def make_encoder_model(input_tensor=None, input_shape=(noise_dim, )): """ Create a build model Args: input_tensor: It's going to be tensor, which is going to be the array input_shape: Noise data that conforms to normal distribution Returns: tf.keras.Model """ 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(32, (3, 3), strides=(2, 2), activation=tf.nn.relu, padding="SAME", name="conv1")(img_input) x = layers.Conv2D(64, (3, 3), strides=(2, 2), activation=tf.nn.relu, padding="SAME", name="conv2")(x) x = layers.Flatten(name="flat")(x) x = layers.Dense(units=noise_dim, name="den1")(x) if input_tensor is not None: inputs = utils.get_source_inputs(input_tensor) else: inputs = img_input model = models.Model(inputs, x, name='Encoder_model') return model
def make_generator_model(input_tensor=None, input_shape=(noise_dim,)): """ Returns: tf.keras.Model """ 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.Dense(7 * 7 * 256, activation=tf.nn.leaky_relu, use_bias=False, name='fc1')(img_input) x = layers.BatchNormalization(name='bn1')(x) x = layers.Reshape(target_shape=(7, 7, 256), name='reshape1')(x) x = layers.Conv2DTranspose(128, (5, 5), strides=(1, 1), activation=tf.nn.leaky_relu, padding='same', use_bias=False, name='deconv1')(x) x = layers.BatchNormalization(name='bn2')(x) x = layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), activation=tf.nn.leaky_relu, padding='same', use_bias=False, name='deconv2')(x) x = layers.BatchNormalization(name='bn3')(x) x = layers.Conv2DTranspose(1, (5, 5), strides=(2, 2), activation=tf.nn.tanh, padding='same', use_bias=False, name='deconv3')(x) if input_tensor is not None: inputs = utils.get_source_inputs(input_tensor) else: inputs = img_input model = models.Model(inputs, x, name='Generator_model') return model
def make_discriminator_model(input_tensor=None, input_shape=(28, 28, 1)): """ Returns: tf.keras.Model """ 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(64, (5, 5), strides=(2, 2), activation=tf.nn.leaky_relu, padding='same', name='conv1')(img_input) x = layers.Dropout(0.3, name='drop1')(x) x = layers.Conv2D(32, (5, 5), strides=(2, 2), activation=tf.nn.leaky_relu, padding='same', name='conv2')(x) x = layers.Dropout(0.3, name='drop2')(x) x = layers.Flatten(name='flatten')(x) x = layers.Dense(units=1, name='fc1')(x) if input_tensor is not None: inputs = utils.get_source_inputs(input_tensor) else: inputs = img_input model = models.Model(inputs, x, name='Discriminator_model') img = layers.Input(shape=img_shape) # Extract feature representation features = model(img) # Determine validity and label of the image validity = layers.Dense(1, activation=tf.nn.sigmoid)(features) label = layers.Dense(num_classes, activation=tf.nn.softmax)(features) model = models.Model(img, [validity, label]) return model
def featurenet_backbone(input_tensor=None, input_shape=None, weights=None, include_top=False, pooling=None, n_filters=32, n_dense=128, n_classes=3): """Construct the deepcell backbone with five convolutional units Args: input_tensor (tensor): Input tensor to specify input size n_filters (int, optional): Defaults to 32. Number of filters for convolutional layers Returns: (backbone_names, backbone_features): List of backbone layers, list of backbone names """ if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Build out backbone c1 = featurenet_block(img_input, n_filters) # 1/2 64x64 c2 = featurenet_block(c1, n_filters) # 1/4 32x32 c3 = featurenet_block(c2, n_filters) # 1/8 16x16 c4 = featurenet_block(c3, n_filters) # 1/16 8x8 c5 = featurenet_block(c4, n_filters) # 1/32 4x4 backbone_features = [c1, c2, c3, c4, c5] backbone_names = ['C1', 'C2', 'C3', 'C4', 'C5'] output_dict = {} for name, feature in zip(backbone_names, backbone_features): output_dict[name] = feature if input_tensor is not None: inputs = keras_utils.get_source_inputs(input_tensor) else: inputs = img_input model = Model(inputs=inputs, outputs=backbone_features) return model, output_dict
def make_decoder_model(input_tensor=None, input_shape=(28, 28, 1)): """ Create a decoder model Args: input_tensor: It's going to be tensor, which is going to be the array input_shape: image tensor size. Returns: tf.keras.Model """ 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.Dense(7 * 7 * 64, activation=tf.nn.relu, name="den1")(img_input) x = layers.Reshape(target_shape=(7, 7, 64), name="reshape1")(x) x = layers.Conv2DTranspose(64, (3, 3), strides=(2, 2), padding="SAME", activation=tf.nn.relu, name="convt1")(x), x = layers.Conv2DTranspose(32, (3, 3), strides=(2, 2), padding="SAME", activation=tf.nn.relu, name="convt2")(x), x = layers.Conv2DTranspose(1, (3, 3), strides=(1, 1), padding="SAME", activation=tf.nn.sigmoid, name="convt3")(x), if input_tensor is not None: inputs = utils.get_source_inputs(input_tensor) else: inputs = img_input model = models.Model(inputs, x, name='Decoder_model') return model
def make_discriminator_model(input_tensor=None, input_shape=(32, 32, 3)): """ Returns: tf.keras.Model """ 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(64, (5, 5), strides=(2, 2), activation=tf.nn.leaky_relu, padding='same', name='conv1')(img_input) x = layers.Dropout(0.3, name='drop1')(x) x = layers.Conv2D(32, (5, 5), strides=(2, 2), activation=tf.nn.leaky_relu, padding='same', name='conv2')(x) x = layers.Dropout(0.3, name='drop2')(x) x = layers.Flatten(name='flatten')(x) x = layers.Dense(units=1, name='fc1')(x) if input_tensor is not None: inputs = utils.get_source_inputs(input_tensor) else: inputs = img_input model = models.Model(inputs, x, name='Discriminator_model') return model
