def DenseNet121(input_shape=None): input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=True) img_input = layers.Input(shape=input_shape) bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input) x = layers.Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x) x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x) x = layers.Activation('relu', name='conv1/relu')(x) x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x) x = layers.MaxPooling2D(3, strides=2, name='pool1')(x) x = dense_block(x, 6, name='conv2') x = transition_block(x, 0.5, name='pool2') x = dense_block(x, 12, name='conv3') x = transition_block(x, 0.5, name='pool3') x = dense_block(x, 24, name='conv4') x = transition_block(x, 0.5, name='pool4') x = dense_block(x, 16, name='conv5') x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x) x = layers.Activation('relu', name='relu')(x) x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation('softmax', None) x = layers.Dense(NUM_CLASSES, activation='softmax', name='predictions')(x) # Create model. model = training.Model(img_input, x, name='densenet121') return model
def validate_input(input_shape, weights, include_top, classes): 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 return obtain_input_shape( input_shape, default_size=224, min_size=0, data_format=keras.backend.image_data_format(), require_flatten=include_top, weights=weights, )
def ResNet50V2(input_shape=None): input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=True) img_input = layers.Input(shape=input_shape) bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input) x = layers.Conv2D(64, 7, strides=2, use_bias=True, name='conv1_conv')(x) x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x) x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x) x = stack2(x, 64, 3, name='conv2') x = stack2(x, 128, 4, name='conv3') x = stack2(x, 256, 6, name='conv4') x = stack2(x, 512, 3, stride1=1, name='conv5') x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='post_bn')(x) x = layers.Activation('relu', name='post_relu')(x) x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation('softmax', None) x = layers.Dense(NUM_CLASSES, activation='softmax', name='predictions')(x) # Create model. model = training.Model(img_input, x, name="resnet50v2") 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 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, classifier_activation='softmax', **kwargs): global layers if 'layers' in kwargs: layers = kwargs.pop('layers') else: layers = VersionAwareLayers() if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) 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') # Determine proper input shape and default size. if input_shape is None: default_size = 224 else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [128, 160, 192, 224]: default_size = rows else: default_size = 224 input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if 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=(8, 8)) #x = _depthwise_conv_block( # x, 128, alpha, depth_multiplier, strides=(2,2), block_id=2) #x = _depthwise_conv_block( # x, 1024, alpha, depth_multiplier, strides=(2,2)) 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.Conv2D(classes, (1, 1), padding='same', name='conv_preds')(x) x = layers.Reshape((classes, ), name='reshape_2')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Activation(activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='mobilenet_%0.2f_%s' % (alpha, rows)) return model
def VGG19(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax'): """Instantiates the VGG19 architecture. Reference: - [Very Deep Convolutional Networks for Large-Scale Image Recognition]( https://arxiv.org/abs/1409.1556) (ICLR 2015) By default, it loads weights pre-trained on ImageNet. Check 'weights' for other options. This model can be built both with 'channels_first' data format (channels, height, width) or 'channels_last' data format (height, width, channels). The default input size for this model is 224x224. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.vgg19.preprocess_input` for an example. Arguments: include_top: whether to include the 3 fully-connected layers at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or 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') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input) x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x) x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv4')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv4')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv4')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # Classification block x = layers.Flatten(name='flatten')(x) x = layers.Dense(4096, activation='relu', name='fc1')(x) x = layers.Dense(4096, activation='relu', name='fc2')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='vgg19') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'vgg19_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', file_hash='cbe5617147190e668d6c5d5026f83318') else: weights_path = data_utils.get_file( 'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='253f8cb515780f3b799900260a226db6') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def ResNet(stack_fn, preact, use_bias, model_name='resnet', include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): """Instantiates the ResNet, ResNetV2, and ResNeXt architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.resnet.preprocess_input` for an example. Arguments: stack_fn: a function that returns output tensor for the stacked residual blocks. preact: whether to use pre-activation or not (True for ResNetV2, False for ResNet and ResNeXt). use_bias: whether to use biases for convolutional layers or not (True for ResNet and ResNetV2, False for ResNeXt). model_name: string, model name. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels. pooling: optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if 'layers' in kwargs: global layers layers = kwargs.pop('layers') if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input) x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x) if not preact: x = tf.keras.layers.experimental.SyncBatchNormalization( axis=bn_axis, name='conv1_bn')(x) x = layers.Activation('relu', name='conv1_relu')(x) x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x) x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x) x = stack_fn(x) if preact: x = tf.keras.layers.experimental.SyncBatchNormalization( axis=bn_axis, name='post_bn')(x) x = layers.Activation('relu', name='post_relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name=model_name) # Load weights. if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES): if include_top: file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5' file_hash = WEIGHTS_HASHES[model_name][0] else: file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5' file_hash = WEIGHTS_HASHES[model_name][1] weights_path = data_utils.get_file(file_name, BASE_WEIGHTS_PATH + file_name, cache_subdir='models', file_hash=file_hash) model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def EfficientNet(width_coefficient, depth_coefficient, default_size, dropout_rate=0.2, drop_connect_rate=0.2, depth_divisor=8, activation='swish', blocks_args='default', model_name='efficientnet', include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax'): """Instantiates the EfficientNet architecture using given scaling coefficients. Args: width_coefficient: float, scaling coefficient for network width. depth_coefficient: float, scaling coefficient for network depth. default_size: integer, default input image size. dropout_rate: float, dropout rate before final classifier layer. drop_connect_rate: float, dropout rate at skip connections. depth_divisor: integer, a unit of network width. activation: activation function. blocks_args: list of dicts, parameters to construct block modules. model_name: string, model name. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False. It should have exactly 3 inputs channels. pooling: optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if blocks_args == 'default': blocks_args = DEFAULT_BLOCKS_ARGS if not (weights in {'imagenet', None} or file_io.file_exists_v2(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 def round_filters(filters, divisor=depth_divisor): """Round number of filters based on depth multiplier.""" filters *= width_coefficient new_filters = max(divisor, int(filters + divisor / 2) // divisor * divisor) # Make sure that round down does not go down by more than 10%. if new_filters < 0.9 * filters: new_filters += divisor return int(new_filters) def round_repeats(repeats): """Round number of repeats based on depth multiplier.""" return int(math.ceil(depth_coefficient * repeats)) # Build stem x = img_input x = layers.Rescaling(1. / 255.)(x) x = layers.Normalization(axis=bn_axis)(x) x = layers.ZeroPadding2D(padding=imagenet_utils.correct_pad(x, 3), name='stem_conv_pad')(x) x = layers.Conv2D(round_filters(32), 3, strides=2, padding='valid', use_bias=False, kernel_initializer=CONV_KERNEL_INITIALIZER, name='stem_conv')(x) x = layers.BatchNormalization(axis=bn_axis, name='stem_bn')(x) x = layers.Activation(activation, name='stem_activation')(x) # Build blocks blocks_args = copy.deepcopy(blocks_args) b = 0 blocks = float(sum(round_repeats(args['repeats']) for args in blocks_args)) for (i, args) in enumerate(blocks_args): assert args['repeats'] > 0 # Update block input and output filters based on depth multiplier. args['filters_in'] = round_filters(args['filters_in']) args['filters_out'] = round_filters(args['filters_out']) for j in range(round_repeats(args.pop('repeats'))): # The first block needs to take care of stride and filter size increase. if j > 0: args['strides'] = 1 args['filters_in'] = args['filters_out'] x = block(x, activation, drop_connect_rate * b / blocks, name='block{}{}_'.format(i + 1, chr(j + 97)), **args) b += 1 # Build top x = layers.Conv2D(round_filters(1280), 1, padding='same', use_bias=False, kernel_initializer=CONV_KERNEL_INITIALIZER, name='top_conv')(x) x = layers.BatchNormalization(axis=bn_axis, name='top_bn')(x) x = layers.Activation(activation, name='top_activation')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) if dropout_rate > 0: x = layers.Dropout(dropout_rate, name='top_dropout')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, kernel_initializer=DENSE_KERNEL_INITIALIZER, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name=model_name) # Load