecture. Reference paper: - [Deep Residual Learning for Image Recognition] (https://arxiv.org/abs/1512.03385) (CVPR 2015) Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.resnet.preprocess_input` for an example. Arguments: stack_fn: a function that returns output tensor for the stacked residual blocks. preact: whether to use pre-activation or not (True for ResNetV2, False for ResNet and ResNeXt). model_name: string, model name. head: whether to include the fully-connected layer at the top of the network. input_shape: optional shape tuple, only to be specified if `head` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels. pooling: optional pooling mode for feature extraction when `head` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. num_class: optional number of classes to classify images into, only to be specified if `head` is True, and if no `weights` argument is specified. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. """ # Input layer. inputs = img_input = layers.Input(shape=input_shape) # Conv1 block. # CIFAR (32x32) or STL-10 (96x96) use small input; otherwise use large input if input_shape[0] == 256: kernel_size, stride, maxpool = 7, 2, True elif input_shape[0] in [96, 128]: kernel_size, stride, maxpool = 5, 1, True elif input_shape[0] == 32: kernel_size, stride, maxpool = 3, 1, False else: raise NotImplementedError x = convnxn(img_input, filters=64, kernel_size=kernel_size, strides=stride, use_bias=preact, name='conv1_conv') if not preact: x = batchnorm(x, bn_sync=bn_sync, name='conv1_bn') x = nonlinearity(x, layer_activation=activation, name='conv1_'+activation) if maxpool: x = layers.MaxPooling2D(3, strides=2, padding='SAME', name='pool1_pool')(x) # Conv2 to Conv5 blocks x = stack_fn(x) if preact: x = batchnorm(x, bn_sync=bn_sync, name='post_bn') x = nonlinearity(x, layer_activation=activation, name='post_'+activation) # Pooling layer if pooling in ['avg', None]: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # # Dropout layer # x = layers.Dropout(0.5)(x) # print("!! dropout layer") # Classifier and/or embedding head outputs = get_head( x, arch=head, dims=head_mlp, num_class=num_class, bn_sync=bn_sync, classifier_activation='linear') # Create model. if bn_sync: model_name += '_sbn' if not head in ['linear', None, False]: model_name += '_{}'.format(head) if head_mlp is not None and len(head_mlp) > 0: model_name += '_mlp' + '_'.join(['%d'%d for d in head_mlp]) model = training.Model(inputs, outputs, name=model_name) res = model(tf.zeros((1, *input_shape)), training=False) model.dim_feat = tf.reshape(res['embeds'], (-1)).shape[0] return model
model = get_compiled_model() model.fit(train_dataset, epochs=3) """### Passing data to multi-input, multi-output models In the previous examples, we were considering a model with a single input (a tensor of shape `(764,)`) and a single output (a prediction tensor of shape `(10,)`). But what about models that have multiple inputs or outputs? Consider the following model, which has an image input of shape `(32, 32, 3)` (that's `(height, width, channels)`) and a timeseries input of shape `(None, 10)` (that's `(timesteps, features)`). Our model will have two outputs computed from the combination of these inputs: a "score" (of shape `(1,)`) and a probability distribution over 5 classes (of shape `(10,)`). """ image_input = keras.Input(shape=(32, 32, 3), name='img_input') timeseries_input = keras.Input(shape=(None, 10), name='ts_input') x1 = layers.Conv2D(3, 3)(image_input) x1 = layers.GlobalMaxPooling2D()(x1) x2 = layers.Conv1D(3, 3)(timeseries_input) x2 = layers.GlobalMaxPooling1D()(x2) x = layers.concatenate([x1, x2]) score_output = layers.Dense(1, name='score_output')(x) class_output = layers.Dense(5, activation='softmax', name='class_output')(x) model = keras.Model(inputs=[image_input, timeseries_input], outputs=[score_output, class_output]) """Let's plot this model, so you can clearly see what we're doing here (note that the shapes shown in the plot are batch shapes, rather than per-sample shapes).""" keras.utils.plot_model(model, 'multi_input_and_output_model.png', show_shapes=True)
def MobileNetV2(input_shape=None, alpha=1.0, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): """Instantiates the MobileNetV2 architecture. Reference paper: - [MobileNetV2: Inverted Residuals and Linear Bottlenecks] (https://arxiv.org/abs/1801.04381) (CVPR 2018) Optionally loads weights pre-trained on ImageNet. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.mobilenet_v2.preprocess_input` for an example. Arguments: input_shape: Optional shape tuple, to be specified if you would like to use a model with an input image resolution that is not (224, 224, 3). It should have exactly 3 inputs channels (224, 224, 3). You can also omit this option if you would like to infer input_shape from an input_tensor. If you choose to include both input_tensor and input_shape then input_shape will be used if they match, if the shapes do not match then we will throw an error. E.g. `(160, 160, 3)` would be one valid value. alpha: Float between 0 and 1. controls the width of the network. This is known as the width multiplier in the MobileNetV2 paper, but the name is kept for consistency with `applications.MobileNetV1` model in Keras. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. include_top: Boolean, whether to include the fully-connected layer at the top of the network. Defaults to `True`. weights: String, one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: String, optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: Integer, optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape or invalid alpha, rows when weights='imagenet' ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if 'layers' in kwargs: global layers layers = kwargs.pop('layers') if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs,)) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') # Determine proper input shape and default size. # If both input_shape and input_tensor are used, they should match if input_shape is not None and input_tensor is not None: try: is_input_t_tensor = backend.is_keras_tensor(input_tensor) except ValueError: try: is_input_t_tensor = backend.is_keras_tensor( layer_utils.get_source_inputs(input_tensor)) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is not type input_tensor') if is_input_t_tensor: if backend.image_data_format == 'channels_first': if backend.int_shape(input_tensor)[1] != input_shape[1]: raise ValueError('input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: if backend.int_shape(input_tensor)[2] != input_shape[1]: raise ValueError('input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: raise ValueError('input_tensor specified: ', input_tensor, 'is not a keras tensor') # If input_shape is None, infer shape from input_tensor if input_shape is None and input_tensor is not None: try: backend.is_keras_tensor(input_tensor) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is type: ', type(input_tensor), 'which is not a valid type') if input_shape is None and not backend.is_keras_tensor(input_tensor): default_size = 224 elif input_shape is None and backend.is_keras_tensor(input_tensor): if backend.image_data_format() == 'channels_first': rows = backend.int_shape(input_tensor)[2] cols = backend.int_shape(input_tensor)[3] else: rows = backend.int_shape(input_tensor)[1] cols = backend.int_shape(input_tensor)[2] if rows == cols and rows in [96, 128, 160, 192, 224]: default_size = rows else: default_size = 224 # If input_shape is None and no input_tensor elif input_shape is None: default_size = 224 # If input_shape is not None, assume default size else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [96, 128, 160, 192, 224]: default_size = rows else: default_size = 224 input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if weights == 'imagenet': if alpha not in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]: raise ValueError('If imagenet weights are being loaded, ' 'alpha can be one of `0.35`, `0.50`, `0.75`, ' '`1.0`, `1.3` or `1.4` only.') if rows != cols or rows not in [96, 128, 160, 192, 224]: rows = 224 logging.warning('`input_shape` is undefined or non-square, ' 'or `rows` is not in [96, 128, 160, 192, 224].' ' Weights for input shape (224, 224) will be' ' loaded as the default.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1 first_block_filters = _make_divisible(32 * alpha, 8) x = layers.ZeroPadding2D( padding=imagenet_utils.correct_pad(img_input, 3), name='Conv1_pad')(img_input) x = layers.Conv2D( first_block_filters, kernel_size=3, strides=(2, 2), padding='valid', use_bias=False, name='Conv1')( x) x = layers.BatchNormalization( axis=channel_axis, epsilon=1e-3, momentum=0.999, name='bn_Conv1')( x) x = layers.ReLU(6., name='Conv1_relu')(x) x = _inverted_res_block( x, filters=16, alpha=alpha, stride=1, expansion=1, block_id=0) x = _inverted_res_block( x, filters=24, alpha=alpha, stride=2, expansion=6, block_id=1) x = _inverted_res_block( x, filters=24, alpha=alpha, stride=1, expansion=6, block_id=2) x = _inverted_res_block( x, filters=32, alpha=alpha, stride=2, expansion=6, block_id=3) x = _inverted_res_block( x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=4) x = _inverted_res_block( x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=5) x = _inverted_res_block( x, filters=64, alpha=alpha, stride=2, expansion=6, block_id=6) x = _inverted_res_block( x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=7) x = _inverted_res_block( x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=8) x = _inverted_res_block( x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=9) x = _inverted_res_block( x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=10) x = _inverted_res_block( x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=11) x = _inverted_res_block( x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=12) x = _inverted_res_block( x, filters=160, alpha=alpha, stride=2, expansion=6, block_id=13) x = _inverted_res_block( x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=14) x = _inverted_res_block( x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=15) x = _inverted_res_block( x, filters=320, alpha=alpha, stride=1, expansion=6, block_id=16) # no alpha applied to last conv as stated in the paper: # if the width multiplier is greater than 1 we # increase the number of output channels if alpha > 1.0: last_block_filters = _make_divisible(1280 * alpha, 8) else: last_block_filters = 1280 x = layers.Conv2D( last_block_filters, kernel_size=1, use_bias=False, name='Conv_1')( x) x = layers.BatchNormalization( axis=channel_axis, epsilon=1e-3, momentum=0.999, name='Conv_1_bn')( x) x = layers.ReLU(6., name='out_relu')(x) if include_top: x = layers.GlobalAveragePooling2D()(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows)) # Load weights. if weights == 'imagenet': if include_top: model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + str(alpha) + '_' + str(rows) + '.h5') weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file( model_name, weight_path, cache_subdir='models') else: model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + str(alpha) + '_' + str(rows) + '_no_top' + '.h5') weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file( model_name, weight_path, cache_subdir='models') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def InceptionResNetV2(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): """Instantiates the Inception-ResNet v2 architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.inception_resnet_v2.preprocess_input` for an example. Arguments: include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is `False` (otherwise the input shape has to be `(299, 299, 3)` (with `'channels_last'` data format) or `(3, 299, 299)` (with `'channels_first'` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `'avg'` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `'max'` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is `True`, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if 'layers' in kwargs: global layers layers = kwargs.pop('layers') if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs,)) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=299, min_size=75, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Stem block: 35 x 35 x 192 x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid') x = conv2d_bn(x, 32, 3, padding='valid') x = conv2d_bn(x, 64, 3) x = layers.MaxPooling2D(3, strides=2)(x) x = conv2d_bn(x, 80, 1, padding='valid') x = conv2d_bn(x, 192, 3, padding='valid') x = layers.MaxPooling2D(3, strides=2)(x) # Mixed 5b (Inception-A block): 35 x 35 x 320 branch_0 = conv2d_bn(x, 96, 1) branch_1 = conv2d_bn(x, 48, 1) branch_1 = conv2d_bn(branch_1, 64, 5) branch_2 = conv2d_bn(x, 64, 1) branch_2 = conv2d_bn(branch_2, 96, 3) branch_2 = conv2d_bn(branch_2, 96, 3) branch_pool = layers.AveragePooling2D(3, strides=1, padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1) branches = [branch_0, branch_1, branch_2, branch_pool] channel_axis = 1 if backend.image_data_format() == 'channels_first' else 3 x = layers.Concatenate(axis=channel_axis, name='mixed_5b')(branches) # 10x block35 (Inception-ResNet-A block): 35 x 35 x 320 for block_idx in range(1, 11): x = inception_resnet_block( x, scale=0.17, block_type='block35', block_idx=block_idx) # Mixed 6a (Reduction-A block): 17 x 17 x 1088 branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid') branch_1 = conv2d_bn(x, 256, 1) branch_1 = conv2d_bn(branch_1, 256, 3) branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_6a')(branches) # 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088 for block_idx in range(1, 21): x = inception_resnet_block( x, scale=0.1, block_type='block17', block_idx=block_idx) # Mixed 7a (Reduction-B block): 8 x 8 x 2080 branch_0 = conv2d_bn(x, 256, 1) branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid') branch_1 = conv2d_bn(x, 256, 1) branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid') branch_2 = conv2d_bn(x, 256, 1) branch_2 = conv2d_bn(branch_2, 288, 3) branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_2, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_7a')(branches) # 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080 for block_idx in range(1, 10): x = inception_resnet_block( x, scale=0.2, block_type='block8', block_idx=block_idx) x = inception_resnet_block( x, scale=1., activation=None, block_type='block8', block_idx=10) # Final convolution block: 8 x 8 x 1536 x = conv2d_bn(x, 1536, 1, name='conv_7b') if include_top: # Classification block x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='inception_resnet_v2') # Load weights. if weights == 'imagenet': if include_top: fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5' weights_path = data_utils.get_file( fname, BASE_WEIGHT_URL + fname, cache_subdir='models', file_hash='e693bd0210a403b3192acc6073ad2e96') else: fname = ('inception_resnet_v2_weights_' 'tf_dim_ordering_tf_kernels_notop.h5') weights_path = data_utils.get_file( fname, BASE_WEIGHT_URL + fname, cache_subdir='models', file_hash='d19885ff4a710c122648d3b5c3b684e4') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def DenseNet( blocks, include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', ): """Instantiates the DenseNet architecture. Reference paper: - [Densely Connected Convolutional Networks] (https://arxiv.org/abs/1608.06993) (CVPR 2017 Best Paper Award) Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.densenet.preprocess_input` for an example. Arguments: blocks: numbers of building blocks for the four dense layers. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `'channels_last'` data format) or `(3, 224, 224)` (with `'channels_first'` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input) x = layers.Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x) x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x) x = layers.Activation('relu', name='conv1/relu')(x) x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x) x = layers.MaxPooling2D(3, strides=2, name='pool1')(x) x = dense_block(x, blocks[0], name='conv2') x = transition_block(x, 0.5, name='pool2') x = dense_block(x, blocks[1], name='conv3') x = transition_block(x, 0.5, name='pool3') x = dense_block(x, blocks[2], name='conv4') x = transition_block(x, 0.5, name='pool4') x = dense_block(x, blocks[3], name='conv5') x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x) x = layers.Activation('relu', name='relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. if blocks == [6, 12, 24, 16]: model = training.Model(inputs, x, name='densenet121') elif blocks == [6, 12, 32, 32]: model = training.Model(inputs, x, name='densenet169') elif blocks == [6, 12, 48, 32]: model = training.Model(inputs, x, name='densenet201') else: model = training.Model(inputs, x, name='densenet') # Load weights. if weights == 'imagenet': if include_top: if blocks == [6, 12, 24, 16]: weights_path = data_utils.get_file( 'densenet121_weights_tf_dim_ordering_tf_kernels.h5', DENSENET121_WEIGHT_PATH, cache_subdir='models', file_hash='9d60b8095a5708f2dcce2bca79d332c7') elif blocks == [6, 12, 32, 32]: weights_path = data_utils.get_file( 'densenet169_weights_tf_dim_ordering_tf_kernels.h5', DENSENET169_WEIGHT_PATH, cache_subdir='models', file_hash='d699b8f76981ab1b30698df4c175e90b') elif blocks == [6, 12, 48, 32]: weights_path = data_utils.get_file( 