def SEDenseNet(input_shape=None, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1, nb_layers_per_block=-1, bottleneck=False, reduction=0.0, dropout_rate=0.0, weight_decay=1e-4, subsample_initial_block=False, include_top=True, weights=None, input_tensor=None, classes=10, activation='softmax'): """Instantiate the SE DenseNet architecture # Arguments input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(32, 32, 3)` (with `channels_last` dim ordering) or `(3, 32, 32)` (with `channels_first` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. E.g. `(200, 200, 3)` would be one valid value. depth: number or layers in the DenseNet nb_dense_block: number of dense blocks to add to end (generally = 3) growth_rate: number of filters to add per dense block nb_filter: initial number of filters. -1 indicates initial number of filters is 2 * growth_rate nb_layers_per_block: number of layers in each dense block. Can be a -1, positive integer or a list. If -1, calculates nb_layer_per_block from the network depth. If positive integer, a set number of layers per dense block. If list, nb_layer is used as provided. Note that list size must be (nb_dense_block + 1) bottleneck: flag to add bottleneck blocks in between dense blocks reduction: reduction factor of transition blocks. Note : reduction value is inverted to compute compression. dropout_rate: dropout rate weight_decay: weight decay rate subsample_initial_block: Set to True to subsample the initial convolution and add a MaxPool2D before the dense blocks are added. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or 'imagenet' (pre-training on ImageNet).. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the weights. 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. activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'. Note that if sigmoid is used, classes must be 1. # Returns A Keras weights instance. """ if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `cifar10` ' '(pre-training on CIFAR-10).') 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 activation not in ['softmax', 'sigmoid']: raise ValueError('activation must be one of "softmax" or "sigmoid"') if activation == 'sigmoid' and classes != 1: raise ValueError('sigmoid activation can only be used when classes = 1') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = __create_dense_net(classes, img_input, include_top, depth, nb_dense_block, growth_rate, nb_filter, nb_layers_per_block, bottleneck, reduction, dropout_rate, weight_decay, subsample_initial_block, activation) # Ensure that the weights 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 weights. model = Model(inputs, x, name='se-densenet') return model
def VGG16_Places365(include_top=True, weights='places', input_tensor=None, input_shape=None, pooling=None, classes=365): """Instantiates the VGG16-places365 architecture. Optionally loads weights pre-trained on Places. Note that when using TensorFlow, for best performance you should set `image_data_format="channels_last"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The data format convention used by the model is the one specified in your Keras config file. # Arguments include_top: whether to include the 3 fully-connected layers at the top of the network. weights: one of `None` (random initialization), 'places' (pre-training on Places), 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, 244)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 48. 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 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 not (weights in {'places', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `places` ' '(pre-training on Places), ' 'or the path to the weights file to be loaded.') if weights == 'places' and include_top and classes != 365: raise ValueError('If using `weights` as places with `include_top`' ' as true, `classes` should be 365') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=48, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = Conv2D(filters=64, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block1_conv1')(img_input) x = Conv2D(filters=64, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block1_conv2')(x) x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block1_pool", padding='valid')(x) # Block 2 x = Conv2D(filters=128, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block2_conv1')(x) x = Conv2D(filters=128, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block2_conv2')(x) x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block2_pool", padding='valid')(x) # Block 3 x = Conv2D(filters=256, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block3_conv1')(x) x = Conv2D(filters=256, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block3_conv2')(x) x = Conv2D(filters=256, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block3_conv3')(x) x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block3_pool", padding='valid')(x) # Block 4 x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block4_conv1')(x) x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block4_conv2')(x) x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block4_conv3')(x) x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block4_pool", padding='valid')(x) # Block 5 x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block5_conv1')(x) x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block5_conv2')(x) x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same', kernel_regularizer=l2(0.0002), activation='relu', name='block5_conv3')(x) x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block5_pool", padding='valid')(x) if include_top: # Classification block x = Flatten(name='flatten')(x) x = Dense(4096, activation='relu', name='fc1')(x) x = Dropout(0.5, name='drop_fc1')(x) x = Dense(4096, activation='relu', name='fc2')(x) x = Dropout(0.5, name='drop_fc2')(x) x = Dense(365, activation='softmax', name="predictions")(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = 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='vgg16-places365') # load weights if weights == 'places': if include_top: weights_path = get_file( 'vgg16-places365_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'vgg16-places365_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'theano': layer_utils.convert_all_kernels_in_model(model) if K.image_data_format() == 'channels_first': if include_top: maxpool = model.get_layer(name='block5_pool') shape = maxpool.output_shape[1:] dense = model.get_layer(name='fc1') layer_utils.convert_dense_weights_data_format( dense, shape, 'channels_first') if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image data format convention ' '(`image_data_format="channels_first"`). ' 'For best performance, set ' '`image_data_format="channels_last"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') elif weights is not None: model.load_weights(weights) return model