weights. if weights == 'imagenet': if include_top: file_suffix = '.h5' file_hash = WEIGHTS_HASHES[model_name[-2:]][0] else: file_suffix = '_notop.h5' file_hash = WEIGHTS_HASHES[model_name[-2:]][1] file_name = model_name + file_suffix weights_path = data_utils.get_file(file_name, BASE_WEIGHTS_PATH + file_name, cache_subdir='models', file_hash=file_hash) model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def DenseNet(blocks, include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax'): """Instantiates the DenseNet architecture. Reference: - [Densely Connected Convolutional Networks]( https://arxiv.org/abs/1608.06993) (CVPR 2017) Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Note: each Keras Application expects a specific kind of input preprocessing. For DenseNet, call `tf.keras.applications.densenet.preprocess_input` on your inputs before passing them to the model. Args: blocks: numbers of building blocks for the four dense layers. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `'channels_last'` data format) or `(3, 224, 224)` (with `'channels_first'` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or file_io.file_exists_v2(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input) x = layers.Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x) x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x) x = layers.Activation('relu', name='conv1/relu')(x) x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x) x = layers.MaxPooling2D(3, strides=2, name='pool1')(x) x = dense_block(x, blocks[0], name='conv2') x = transition_block(x, 0.5, name='pool2') x = dense_block(x, blocks[1], name='conv3') x = transition_block(x, 0.5, name='pool3') x = dense_block(x, blocks[2], name='conv4') x = transition_block(x, 0.5, name='pool4') x = dense_block(x, blocks[3], name='conv5') x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x) x = layers.Activation('relu', name='relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. if blocks == [6, 12, 24, 16]: model = training.Model(inputs, x, name='densenet121') elif blocks == [6, 12, 32, 32]: model = training.Model(inputs, x, name='densenet169') elif blocks == [6, 12, 48, 32]: model = training.Model(inputs, x, name='densenet201') else: model = training.Model(inputs, x, name='densenet') # Load weights. if weights == 'imagenet': if include_top: if blocks == [6, 12, 24, 16]: weights_path = data_utils.get_file( 'densenet121_weights_tf_dim_ordering_tf_kernels.h5', DENSENET121_WEIGHT_PATH, cache_subdir='models', file_hash='9d60b8095a5708f2dcce2bca79d332c7') elif blocks == [6, 12, 32, 32]: weights_path = data_utils.get_file( 'densenet169_weights_tf_dim_ordering_tf_kernels.h5', DENSENET169_WEIGHT_PATH, cache_subdir='models', file_hash='d699b8f76981ab1b30698df4c175e90b') elif blocks == [6, 12, 48, 32]: weights_path = data_utils.get_file( 'densenet201_weights_tf_dim_ordering_tf_kernels.h5', DENSENET201_WEIGHT_PATH, cache_subdir='models', file_hash='1ceb130c1ea1b78c3bf6114dbdfd8807') else: if blocks == [6, 12, 24, 16]: weights_path = data_utils.get_file( 'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5', DENSENET121_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='30ee3e1110167f948a6b9946edeeb738') elif blocks == [6, 12, 32, 32]: weights_path = data_utils.get_file( 'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5', DENSENET169_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='b8c4d4c20dd625c148057b9ff1c1176b') elif blocks == [6, 12, 48, 32]: weights_path = data_utils.get_file( 'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5', DENSENET201_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='c13680b51ded0fb44dff2d8f86ac8bb1') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def InceptionResNetV2(input_shape=None): input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=299, min_size=75, data_format=backend.image_data_format(), require_flatten=True) img_input = layers.Input(shape=input_shape) # Stem block: 35 x 35 x 192 x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid') x = conv2d_bn(x, 32, 3, padding='valid') x = conv2d_bn(x, 64, 3) x = layers.MaxPooling2D(3, strides=2)(x) x = conv2d_bn(x, 80, 1, padding='valid') x = conv2d_bn(x, 192, 3, padding='valid') x = layers.MaxPooling2D(3, strides=2)(x) # Mixed 5b (Inception-A block): 35 x 35 x 320 branch_0 = conv2d_bn(x, 96, 1) branch_1 = conv2d_bn(x, 48, 1) branch_1 = conv2d_bn(branch_1, 64, 5) branch_2 = conv2d_bn(x, 64, 1) branch_2 = conv2d_bn(branch_2, 96, 3) branch_2 = conv2d_bn(branch_2, 96, 3) branch_pool = layers.AveragePooling2D(3, strides=1, padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1) branches = [branch_0, branch_1, branch_2, branch_pool] channel_axis = 1 if backend.image_data_format() == 'channels_first' else 3 x = layers.Concatenate(axis=channel_axis, name='mixed_5b')(branches) # 10x block35 (Inception-ResNet-A block): 35 x 35 x 320 for block_idx in range(1, 11): x = inception_resnet_block(x, scale=0.17, block_type='block35', block_idx=block_idx) # Mixed 6a (Reduction-A block): 17 x 17 x 1088 branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid') branch_1 = conv2d_bn(x, 256, 1) branch_1 = conv2d_bn(branch_1, 256, 3) branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_6a')(branches) # 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088 for block_idx in range(1, 21): x = inception_resnet_block(x, scale=0.1, block_type='block17', block_idx=block_idx) # Mixed 7a (Reduction-B block): 8 x 8 x 2080 branch_0 = conv2d_bn(x, 256, 1) branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid') branch_1 = conv2d_bn(x, 256, 1) branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid') branch_2 = conv2d_bn(x, 256, 1) branch_2 = conv2d_bn(branch_2, 288, 3) branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_2, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_7a')(branches) # 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080 for block_idx in range(1, 10): x = inception_resnet_block(x, scale=0.2, block_type='block8', block_idx=block_idx) x = inception_resnet_block(x, scale=1., activation=None, block_type='block8', block_idx=10) # Final convolution block: 8 x 8 x 1536 x = conv2d_bn(x, 1536, 1, name='conv_7b') # Classification block x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation('softmax', None) x = layers.Dense(NUM_CLASSES, activation='softmax', name='predictions')(x) # Create model. model = training.Model(img_input, x, name='inception_resnet_v2') return model
def test_obtain_input_shape(self, data_format): # input_shape and default_size are not identical. with self.assertRaises(ValueError): utils.obtain_input_shape(input_shape=(224, 224, 3), default_size=299, min_size=139, data_format='channels_last', require_flatten=True, weights='imagenet') # Test invalid use cases shape = (139, 139) if data_format == 'channels_last': input_shape = shape + (99, ) else: input_shape = (99, ) + shape # input_shape is smaller than min_size. shape = (100, 100) if data_format == 'channels_last': input_shape = shape + (3, ) else: input_shape = (3, ) + shape with self.assertRaises(ValueError): utils.obtain_input_shape(input_shape=input_shape, default_size=None, min_size=139, data_format=data_format, require_flatten=False) # shape is 1D. shape = (100, ) if data_format == 'channels_last': input_shape = shape + (3, ) else: input_shape = (3, ) + shape with self.assertRaises(ValueError): utils.obtain_input_shape(input_shape=input_shape, default_size=None, min_size=139, data_format=data_format, require_flatten=False) # the number of channels is 5 not 3. shape = (100, 100) if data_format == 'channels_last': input_shape = shape + (5, ) else: input_shape = (5, ) + shape with self.assertRaises(ValueError): utils.obtain_input_shape(input_shape=input_shape, default_size=None, min_size=139, data_format=data_format, require_flatten=False) # require_flatten=True with dynamic input shape. with self.assertRaises(ValueError): utils.obtain_input_shape(input_shape=None, default_size=None, min_size=139, data_format='channels_first', require_flatten=True) # test include top self.assertEqual( utils.obtain_input_shape(input_shape=(3, 200, 200), default_size=None, min_size=139, data_format='channels_first', require_flatten=True), (3, 200, 200)) self.assertEqual( utils.obtain_input_shape(input_shape=None, default_size=None, min_size=139, data_format='channels_last', require_flatten=False), (None, None, 3)) self.assertEqual( utils.obtain_input_shape(input_shape=None, default_size=None, min_size=139, data_format='channels_first', require_flatten=False), (3, None, None)) self.assertEqual( utils.obtain_input_shape(input_shape=None, default_size=None, min_size=139, data_format='channels_last', require_flatten=False), (None, None, 3)) self.assertEqual( utils.obtain_input_shape(input_shape=(150, 150, 3), default_size=None, min_size=139, data_format='channels_last', require_flatten=False), (150, 150, 3)) self.assertEqual( utils.obtain_input_shape(input_shape=(3, None, None), default_size=None, min_size=139, data_format='channels_first', require_flatten=False), (3, None, None))
def InceptionResNetV2(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): """Instantiates the Inception-ResNet v2 architecture. Reference: - [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://arxiv.org/abs/1602.07261) (AAAI 2017) Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.inception_resnet_v2.preprocess_input` for an example. Arguments: include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is `False` (otherwise the input shape has to be `(299, 299, 3)` (with `'channels_last'` data format) or `(3, 299, 299)` (with `'channels_first'` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `'avg'` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `'max'` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is `True`, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ global layers if 'layers' in kwargs: layers = kwargs.pop('layers') else: layers = VersionAwareLayers() if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=299, min_size=75, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Stem block: 35 x 35 x 192 x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid') x = conv2d_bn(x, 32, 3, padding='valid') x = conv2d_bn(x, 64, 3) x = layers.MaxPooling2D(3, strides=2)(x) x = conv2d_bn(x, 80, 1, padding='valid') x = conv2d_bn(x, 192, 3, padding='valid') x = layers.MaxPooling2D(3, strides=2)(x) # Mixed 