'densenet201_weights_tf_dim_ordering_tf_kernels.h5', DENSENET201_WEIGHT_PATH, cache_subdir='models', file_hash='1ceb130c1ea1b78c3bf6114dbdfd8807') else: if blocks == [6, 12, 24, 16]: weights_path = data_utils.get_file( 'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5', DENSENET121_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='30ee3e1110167f948a6b9946edeeb738') elif blocks == [6, 12, 32, 32]: weights_path = data_utils.get_file( 'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5', DENSENET169_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='b8c4d4c20dd625c148057b9ff1c1176b') elif blocks == [6, 12, 48, 32]: weights_path = data_utils.get_file( 'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5', DENSENET201_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='c13680b51ded0fb44dff2d8f86ac8bb1') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def MobileNet(input_shape=None, alpha=1.0, depth_multiplier=1, dropout=1e-3, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000, **kwargs): """Instantiates the MobileNet architecture. Arguments: input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or (3, 224, 224) (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. alpha: controls the width of the network. This is known as the width multiplier in the MobileNet paper. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. depth_multiplier: depth multiplier for depthwise convolution. This is called the resolution multiplier in the MobileNet paper. dropout: dropout rate include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. **kwargs: For backwards compatibility only. Returns: A Keras model instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if 'layers' in kwargs: global layers layers = kwargs.pop('layers') if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') # Determine proper input shape and default size. if input_shape is None: default_size = 224 else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [128, 160, 192, 224]: default_size = rows else: default_size = 224 input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if weights == 'imagenet': if depth_multiplier != 1: raise ValueError('If imagenet weights are being loaded, ' 'depth multiplier must be 1') if alpha not in [0.25, 0.50, 0.75, 1.0]: raise ValueError('If imagenet weights are being loaded, ' 'alpha can be one of' '`0.25`, `0.50`, `0.75` or `1.0` only.') if rows != cols or rows not in [128, 160, 192, 224]: rows = 224 logging.warning('`input_shape` is undefined or non-square, ' 'or `rows` is not in [128, 160, 192, 224]. ' 'Weights for input shape (224, 224) will be' ' loaded as the default.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = _conv_block(img_input, 32, alpha, strides=(2, 2)) x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1) x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, strides=(2, 2), block_id=2) x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3) x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, strides=(2, 2), block_id=4) x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, strides=(2, 2), block_id=6) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11) x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, strides=(2, 2), block_id=12) x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13) if include_top: if backend.image_data_format() == 'channels_first': shape = (int(1024 * alpha), 1, 1) else: shape = (1, 1, int(1024 * alpha)) x = layers.GlobalAveragePooling2D()(x) x = layers.Reshape(shape, name='reshape_1')(x) x = layers.Dropout(dropout, name='dropout')(x) x = layers.Conv2D(classes, (1, 1), padding='same', name='conv_preds')(x) x = layers.Reshape((classes, ), name='reshape_2')(x) x = layers.Activation('softmax', name='act_softmax')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='mobilenet_%0.2f_%s' % (alpha, rows)) # Load weights. if weights == 'imagenet': if alpha == 1.0: alpha_text = '1_0' elif alpha == 0.75: alpha_text = '7_5' elif alpha == 0.50: alpha_text = '5_0' else: alpha_text = '2_5' if include_top: model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows) weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file(model_name, weight_path, cache_subdir='models') else: model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows) weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file(model_name, weight_path, cache_subdir='models') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def ResNet50Plus(include_top=False, input_tensor=None, input_shape=(192, 192, 3), alpha=1.0, pooling='cov', classes=8, **kwargs): """ Adaption of ResNet50 that uses ELU instead of ReLU and uses less batch normalization layers. """ if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if K.image_data_format() == 'channels_last': bn_axis = 3 else: bn_axis = 1 x = layers.ZeroPadding2D(padding=(3, 3), name='conv1_pad')(img_input) x = layers.Conv2D(64, (7, 7), strides=(2, 2), padding='valid', kernel_initializer='he_normal', name='conv1')(x) x = layers.BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = layers.ELU(alpha=alpha)(x) x = layers.ZeroPadding2D(padding=(1, 1), name='pool1_pad')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', alpha=alpha, strides=(1, 1)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', alpha=alpha) x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', alpha=alpha) x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', alpha=alpha) x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', alpha=alpha) x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', alpha=alpha) x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', alpha=alpha) x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', alpha=alpha) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b', alpha=alpha) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c', alpha=alpha) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d', alpha=alpha) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e', alpha=alpha) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f', alpha=alpha) x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', alpha=alpha) x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', alpha=alpha) x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', alpha=alpha) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) x = layers.Dense(classes, activation='softmax', name='fc1000')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) elif pooling == 'cov': # Reduce number of channels before applying covariance pooling # num_channels = int(np.ceil(np.max(np.roots([1, 1, -2*classes])))) x = layers.Conv2D(classes, (1, 1), padding='valid', kernel_initializer='he_normal', name='reduce_channels')(x) x = GlobalCovPooling2D(num_iter=5)(x) x = layers.Dense(classes, activation='softmax', name='fc{}'.format(classes))(x) else: warnings.warn('The output shape of `ResNet50(include_top=False)` ' 'has been changed since Keras 2.2.0.') # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='resnet50plus') return model
def SmallResNet(stack_fn, preact, use_bias, model_name='resnet', include_top=True, input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.Conv2D(64, 3, padding='same', use_bias=use_bias, name='conv1_conv')(img_input) if not preact: x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1_bn')(x) x = layers.Activation('relu', name='conv1_relu')(x) x = stack_fn(x) if preact: x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='post_bn')(x) x = layers.Activation('relu', name='post_relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name=model_name) return model
def InceptionV3( include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', ): """Instantiates the Inception v3 architecture. Reference paper: - [Rethinking the Inception Architecture for Computer Vision]( http://arxiv.org/abs/1512.00567) (CVPR 2016) Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in the `tf.keras.backend.image_data_format()`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.inception_v3.preprocess_input` for an example. Arguments: include_top: Boolean, whether to include the fully-connected layer at the top, as the last layer of the network. Default to `True`. weights: One of `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded. Default to `imagenet`. input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. `input_tensor` is useful for sharing inputs between multiple different networks. Default to None. input_shape: Optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(299, 299, 3)` (with `channels_last` data format) or `(3, 299, 299)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g. `(150, 150, 3)` would be one valid value. `input_shape` will be ignored if the `input_tensor` is provided. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` (default) means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Default to 1000. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=299, min_size=75, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if backend.image_data_format() == 'channels_first': channel_axis = 1 else: channel_axis = 3 x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid') x = conv2d_bn(x, 32, 3, 3, padding='valid') x = conv2d_bn(x, 64, 3, 3) x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv2d_bn(x, 80, 1, 1, padding='valid') x = conv2d_bn(x, 192, 3, 3, padding='valid') x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) # mixed 0: 35 x 35 x 256 branch1x1 = conv2d_bn(x, 64, 1, 1) branch5x5 = conv2d_bn(x, 48, 1, 1) branch5x5 = conv2d_bn(branch5x5, 64, 5, 5) branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 32, 1, 1) x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed0') # mixed 1: 35 x 35 x 288 branch1x1 = conv2d_bn(x, 64, 1, 1) branch5x5 = conv2d_bn(x, 48, 1, 1) branch5x5 = conv2d_bn(branch5x5, 64, 5, 5) branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1, 1) x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed1') # mixed 2: 35 x 35 x 288 branch1x1 = conv2d_bn(x, 64, 1, 1) branch5x5 = conv2d_bn(x, 48, 1, 1) branch5x5 = conv2d_bn(branch5x5, 64, 5, 5) branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1, 1) x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed2') # mixed 3: 17 x 17 x 768 branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid') branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid') branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) x = layers.concatenate([branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3') # mixed 4: 17 x 17 x 768 branch1x1 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(x, 128, 1, 1) branch7x7 = conv2d_bn(branch7x7, 128, 1, 7) branch7x7 = conv2d_bn(branch7x7, 192, 7, 1) branch7x7dbl = conv2d_bn(x, 128, 1, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7) branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool], axis=channel_axis, name='mixed4') # mixed 5, 6: 17 x 17 x 768 for i in range(2): branch1x1 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(x, 160, 1, 1) branch7x7 = conv2d_bn(branch7x7, 160, 1, 7) branch7x7 = conv2d_bn(branch7x7, 192, 7, 1) branch7x7dbl = conv2d_bn(x, 160, 1, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7) branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate( [branch1x1, branch7x7, branch7x7dbl, branch_pool], axis=channel_axis, name='mixed' + str(5 + i)) # mixed 7: 17 x 17 x 768 branch1x1 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(branch7x7, 192, 1, 7) branch7x7 = conv2d_bn(branch7x7, 192, 7, 1) branch7x7dbl = conv2d_bn(x, 192, 1, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool], axis=channel_axis, name='mixed7') # mixed 