def bn_feature_net_2D(receptive_field=61, input_shape=(256, 256, 1), inputs=None, n_features=3, n_channels=1, reg=1e-5, n_conv_filters=64, n_dense_filters=200, VGG_mode=False, init='he_normal', norm_method='std', location=False, dilated=False, padding=False, padding_mode='reflect', multires=False, include_top=True): """Creates a 2D featurenet. Args: receptive_field (int): the receptive field of the neural network. input_shape (tuple): If no input tensor, create one with this shape. inputs (tensor): optional input tensor n_features (int): Number of output features n_channels (int): number of input channels reg (int): regularization value n_conv_filters (int): number of convolutional filters n_dense_filters (int): number of dense filters VGG_mode (bool): If multires, uses VGG_mode for multiresolution init (str): Method for initalizing weights. norm_method (str): ImageNormalization mode to use location (bool): Whether to include location data dilated (bool): Whether to use dilated pooling. padding (bool): Whether to use padding. padding_mode (str): Type of padding, one of 'reflect' or 'zero' multires (bool): Enables multi-resolution mode include_top (bool): Whether to include the final layer of the model Returns: tensorflow.keras.Model: 2D FeatureNet """ # Create layers list (x) to store all of the layers. # We need to use the functional API to enable the multiresolution mode x = [] win = (receptive_field - 1) // 2 if dilated: padding = True if K.image_data_format() == 'channels_first': channel_axis = 1 row_axis = 2 col_axis = 3 if not dilated: input_shape = (n_channels, receptive_field, receptive_field) else: row_axis = 1 col_axis = 2 channel_axis = -1 if not dilated: input_shape = (receptive_field, receptive_field, n_channels) if inputs is not None: if not K.is_keras_tensor(inputs): img_input = Input(tensor=inputs, shape=input_shape) else: img_input = inputs x.append(img_input) else: x.append(Input(shape=input_shape)) x.append( ImageNormalization2D(norm_method=norm_method, filter_size=receptive_field)(x[-1])) if padding: if padding_mode == 'reflect': x.append(ReflectionPadding2D(padding=(win, win))(x[-1])) elif padding_mode == 'zero': x.append(ZeroPadding2D(padding=(win, win))(x[-1])) if location: x.append(Location2D(in_shape=tuple(x[-1].shape.as_list()[1:]))(x[-1])) x.append(Concatenate(axis=channel_axis)([x[-2], x[-1]])) layers_to_concat = [] rf_counter = receptive_field block_counter = 0 d = 1 while rf_counter > 4: filter_size = 3 if rf_counter % 2 == 0 else 4 x.append( Conv2D(n_conv_filters, filter_size, dilation_rate=d, kernel_initializer=init, padding='valid', kernel_regularizer=l2(reg))(x[-1])) x.append(BatchNormalization(axis=channel_axis)(x[-1])) x.append(Activation('relu')(x[-1])) block_counter += 1 rf_counter -= filter_size - 1 if block_counter % 2 == 0: if dilated: x.append( DilatedMaxPool2D(dilation_rate=d, pool_size=(2, 2))(x[-1])) d *= 2 else: x.append(MaxPool2D(pool_size=(2, 2))(x[-1])) if VGG_mode: n_conv_filters *= 2 rf_counter = rf_counter // 2 if multires: layers_to_concat.append(len(x) - 1) if multires: c = [] for l in layers_to_concat: output_shape = x[l].get_shape().as_list() target_shape = x[-1].get_shape().as_list() row_crop = int(output_shape[row_axis] - target_shape[row_axis]) if row_crop % 2 == 0: row_crop = (row_crop // 2, row_crop // 2) else: row_crop = (row_crop // 2, row_crop // 2 + 1) col_crop = int(output_shape[col_axis] - target_shape[col_axis]) if col_crop % 2 == 0: col_crop = (col_crop // 2, col_crop // 2) else: col_crop = (col_crop // 2, col_crop // 2 + 1) cropping = (row_crop, col_crop) c.append(Cropping2D(cropping=cropping)(x[l])) if multires: x.append(Concatenate(axis=channel_axis)(c)) x.append( Conv2D(n_dense_filters, (rf_counter, rf_counter), dilation_rate=d, kernel_initializer=init, padding='valid', kernel_regularizer=l2(reg))(x[-1])) x.append(BatchNormalization(axis=channel_axis)(x[-1])) x.append(Activation('relu')(x[-1])) if include_top: x.append( TensorProduct(n_dense_filters, kernel_initializer=init, kernel_regularizer=l2(reg))(x[-1])) x.append(BatchNormalization(axis=channel_axis)(x[-1])) x.append(Activation('relu')(x[-1])) x.append( TensorProduct(n_features, kernel_initializer=init, kernel_regularizer=l2(reg))(x[-1])) if not dilated: x.append(Flatten()(x[-1])) x.append(Softmax(axis=channel_axis)(x[-1])) if inputs is not None: real_inputs = keras_utils.get_source_inputs(x[0]) else: real_inputs = x[0] model = Model(inputs=real_inputs, outputs=x[-1]) return model
def SEInceptionV3(include_top=True, weights=None, input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the Squeeze and Excite Inception v3 architecture. # Arguments include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or "imagenet" (pre-training on ImageNet). input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the weights. 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` insight_data format) or `(3, 299, 299)` (with `channels_first` insight_data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 139. 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 weights 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 weights 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 weights instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') 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=299, min_size=139, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if K.