5b (Inception-A block): 35 x 35 x 320 branch_0 = conv2d_bn(x, 96, 1) branch_1 = conv2d_bn(x, 48, 1) branch_1 = conv2d_bn(branch_1, 64, 5) branch_2 = conv2d_bn(x, 64, 1) branch_2 = conv2d_bn(branch_2, 96, 3) branch_2 = conv2d_bn(branch_2, 96, 3) branch_pool = layers.AveragePooling2D(3, strides=1, padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1) branches = [branch_0, branch_1, branch_2, branch_pool] channel_axis = 1 if backend.image_data_format() == 'channels_first' else 3 x = layers.Concatenate(axis=channel_axis, name='mixed_5b')(branches) # 10x block35 (Inception-ResNet-A block): 35 x 35 x 320 for block_idx in range(1, 11): x = inception_resnet_block(x, scale=0.17, block_type='block35', block_idx=block_idx) # Mixed 6a (Reduction-A block): 17 x 17 x 1088 branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid') branch_1 = conv2d_bn(x, 256, 1) branch_1 = conv2d_bn(branch_1, 256, 3) branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_6a')(branches) # 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088 for block_idx in range(1, 21): x = inception_resnet_block(x, scale=0.1, block_type='block17', block_idx=block_idx) # Mixed 7a (Reduction-B block): 8 x 8 x 2080 branch_0 = conv2d_bn(x, 256, 1) branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid') branch_1 = conv2d_bn(x, 256, 1) branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid') branch_2 = conv2d_bn(x, 256, 1) branch_2 = conv2d_bn(branch_2, 288, 3) branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_2, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_7a')(branches) # 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080 for block_idx in range(1, 10): x = inception_resnet_block(x, scale=0.2, block_type='block8', block_idx=block_idx) x = inception_resnet_block(x, scale=1., activation=None, block_type='block8', block_idx=10) # Final convolution block: 8 x 8 x 1536 x = conv2d_bn(x, 1536, 1, name='conv_7b') if include_top: # Classification block x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='inception_resnet_v2') # Load weights. if weights == 'imagenet': if include_top: fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5' weights_path = data_utils.get_file( fname, BASE_WEIGHT_URL + fname, cache_subdir='models', file_hash='e693bd0210a403b3192acc6073ad2e96') else: fname = ('inception_resnet_v2_weights_' 'tf_dim_ordering_tf_kernels_notop.h5') weights_path = data_utils.get_file( fname, BASE_WEIGHT_URL + fname, cache_subdir='models', file_hash='d19885ff4a710c122648d3b5c3b684e4') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def VGG16(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax'): """Instantiates the VGG16 model. Reference: - [Very Deep Convolutional Networks for Large-Scale Image Recognition]( https://arxiv.org/abs/1409.1556) (ICLR 2015) For image classification use cases, see [this page for detailed examples]( https://keras.io/api/applications/#usage-examples-for-image-classification-models). For transfer learning use cases, make sure to read the [guide to transfer learning & fine-tuning]( https://keras.io/guides/transfer_learning/). The default input size for this model is 224x224. Note: each Keras Application expects a specific kind of input preprocessing. For VGG16, call `tf.keras.applications.vgg16.preprocess_input` on your inputs before passing them to the model. `vgg16.preprocess_input` will convert the input images from RGB to BGR, then will zero-center each color channel with respect to the ImageNet dataset, without scaling. Args: include_top: whether to include the 3 fully-connected layers at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 input channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. When loading pretrained weights, `classifier_activation` can only be `None` or `"softmax"`. Returns: A `keras.Model` instance. """ if not (weights in {'imagenet', None} or file_io.file_exists_v2(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input) x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x) x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # Classification block x = layers.Flatten(name='flatten')(x) x = layers.Dense(4096, activation='relu', name='fc1')(x) x = layers.Dense(4096, activation='relu', name='fc2')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='vgg16') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', file_hash='64373286793e3c8b2b4e3219cbf3544b') else: weights_path = data_utils.get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='6d6bbae143d832006294945121d1f1fc') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def MobileNet(input_shape=None, alpha=1.0, depth_multiplier=1, dropout=1e-3): if input_shape is None: default_size = 224 else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [128, 160, 192, 224]: default_size = rows else: default_size = 224 input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=True) row_axis = 0 if backend.image_data_format() == 'channels_last' else 0 rows = input_shape[row_axis] img_input = layers.Input(shape=input_shape) 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 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(NUM_CLASSES, (1, 1), padding='same', name='conv_preds')(x) x = layers.Reshape((NUM_CLASSES,), name='reshape_2')(x) imagenet_utils.validate_activation('softmax', None) x = layers.Activation(activation='softmax', name='predictions')(x) # Create model. model = training.Model(img_input, x, name='mobilenet_%0.2f_%s' % (alpha, rows)) return model