8: 8 x 8 x 1280 branch3x3 = conv2d_bn(x, 192, 1, 1) branch3x3 = conv2d_bn(branch3x3, 320, 3, 3, strides=(2, 2), padding='valid') branch7x7x3 = conv2d_bn(x, 192, 1, 1) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid') branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) x = layers.concatenate([branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8') # mixed 9: 8 x 8 x 2048 for i in range(2): branch1x1 = conv2d_bn(x, 320, 1, 1) branch3x3 = conv2d_bn(x, 384, 1, 1) branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3) branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1) branch3x3 = layers.concatenate([branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i)) branch3x3dbl = conv2d_bn(x, 448, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3) branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3) branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1) branch3x3dbl = layers.concatenate([branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate( [branch1x1, branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed' + str(9 + i)) if include_top: # Classification block x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='inception_v3') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'inception_v3_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', file_hash='9a0d58056eeedaa3f26cb7ebd46da564') else: weights_path = data_utils.get_file( 'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='bcbd6486424b2319ff4ef7d526e38f63') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def MobileNetV2(input_shape=None, alpha=1.0, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000, **kwargs): """Instantiates the MobileNetV2 architecture. # Arguments input_shape: optional shape tuple, to be specified if you would like to use a model with an input img resolution that is not (224, 224, 3). It should have exactly 3 inputs channels (224, 224, 3). You can also omit this option if you would like to infer input_shape from an input_tensor. If you choose to include both input_tensor and input_shape then input_shape will be used if they match, if the shapes do not match then we will throw an error. E.g. `(160, 160, 3)` would be one valid value. alpha: controls the width of the network. This is known as the width multiplier in the MobileNetV2 paper, but the name is kept for consistency with MobileNetV1 in Keras. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape or invalid alpha, rows when weights='imagenet' """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') # Determine proper input shape and default size. # If both input_shape and input_tensor are used, they should match if input_shape is not None and input_tensor is not None: try: is_input_t_tensor = backend.is_keras_tensor(input_tensor) except ValueError: try: is_input_t_tensor = backend.is_keras_tensor( keras_utils.get_source_inputs(input_tensor)) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is not type input_tensor') if is_input_t_tensor: if backend.image_data_format == 'channels_first': if backend.int_shape(input_tensor)[1] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: if backend.int_shape(input_tensor)[2] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: raise ValueError('input_tensor specified: ', input_tensor, 'is not a keras tensor') # If input_shape is None, infer shape from input_tensor if input_shape is None and input_tensor is not None: try: backend.is_keras_tensor(input_tensor) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is type: ', type(input_tensor), 'which is not a valid type') if input_shape is None and not backend.is_keras_tensor(input_tensor): default_size = 224 elif input_shape is None and backend.is_keras_tensor(input_tensor): if backend.image_data_format() == 'channels_first': rows = backend.int_shape(input_tensor)[2] cols = backend.int_shape(input_tensor)[3] else: rows = backend.int_shape(input_tensor)[1] cols = backend.int_shape(input_tensor)[2] if rows == cols and rows in [96, 128, 160, 192, 224]: default_size = rows else: default_size = 224 # If input_shape is None and no input_tensor elif input_shape is None: default_size = 224 # If input_shape is not None, assume default size else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [96, 128, 160, 192, 224]: default_size = rows else: default_size = 224 input_shape = _obtain_input_shape(input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if weights == 'imagenet': if alpha not in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]: raise ValueError('If imagenet weights are being loaded, ' 'alpha can be one of `0.35`, `0.50`, `0.75`, ' '`1.0`, `1.3` or `1.4` only.') if rows != cols or rows not in [96, 128, 160, 192, 224]: rows = 224 warnings.warn('MobileNet shape is undefined.' ' Weights for input shape' '(224, 224) will be loaded.') if backend.image_data_format() != 'channels_last': warnings.warn('The MobileNet family of models is only available ' 'for the input data format "channels_last" ' '(width, height, channels). ' 'However your settings specify the default ' 'data format "channels_first" (channels, width, height).' ' You should set `image_data_format="channels_last"` ' 'in your Keras config located at ~/.keras/keras.json. ' 'The model being returned right now will expect inputs ' 'to follow the "channels_last" data format.') backend.set_image_data_format('channels_last') old_data_format = 'channels_first' else: old_data_format = None if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor first_block_filters = _make_divisible(32 * alpha, 8) x = layers.ZeroPadding2D(padding=correct_pad(backend, img_input, 3), name='Conv1_pad')(img_input) x = layers.Conv2D(first_block_filters, kernel_size=3, strides=(2, 2), padding='valid', use_bias=False, name='Conv1')(x) x = layers.BatchNormalization(epsilon=1e-3, momentum=0.999, name='bn_Conv1')(x) x = layers.ReLU(6., name='Conv1_relu')(x) x = _inverted_res_block(x, filters=16, alpha=alpha, stride=1, expansion=1, block_id=0) x = _inverted_res_block(x, filters=24, alpha=alpha, stride=2, expansion=6, block_id=1) x = _inverted_res_block(x, filters=24, alpha=alpha, stride=1, expansion=6, block_id=2) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=2, expansion=6, block_id=3) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=4) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=5) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=2, expansion=6, block_id=6) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=7) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=8) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=9) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=10) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=11) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=12) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=2, expansion=6, block_id=13) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=14) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=15) x = _inverted_res_block(x, filters=320, alpha=alpha, stride=1, expansion=6, block_id=16) # no alpha applied to last conv as stated in the paper: # if the width multiplier is greater than 1 we # increase the number of output channels if alpha > 1.0: last_block_filters = _make_divisible(1280 * alpha, 8) else: last_block_filters = 1280 x = layers.Conv2D(last_block_filters, kernel_size=1, use_bias=False, name='Conv_1')(x) x = layers.BatchNormalization(epsilon=1e-3, momentum=0.999, name='Conv_1_bn')(x) x = layers.ReLU(6., name='out_relu')(x) if include_top: x = layers.GlobalAveragePooling2D()(x) x = layers.Dense(classes, activation='softmax', use_bias=True, name='Logits')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = keras_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows)) # Load weights. if weights == 'imagenet': if backend.image_data_format() == 'channels_first': raise ValueError('Weights for "channels_first" format ' 'are not available.') if include_top: model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + str(alpha) + '_' + str(rows) + '.h5') weigh_path = BASE_WEIGHT_PATH + model_name weights_path = keras_utils.get_file(model_name, weigh_path, cache_subdir='models') else: model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + str(alpha) + '_' + str(rows) + '_no_top' + '.h5') weigh_path = BASE_WEIGHT_PATH + model_name weights_path = keras_utils.get_file(model_name, weigh_path, cache_subdir='models') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) if old_data_format: backend.set_image_data_format(old_data_format) return model
def AlexNet(include_top=True, input_tensor=None, input_shape=None, pooling=None, classes=1000): """ Instantiates the AlexNet architecture. Args: include_top: whether to include the 3 fully-connected layers at the top of the network. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 input channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Returns: A Keras model instance. """ if classes == 1000: raise ValueError('If use dataset is `imagenet`, please use it,' 'otherwise please use classifier images classes.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = layers.Conv2D(96, (11, 11), strides=4, activation=tf.nn.relu, padding='same', name='conv1')(img_input) x = layers.MaxPool2D((2, 2), strides=(2, 2), name='max_pool1')(x) x = layers.Conv2D(256, (5, 5), strides=1, activation=tf.nn.relu, padding='same', name='conv2')(x) x = layers.MaxPool2D((3, 3), strides=(2, 2), name='max_pool2')(x) x = layers.Conv2D(384, (3, 3), strides=1, activation=tf.nn.relu, padding='same', name='conv3')(x) x = layers.Conv2D(384, (3, 3), strides=1, activation=tf.nn.relu, padding='same', name='conv4')(x) x = layers.Conv2D(256, (3, 3), strides=1, activation=tf.nn.relu, padding='same', )(x) x = layers.MaxPool2D((3, 3), strides=(2, 2), name='max_pool3')(x) x = layers.AvgPool2D((6, 6), strides=(6, 6), name='avg_pool1')(x) if include_top: # Classification block x = layers.Flatten(name='flatten')(x) x = layers.Dropout(0.3, name='drop1')(x) x = layers.Dense(4096, activation=tf.nn.relu, name='fc1')(x) x = layers.Dropout(0.3, name='drop2')(x) x = layers.Dense(4096, activation=tf.nn.relu, name='fc2')(x) x = layers.Dense(classes, activation=tf.nn.softmax, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name='AlexNet') return model
def EfficientNet(input_shape, block_args_list, global_params, include_top=True, pooling=None): batch_norm_momentum = global_params.batch_norm_momentum batch_norm_epsilon = global_params.batch_norm_epsilon if global_params.data_format == 'channels_first': channel_axis = 1 else: channel_axis = -1 # Stem part inputs = KL.Input(shape=input_shape) x = inputs x = KL.Conv2D( filters=round_filters(32, global_params), kernel_size=[3, 3], strides=[2, 2], kernel_initializer=ConvKernalInitializer(), padding='same', use_bias=False )(x) x = KL.BatchNormalization( axis=channel_axis, momentum=batch_norm_momentum, epsilon=batch_norm_epsilon )(x) x = Swish()(x) # Blocks part block_idx = 1 n_blocks = sum([block_args.num_repeat for block_args in block_args_list]) drop_rate = global_params.drop_connect_rate or 0 drop_rate_dx = drop_rate / n_blocks for block_args in block_args_list: assert block_args.num_repeat > 0 # Update block input and output filters based on depth multiplier. block_args = block_args._replace( input_filters=round_filters(block_args.input_filters, global_params), output_filters=round_filters(block_args.output_filters, global_params), num_repeat=round_repeats(block_args.num_repeat, global_params) ) # The first block needs to take care of stride and filter size increase. x = MBConvBlock(block_args, global_params, drop_connect_rate=drop_rate_dx * block_idx)(x) block_idx += 1 if block_args.num_repeat > 1: block_args = block_args._replace(input_filters=block_args.output_filters, strides=[1, 1]) for _ in xrange(block_args.num_repeat - 1): x = MBConvBlock(block_args, global_params, drop_connect_rate=drop_rate_dx * block_idx)(x) block_idx += 1 # Head part x = KL.Conv2D( filters=round_filters(1280, global_params), kernel_size=[1, 1], strides=[1, 1], kernel_initializer=ConvKernalInitializer(), padding='same', use_bias=False )(x) x = KL.BatchNormalization( axis=channel_axis, momentum=batch_norm_momentum, epsilon=batch_norm_epsilon )(x) x = Swish()(x) if include_top: x = KL.GlobalAveragePooling2D(data_format=global_params.data_format)(x) if global_params.dropout_rate > 0: x = KL.Dropout(global_params.dropout_rate)(x) x = KL.Dense(global_params.num_classes, kernel_initializer=DenseKernalInitializer())(x) x = KL.Activation('softmax')(x) else: if pooling == 'avg': x = KL.GlobalAveragePooling2D(data_format=global_params.data_format)(x) elif pooling == 'max': x = KL.GlobalMaxPooling2D(data_format=global_params.data_format)(x) outputs = x model = KM.Model(inputs, outputs) return model
def ResNet(stack_fn, preact, use_bias, model_name='resnet', include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): """Instantiates the ResNet, ResNetV2, and ResNeXt architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.resnet.preprocess_input` for an example. Arguments: stack_fn: a function that returns output tensor for the stacked residual blocks. preact: whether to use pre-activation or not (True for ResNetV2, False for ResNet and ResNeXt). use_bias: whether to use biases for convolutional layers or not (True for ResNet and ResNetV2, False for ResNeXt). model_name: string, model name. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels. pooling: optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if 'layers' in kwargs: global layers layers = kwargs.pop('layers') if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input) x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x) if not preact: x = tf.keras.layers.experimental.SyncBatchNormalization( axis=bn_axis, name='conv1_bn')(x) x = layers.Activation('relu', name='conv1_relu')(x) x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x) x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x) x = stack_fn(x) if preact: x = tf.keras.layers.experimental.SyncBatchNormalization( axis=bn_axis, name='post_bn')(x) x = layers.Activation('relu', name='post_relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name=model_name) # Load weights. if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES): if include_top: file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5' file_hash = WEIGHTS_HASHES[model_name][0] else: file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5' file_hash = WEIGHTS_HASHES[model_name][1] weights_path = data_utils.get_file(file_name, BASE_WEIGHTS_PATH + file_name, cache_subdir='models', file_hash=file_hash) model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def ResNet50(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, **kwargs): """Instantiates the ResNet50 architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. # Arguments include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ # global backend, layers, models, keras_utils # backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) with tf.name_scope("input_layer") as scope: if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if backend.image_data_format() == 'channels_last': bn_axis = 3 else: bn_axis = 1 with tf.name_scope("resnet") as scope: x = layers.ZeroPadding2D(padding=(3, 3), name='conv1_pad')(img_input) x = layers.Conv2D(64, (7, 7), strides=(2, 2), padding='valid', kernel_initializer='he_normal', name='conv1')(x) x = layers.BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = layers.Activation('relu')(x) x = layers.ZeroPadding2D(padding=(1, 1), name='pool1_pad')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) with tf.name_scope("module_0") as scope: x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b') x = identity_block(x, 3, [64, 64, 256], stage=2, block='c') with tf.name_scope("module_1") as scope: x = conv_block(x, 3, [128, 128, 512], stage=3, block='a') x = identity_block(x, 3, [128, 128, 512], stage=3, block='b') x = identity_block(x, 3, [128, 128, 512], stage=3, block='c') x = identity_block(x, 3, [128, 128, 512], stage=3, block='d') with tf.name_scope("module_2") as scope: x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f') with tf.name_scope("module_3") as scope: x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c') with tf.name_scope("top_layer") as scope: if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) x = layers.Dense(classes, activation='softmax', name='fc1000')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) else: warnings.warn( 'The output shape of `ResNet50(include_top=False)` ' 'has been changed since Keras 2.2.0.') with tf.name_scope("input_layer") as scope: # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = keras_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name='resnet50') # Load weights. # if weights == 'imagenet': # if include_top: # weights_path = keras_utils.get_file( # 'resnet50_weights_tf_dim_ordering_tf_kernels.h5', # WEIGHTS_PATH, # cache_subdir='models', # md5_hash='a7b3fe01876f51b976af0dea6bc144eb') # else: # weights_path = keras_utils.get_file( # 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5', # WEIGHTS_PATH_NO_TOP, # cache_subdir='models', # md5_hash='a268eb855778b3df3c7506639542a6af') # model.load_weights(weights_path) # if backend.backend() == 'theano': # keras_utils.convert_all_kernels_in_model(model) # elif weights is not None: # model.load_weights(weights) return model