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 = 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 = MaxPooling2D((3, 3), strides=(2, 2))(x) # mixed 0, 1, 2: 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 = 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') # squeeze and excite block x = squeeze_excite_block(x) # mixed 1: 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 = 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') # squeeze and excite block x = squeeze_excite_block(x) # mixed 2: 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 = 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') # squeeze and excite block x = squeeze_excite_block(x) # 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 = MaxPooling2D((3, 3), strides=(2, 2))(x) x = layers.concatenate([branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3') # squeeze and excite block x = squeeze_excite_block(x) # 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 = 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') # squeeze and excite block x = squeeze_excite_block(x) # 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 = 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{}'.format(5 + i)) # squeeze and excite block x = squeeze_excite_block(x) # 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 = 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') # squeeze and excite block x = squeeze_excite_block(x) # 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 = MaxPooling2D((3, 3), strides=(2, 2))(x) x = layers.concatenate([branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8') # squeeze and excite block x = squeeze_excite_block(x) # 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_{i}'.format(i=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 = 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{}'.format(9 + i)) # squeeze and excite block x = squeeze_excite_block(x) if include_top: # Classification block x = GlobalAveragePooling2D(name='avg_pool')(x) x = Dense(classes, activation='softmax', name='predictions')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = GlobalMaxPooling2D()(x) # Ensure that the weights 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 weights. model = Model(inputs, x, name='inception_v3') return model
def SEMobileNet(input_shape=None, alpha=1.0, depth_multiplier=1, dropout=1e-3, include_top=True, weights=None, input_tensor=None, pooling=None, classes=1000): """Instantiates the SE-MobileNet architecture. Note that only TensorFlow is supported for now, therefore it only works with the data format `image_data_format='channels_last'` in your Keras config at `~/.keras/keras.json`. To load a MobileNet model via `load_model`, import the custom objects `relu6` and `DepthwiseConv2D` and pass them to the `custom_objects` parameter. E.g. model = load_model('mobilenet.h5', custom_objects={ 'relu6': mobilenet.relu6, 'DepthwiseConv2D': mobilenet.DepthwiseConv2D}) # 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. - 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 (also called the resolution multiplier) dropout: dropout rate 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 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 input shape - `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. RuntimeError: If attempting to run this model with a backend that does not support separable convolutions. """ if K.backend() != 'tensorflow': raise RuntimeError('Only TensorFlow backend is currently supported, ' 'as other backends do not support ' 'depthwise convolution.') if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') 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 K.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 = _obtain_input_shape(input_shape, default_size=default_size, min_size=32, data_format=K.image_data_format(), require_flatten=include_top, weights=weights) if K.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 input_tensor is None: img_input = Input(shape=input_shape) else: if not is_keras_tensor(input_tensor): img_input = 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 K.image_data_format() == 'channels_first': shape = (int(1024 * alpha), 1, 1) else: shape = (1, 1, int(1024 * alpha)) x = GlobalAveragePooling2D()(x) x = Reshape(shape, name='reshape_n_1')(x) x = Dropout(dropout, name='dropout')(x) x = Conv2D(classes, (1, 1), padding='same', name='conv_preds')(x) x = Activation('softmax', name='act_softmax')(x) x = Reshape((classes,), name='reshape_final')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = 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='se_mobilenet_%0.2f_%s' % (alpha, rows)) 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 SENet(model_params, input_tensor=None, input_shape=None, include_top=True, classes=1000, weights='imagenet', **kwargs): """Instantiates the ResNet, SEResNet 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`. Args: 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. 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 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') residual_block = model_params.residual_block init_filters = model_params.init_filters bn_params = get_bn_params() # define input if input_tensor is None: input = layers.Input(shape=input_shape, name='input') else: if not backend.is_keras_tensor(input_tensor): input = layers.Input(tensor=input_tensor, shape=input_shape) else: input = input_tensor x = input if model_params.input_3x3: x = layers.ZeroPadding2D(1)(x) x = layers.Conv2D(init_filters, (3, 3), strides=2, use_bias=False, kernel_initializer='he_uniform')(x) x = layers.BatchNormalization(**bn_params)(x) x = layers.Activation('relu')(x) x = layers.ZeroPadding2D(1)(x) x = layers.Conv2D(init_filters, (3, 3), use_bias=False, kernel_initializer='he_uniform')(x) x = layers.BatchNormalization(**bn_params)(x) x = layers.Activation('relu')(x) x = layers.ZeroPadding2D(1)(x) x = layers.Conv2D(init_filters * 2, (3, 3), use_bias=False, kernel_initializer='he_uniform')(x) x = layers.BatchNormalization(**bn_params)(x) x = layers.Activation('relu')(x) else: x = layers.ZeroPadding2D(3)(x) x = layers.Conv2D(init_filters, (7, 7), strides=2, use_bias=False, kernel_initializer='he_uniform')(x) x = layers.BatchNormalization(**bn_params)(x) x = layers.Activation('relu')(x) x = layers.ZeroPadding2D(1)(x) x = layers.MaxPooling2D((3, 3), strides=2)(x) # body of resnet filters = model_params.init_filters * 2 for i, stage in enumerate(model_params.repetitions): # increase number of filters with each stage filters *= 2 for j in range(stage): # decrease spatial dimensions for each stage (except first, because we have maxpool before) if i == 0 and j == 0: x = residual_block(filters, reduction=model_params.reduction, strides=1, groups=model_params.groups, is_first=True, **kwargs)(x) elif i != 0 and j == 0: x = residual_block(filters, reduction=model_params.reduction, strides=2, groups=model_params.groups, **kwargs)(x) else: x = residual_block(filters, reduction=model_params.reduction, strides=1, groups=model_params.groups, **kwargs)(x) if include_top: x = layers.GlobalAveragePooling2D()(x) if model_params.dropout is not None: x = layers.Dropout(model_params.dropout)(x) x = layers.Dense(classes)(x) x = layers.Activation('softmax', name='output')(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 = input model_name = model_params.model_name model = models.Model(inputs, x, name=model_name) if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES): if include_top: file_name = model_name + '_imagenet_1000.h5' file_hash = WEIGHTS_HASHES[model_name][0] else: file_name = model_name + '_imagenet_1000_no_top.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 bn_feature_net_2D(receptive_field=61, input_shape=(256, 256, 1), inputs=None, n_features=3, n_channels=1, reg=1e-5, n_conv_filters=64, n_dense_filters=200, VGG_mode=False, init='he_normal', norm_method='std', location=False, dilated=False, padding=False, padding_mode='reflect', multires=False, include_top=True): # Create layers list (x) to store all of the layers. # We need to use the functional API to enable the multiresolution mode x = [] win = (receptive_field - 1) // 2 if dilated: padding = True if K.image_data_format() == 'channels_first': channel_axis = 1 row_axis = 2 col_axis = 3 if not dilated: input_shape = (n_channels, receptive_field, receptive_field) else: row_axis = 1 col_axis = 2 channel_axis = -1 if not dilated: input_shape = (receptive_field, receptive_field, n_channels) if inputs is not None: if not K.is_keras_tensor(inputs): img_input = Input(tensor=inputs, shape=input_shape) else: img_input = inputs x.append(img_input) else: x.append(Input(shape=input_shape)) x.append( ImageNormalization2D(norm_method=norm_method, filter_size=receptive_field)(x[-1])) if padding: if padding_mode == 'reflect': x.append(ReflectionPadding2D(padding=(win, win))(x[-1])) elif padding_mode == 'zero': x.append(ZeroPadding2D(padding=(win, win))(x[-1])) if location: x.append(Location2D(in_shape=tuple(x[-1].shape.as_list()[1:]))(x[-1])) x.append(Concatenate(axis=channel_axis)([x[-2], x[-1]])) if multires: layers_to_concat = [] rf_counter = receptive_field block_counter = 0 d = 1 while rf_counter > 4: filter_size = 3 if rf_counter % 2 == 0 else 4 x.append( Conv2D(n_conv_filters, (filter_size, filter_size), dilation_rate=d, kernel_initializer=init, padding='valid', kernel_regularizer=l2(reg))(x[-1])) x.append(BatchNormalization(axis=channel_axis)(x[-1])) x.append(Activation('relu')(x[-1])) block_counter += 1 rf_counter -= filter_size - 1 if block_counter % 2 == 0: if dilated: x.append( DilatedMaxPool2D(dilation_rate=d, pool_size=(2, 2))(x[-1])) d *= 2 else: x.append(MaxPool2D(pool_size=(2, 2))(x[-1])) if VGG_mode: n_conv_filters *= 2 rf_counter = rf_counter // 2 if multires: layers_to_concat.append(len(x) - 1) if multires: c = [] for l in layers_to_concat: output_shape = x[l].get_shape().as_list() target_shape = x[-1].get_shape().as_list() row_crop = int(output_shape[row_axis] - target_shape[row_axis]) if row_crop % 2 == 0: row_crop = (row_crop // 2, row_crop // 2) else: row_crop = (row_crop // 2, row_crop // 2 + 1) col_crop = int(output_shape[col_axis] - target_shape[col_axis]) if col_crop % 2 == 0: col_crop = (col_crop // 2, col_crop // 2) else: col_crop = (col_crop // 2, col_crop // 2 + 1) cropping = (row_crop, col_crop) c.append(Cropping2D(cropping=cropping)(x[l])) if multires: x.append(Concatenate(axis=channel_axis)(c)) x.append( Conv2D(n_dense_filters, (rf_counter, rf_counter), dilation_rate=d, kernel_initializer=init, padding='valid', kernel_regularizer=l2(reg))(x[-1])) x.append(BatchNormalization(axis=channel_axis)(x[-1])) x.append(Activation('relu')(x[-1])) if include_top: x.append( TensorProduct(n_dense_filters, kernel_initializer=init, kernel_regularizer=l2(reg))(x[-1])) x.append(BatchNormalization(axis=channel_axis)(x[-1])) x.append(Activation('relu')(x[-1])) x.append( TensorProduct(n_features, kernel_initializer=init, kernel_regularizer=l2(reg))(x[-1])) if not dilated: x.append(Flatten()(x[-1])) x.append(Softmax(axis=channel_axis)(x[-1])) if inputs is not None: real_inputs = keras_utils.get_source_inputs(x[0]) else: real_inputs = x[0] model = Model(inputs=real_inputs, outputs=x[-1]) return model
def InceptionV1_slim(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1001): """Instantiates the Inception v1 architecture. With weights from slim ! In this case the range of the input image is (-1,1) This architecture is defined in: Going deeper with convolutions Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich. http://arxiv.org/abs/1409.4842v1 Optionally loads weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_data_format="channels_last"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The data format convention used by the model is the one specified in your Keras config file. Note that the default input image size for this model is 224x224. Arguments: include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or "imagenet" (pre-training on ImageNet). 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 139. 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 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 weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') if weights == 'imagenet' and include_top and classes != 1001: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1001') # Determine proper input shape input_shape = _obtain_input_shape( input_shape, #default_size=299, default_size=224, min_size=139, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape, name='input_1') else: img_input = Input(tensor=input_tensor, shape=input_shape, name='input_1') if K.image_data_format() == 'channels_first': channel_axis = 1 else: channel_axis = 3 # 'Sequential bit at start' x = img_input x = conv2d_bn(x, 64, 7, 7, strides=(2, 2), padding='same', name='Conv2d_1a_7x7') x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='MaxPool_2a_3x3')(x) x = conv2d_bn(x, 64, 1, 1, strides=(1, 1), padding='same', name='Conv2d_2b_1x1') x = conv2d_bn(x, 192, 3, 3, strides=(1, 1), padding='same', name='Conv2d_2c_3x3') x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='MaxPool_3a_3x3')(x) # Now the '3' level inception units x = concatenated_block(x, ((64, ), (96, 128), (16, 32), (32, )), channel_axis, 'Mixed_3b') x = concatenated_block(x, ((128, ), (128, 192), (32, 96), (64, )), channel_axis, 'Mixed_3c') x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='MaxPool_4a_3x3')(x) # Now the '4' level inception units x = concatenated_block(x, ((192, ), (96, 208), (16, 48), (64, )), channel_axis, 'Mixed_4b') x = concatenated_block(x, ((160, ), (112, 224), (24, 64), (64, )), channel_axis, 'Mixed_4c') x = concatenated_block(x, ((128, ), (128, 256), (24, 64), (64, )), channel_axis, 'Mixed_4d') x = concatenated_block(x, ((112, ), (144, 288), (32, 64), (64, )), channel_axis, 'Mixed_4e') x = concatenated_block(x, ((256, ), (160, 320), (32, 128), (128, )), channel_axis, 'Mixed_4f') x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='MaxPool_5a_2x2')(x) # Now the '5' level inception units x = concatenated_block(x, ((256, ), (160, 320), (32, 128), (128, )), channel_axis, 'Mixed_5b') x = concatenated_block(x, ((384, ), (192, 384), (48, 128), (128, )), channel_axis, 'Mixed_5c') if include_top: # Classification block # 'AvgPool_0a_7x7' x = AveragePooling2D((7, 7), strides=(1, 1), padding='valid')(x) # 'Dropout_0b' x = Dropout(0.4)( x) # slim has keep_prob (@0.8), keras uses drop_fraction #logits = conv2d_bn(x, classes, 1, 1, strides=(1, 1), padding='valid', name='Logits', # normalizer=False, activation=None, ) # Write out the logits explictly, since it is pretty different x = Conv2D(classes, (1, 1), strides=(1, 1), padding='valid', use_bias=True, name='Logits')(x) x = Flatten(name='Logits_flat')(x) #x = x[:, 1:] # ??Shift up so that first class ('blank background') vanishes # Would be more efficient to strip off position[0] from the weights+bias terms directly in 'Logits' x = Activation('softmax', name='Predictions')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D(name='global_pooling')(x) elif pooling == 'max': x = GlobalMaxPooling2D(name='global_pooling')(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 # Finally : Create model model = Model(inputs, x, name='inception_v1_slim') # LOAD model weights if weights == 'imagenet': if K.image_data_format() == 'channels_first': if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image data format convention ' '(`image_data_format="channels_first"`). ' 'For best performance, set ' '`image_data_format="channels_last"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') if include_top: weights_path = get_file( 'inception_v1_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', md5_hash='723bf2f662a5c07db50d28c8d35b626d') else: weights_path = get_file( 'inception_v1_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='6fa8ecdc5f6c402a59909437f0f5c975') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def VGG16(include_top=True, weights='vggface', input_tensor=None, input_shape=None, pooling=None, classes=2622): input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=48, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_1')( img_input) x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool1')(x) # Block 2 x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_1')( x) x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_2')( x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool2')(x) # Block 3 x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_1')( x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_2')( x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_3')( x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool3')(x) # Block 4 x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_1')( x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_2')( x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_3')( x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool4')(x) # Block 5 x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_1')( x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_2')( x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_3')( x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool5')(x) if include_top: # Classification block x = Flatten(name='flatten')(x) x = Dense(4096, name='fc6')(x) x = Activation('relu', name='fc6/relu')(x) x = Dense(4096, name='fc7')(x) x = Activation('relu', name='fc7/relu')(x) x = Dense(classes, name='fc8')(x) x = Activation('softmax', name='fc8/softmax')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = 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='vggface_vgg16') # load weights if weights == 'vggface': if include_top: weights_path = get_file('rcmalli_vggface_tf_vgg16.h5', utils. VGG16_WEIGHTS_PATH, cache_subdir=utils.VGGFACE_DIR) else: weights_path = get_file('rcmalli_vggface_tf_notop_vgg16.h5', utils.VGG16_WEIGHTS_PATH_NO_TOP, cache_subdir=utils.VGGFACE_DIR) model.load_weights(weights_path, by_name=True) if K.backend() == 'theano': layer_utils.convert_all_kernels_in_model(model) if K.image_data_format() == 'channels_first': if include_top: maxpool = model.get_layer(name='pool5') shape = maxpool.output_shape[1:] dense = model.get_layer(name='fc6') layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first') if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image data format convention ' '(`image_data_format="channels_first"`). ' 'For best performance, set ' '`image_data_format="channels_last"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') return model
def SENET50(include_top=True, weights='vggface', input_tensor=None, input_shape=None, pooling=None, classes=8631): input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=197, data_format=K.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = 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 = Conv2D( 64, (7, 7), use_bias=False, strides=(2, 2), padding='same', name='conv1/7x7_s2')(img_input) x = BatchNormalization(axis=bn_axis, name='conv1/7x7_s2/bn')(x) x = Activation('relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2))(x) x = senet_conv_block(x, 3, [64, 64, 256], stage=2, block=1, strides=(1, 1)) x = senet_identity_block(x, 3, [64, 64, 256], stage=2, block=2) x = senet_identity_block(x, 3, [64, 64, 256], stage=2, block=3) x = senet_conv_block(x, 3, [128, 128, 512], stage=3, block=1) x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=2) x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=3) x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=4) x = senet_conv_block(x, 3, [256, 256, 1024], stage=4, block=1) x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=2) x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=3) x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=4) x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=5) x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=6) x = senet_conv_block(x, 3, [512, 512, 2048], stage=5, block=1) x = senet_identity_block(x, 3, [512, 512, 2048], stage=5, block=2) x = senet_identity_block(x, 3, [512, 512, 2048], stage=5, block=3) x = AveragePooling2D((7, 7), name='avg_pool')(x) if include_top: x = Flatten()(x) x = Dense(classes, activation='softmax', name='classifier')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = 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='vggface_senet50') # load weights if weights == 'vggface': if include_top: weights_path = get_file('rcmalli_vggface_tf_senet50.h5', utils.SENET50_WEIGHTS_PATH, cache_subdir=utils.VGGFACE_DIR) else: weights_path = get_file('rcmalli_vggface_tf_notop_senet50.h5', utils.SENET50_WEIGHTS_PATH_NO_TOP, cache_subdir=utils.VGGFACE_DIR) model.load_weights(weights_path) if K.backend() == 'theano': layer_utils.convert_all_kernels_in_model(model) if include_top: maxpool = model.get_layer(name='avg_pool') shape = maxpool.output_shape[1:] dense = model.get_layer(name='classifier') layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first') if K.image_data_format() == 'channels_first' and K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image data format convention ' '(`image_data_format="channels_first"`). ' 'For best performance, set ' '`image_data_format="channels_last"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') elif weights is not None: model.load_weights(weights) return model
def SEResNext(input_shape=None, depth=29, cardinality=8, width=64, weight_decay=5e-4, include_top=True, weights=None, input_tensor=None, pooling=None, classes=10): """Instantiate the ResNeXt architecture. Note that , when using TensorFlow for best performance you should set `image_data_format="channels_last"` in your Keras config at ~/.keras/keras.json. The weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the weights is the one specified in your Keras config file. # Arguments depth: number or layers in the ResNeXt weights. Can be an integer or a list of integers. cardinality: the size of the set of transformations width: multiplier to the ResNeXt width (number of filters) weight_decay: weight decay (l2 norm) include_top: whether to include the fully-connected layer at the top of the network. weights: `None` (random initialization) input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the weights. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(32, 32, 3)` (with `tf` dim ordering) or `(3, 32, 32)` (with `th` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. 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 weights 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 weights 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 weights instance. """ if weights not in {'cifar10', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `cifar10` ' '(pre-training on CIFAR-10).') if weights == 'cifar10' and include_top and classes != 10: raise ValueError('If using `weights` as CIFAR 10 with `include_top`' ' as true, `classes` should be 10') if type(depth) is int: if (depth - 2) % 9 != 0: raise ValueError('Depth of the network must be such that (depth - 2)' 'should be divisible by 9.') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = __create_res_next(classes, img_input, include_top, depth, cardinality, width, weight_decay, pooling) # Ensure that the weights 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 weights. model = Model(inputs, x, name='se-resnext') 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 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 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, kernel_regularizer=regularizers.l2(regular_weight), 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') elif blocks == [6, 12, 32, 32]: model = models.Model(inputs, x, name='densenet169') elif blocks == [6, 12, 48, 32]: model = models.Model(inputs, x, name='densenet201') else: model = models.Model(inputs, x, name='densenet') # Load weights. if weights == 'imagenet': if include_top: if blocks == [6, 12, 24, 16]: weights_path = keras_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 = keras_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 = keras_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 = keras_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 = keras_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 = keras_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 resnet_dropout(include_top=False, weights='imagenet', input_tensor=None, pooling='avg', input_shape=(224, 224, 3), classes=25, dp_rate=0., n_retrain_layers=0): WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5' WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') 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=197,data_format=K.image_data_format(),include_top=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = 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 = ZeroPadding2D((3, 3))(img_input) x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x) x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = Activation('relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2))(x) 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') 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') 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') 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 = Dropout(dp_rate)(x) x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c') x = AveragePooling2D((7, 7), name='avg_pool')(x) if include_top: x = Flatten()(x) x = Dense(classes, activation='softmax', name='fc1000')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = 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') # load weights if weights == 'imagenet': if include_top: weights_path = get_file( 'resnet50_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', md5_hash='a7b3fe01876f51b976af0dea6bc144eb') else: weights_path = 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) split_value = len(model.layers) + 1 - n_retrain_layers for layer in model.layers[:split_value]: layer.trainable = False for layer in model.layers[split_value:]: layer.trainable = True return model
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 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. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. RuntimeError: If attempting to run this model with a backend that does not support separable convolutions. """ 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 = _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 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 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.Activation('softmax', name='act_softmax')(x) x = layers.Reshape((classes, ), name='reshape_2')(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='mobilenet_%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 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 = keras_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 = keras_utils.get_file(model_name, weight_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 SEInceptionResNetV2(include_top=True, weights=None, input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the SE-Inception-ResNet v2 architecture. Optionally loads weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `"image_data_format": "channels_last"` in your Keras config at `~/.keras/keras.json`. The model and the weights are compatible with both TensorFlow and Theano backends (but not CNTK). The data format convention used by the model is the one specified in your Keras config file. Note that the default input image size for this model is 299x299, instead of 224x224 as in the VGG16 and ResNet models. Also, the input preprocessing function is different (i.e., do not use `imagenet_utils.preprocess_input()` with this model. Use `preprocess_input()` defined in this module instead). # Arguments include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or `'imagenet'` (pre-training on ImageNet). 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 139. 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 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. RuntimeError: If attempting to run this model with an unsupported backend. """ if K.backend() in {'cntk'}: raise RuntimeError( '{backend} backend is currently unsupported for this model.'. format(backend=K.backend())) if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') 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=299, min_size=139, data_format=K.image_data_format(), require_flatten=False, weights=weights) if input_tensor is None: img_input = Input(shape=input_shape) else: if not is_keras_tensor(input_tensor): img_input = 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 = MaxPooling2D(3, strides=2)(x) x = conv2d_bn(x, 80, 1, padding='valid') x = conv2d_bn(x, 192, 3, padding='valid') x = 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 = 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 K.image_data_format() == 'channels_first' else 3 x = Concatenate(axis=channel_axis, name='mixed_5b')(branches) # squeeze and excite block x = squeeze_excite_block(x) # 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 = MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_pool] x = Concatenate(axis=channel_axis, name='mixed_6a')(branches) # squeeze and excite block x = squeeze_excite_block(x) # 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 = MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_2, branch_pool] x = Concatenate(axis=channel_axis, name='mixed_7a')(branches) # squeeze and excite block x = squeeze_excite_block(x) # 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) # squeeze and excite block x = squeeze_excite_block(x) # Final convolution block: 8 x 8 x 1536 x = conv2d_bn(x, 1536, 1, name='conv_7b') if include_top: # Classification block x = GlobalAveragePooling2D(name='avg_pool')(x) x = Dense(classes, activation='softmax', name='predictions')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = 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='se_inception_resnet_v2') return model
def SEResNet(input_shape=None, initial_conv_filters=64, depth=[3, 4, 6, 3], filters=[64, 128, 256, 512], width=1, bottleneck=False, weight_decay=1e-4, include_top=True, weights=None, input_tensor=None, pooling=None, classes=1000): """ Instantiate the Squeeze and Excite ResNet architecture. Note that , when using TensorFlow for best performance you should set `image_data_format="channels_last"` in your Keras config at ~/.keras/keras.json. The model are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments initial_conv_filters: number of features for the initial convolution depth: number or layers in the each block, defined as a list. ResNet-50 = [3, 4, 6, 3] ResNet-101 = [3, 6, 23, 3] ResNet-152 = [3, 8, 36, 3] filter: number of filters per block, defined as a list. filters = [64, 128, 256, 512 width: width multiplier for the network (for Wide ResNets) bottleneck: adds a bottleneck conv to reduce computation weight_decay: weight decay (l2 norm) include_top: whether to include the fully-connected layer at the top of the network. weights: `None` (random initialization) or `imagenet` (trained on ImageNet) 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 `tf` dim ordering) or `(3, 224, 224)` (with `th` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. 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 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. """ if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') 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') assert len(depth) == len(filters), "The length of filter increment list must match the length " \ "of the depth list." # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=32, data_format=K.image_data_format(), require_flatten=False) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = _create_se_resnet(classes, img_input, include_top, initial_conv_filters, filters, depth, width, bottleneck, weight_decay, pooling) # Ensure that the model takes into accounttf.python.keras.backend # 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='resnext') # load 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