def InceptionResNetV2(require_flatten=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the 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 require_flatten: 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 `require_flatten` 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 `require_flatten` 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 `require_flatten` 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(K.backend() + ' backend is currently unsupported for this model.') 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 require_flatten and classes != 1000: raise ValueError( 'If using `weights` as imagenet with `require_flatten`' ' 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 K.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) # 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) # 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) # 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080 for block_idx in range(1, 10): x = inception_resnet_block(x, scale=0.2, block_type='block8', block_idx=block_idx) x = inception_resnet_block(x, scale=1., activation=None, block_type='block8', block_idx=10) # Final convolution block: 8 x 8 x 1536 x = conv2d_bn(x, 1536, 1, name='conv_7b') if require_flatten: # 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='inception_resnet_v2') # Load 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 require_flatten: weights_filename = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5' weights_path = get_file( weights_filename, BASE_WEIGHT_URL + weights_filename, cache_subdir='models', md5_hash='e693bd0210a403b3192acc6073ad2e96') else: weights_filename = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5' weights_path = get_file( weights_filename, BASE_WEIGHT_URL + weights_filename, cache_subdir='models', md5_hash='d19885ff4a710c122648d3b5c3b684e4') model.load_weights(weights_path) return model
def Xception(require_flatten=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the Xception architecture. Optionally loads weights pre-trained on ImageNet. This model is available for TensorFlow only, and can only be used with inputs following the TensorFlow data format `(width, height, channels)`. You should set `image_data_format="channels_last"` in your Keras config located at ~/.keras/keras.json. Note that the default input image size for this model is 299x299. # Arguments require_flatten: 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 `require_flatten` is False (otherwise the input shape has to be `(299, 299, 3)`. It should have exactly 3 inputs channels, and width and height should be no smaller than 71. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `require_flatten` 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 `require_flatten` 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 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 require_flatten and classes != 1000: raise ValueError('If using `weights` as imagenet with `require_flatten`' ' as true, `classes` should be 1000') if K.backend() != 'tensorflow': raise RuntimeError('The Xception model is only available with ' 'the TensorFlow backend.') if K.image_data_format() != 'channels_last': warnings.warn('The Xception model 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.') K.set_image_data_format('channels_last') old_data_format = 'channels_first' else: old_data_format = None # Determine proper input shape input_shape = obtain_input_shape(input_shape, default_size=299, min_size=71, data_format=K.image_data_format(), require_flatten=require_flatten) 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 = Conv2D(32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(img_input) x = BatchNormalization(name='block1_conv1_bn')(x) x = Activation('relu', name='block1_conv1_act')(x) x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x) x = BatchNormalization(name='block1_conv2_bn')(x) x = Activation('relu', name='block1_conv2_act')(x) residual = Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = BatchNormalization()(residual) x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x) x = BatchNormalization(name='block2_sepconv1_bn')(x) x = Activation('relu', name='block2_sepconv2_act')(x) x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x) x = BatchNormalization(name='block2_sepconv2_bn')(x) x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block2_pool')(x) x = layers.add([x, residual]) residual = Conv2D(256, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = BatchNormalization()(residual) x = Activation('relu', name='block3_sepconv1_act')(x) x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x) x = BatchNormalization(name='block3_sepconv1_bn')(x) x = Activation('relu', name='block3_sepconv2_act')(x) x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x) x = BatchNormalization(name='block3_sepconv2_bn')(x) x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block3_pool')(x) x = layers.add([x, residual]) residual = Conv2D(728, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = BatchNormalization()(residual) x = Activation('relu', name='block4_sepconv1_act')(x) x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x) x = BatchNormalization(name='block4_sepconv1_bn')(x) x = Activation('relu', name='block4_sepconv2_act')(x) x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x) x = BatchNormalization(name='block4_sepconv2_bn')(x) x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block4_pool')(x) x = layers.add([x, residual]) for i in range(8): residual = x prefix = 'block' + str(i + 5) x = Activation('relu', name=prefix + '_sepconv1_act')(x) x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(x) x = BatchNormalization(name=prefix + '_sepconv1_bn')(x) x = Activation('relu', name=prefix + '_sepconv2_act')(x) x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(x) x = BatchNormalization(name=prefix + '_sepconv2_bn')(x) x = Activation('relu', name=prefix + '_sepconv3_act')(x) x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(x) x = BatchNormalization(name=prefix + '_sepconv3_bn')(x) x = layers.add([x, residual]) residual = Conv2D(1024, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = BatchNormalization()(residual) x = Activation('relu', name='block13_sepconv1_act')(x) x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x) x = BatchNormalization(name='block13_sepconv1_bn')(x) x = Activation('relu', name='block13_sepconv2_act')(x) x = SeparableConv2D(1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x) x = BatchNormalization(name='block13_sepconv2_bn')(x) x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block13_pool')(x) x = layers.add([x, residual]) x = SeparableConv2D(1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x) x = BatchNormalization(name='block14_sepconv1_bn')(x) x = Activation('relu', name='block14_sepconv1_act')(x) x = SeparableConv2D(2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x) x = BatchNormalization(name='block14_sepconv2_bn')(x) x = Activation('relu', name='block14_sepconv2_act')(x) if require_flatten: 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='xception') # load weights if weights == 'imagenet': if require_flatten: weights_path = get_file('xception_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('xception_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if old_data_format: K.set_image_data_format(old_data_format) 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, classifier_activation='softmax', **kwargs): """Instantiates the MobileNet architecture. Reference: - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications]( https://arxiv.org/abs/1704.04861) Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in the `tf.keras.backend.image_data_format()`. Note: each Keras Application expects a specific kind of input preprocessing. For MobileNet, call `tf.keras.applications.mobilenet.preprocess_input` on your inputs before passing them to the model. 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. Default to `None`. `input_shape` will be ignored if the `input_tensor` is provided. 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. Default to 1.0. depth_multiplier: Depth multiplier for depthwise convolution. This is called the resolution multiplier in the MobileNet paper. Default to 1.0. dropout: Dropout rate. Default to 0.001. include_top: Boolean, whether to include the fully-connected layer at the top of the network. Default to `True`. weights: One of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. Default to `imagenet`. input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. `input_tensor` is useful for sharing inputs between multiple different networks. Default to None. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` (default) means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: Optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Defaults to 1000. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ global layers if 'layers' in kwargs: layers = kwargs.pop('layers') else: layers = VersionAwareLayers() if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) if not (weights in {'imagenet', None} or file_io.file_exists_v2(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') # Determine proper input shape and default size. if input_shape is None: default_size = 224 else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [128, 160, 192, 224]: default_size = rows else: default_size = 224 input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if weights == 'imagenet': if depth_multiplier != 1: raise ValueError('If imagenet weights are being loaded, ' 'depth multiplier must be 1') if alpha not in [0.25, 0.50, 0.75, 1.0]: raise ValueError('If imagenet weights are being loaded, ' 'alpha can be one of' '`0.25`, `0.50`, `0.75` or `1.0` only.') if rows != cols or rows not in [128, 160, 192, 224]: rows = 224 logging.warning('`input_shape` is undefined or non-square, ' 'or `rows` is not in [128, 160, 192, 224]. ' 'Weights for input shape (224, 224) will be' ' loaded as the default.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = _conv_block(img_input, 32, alpha, strides=(2, 2)) x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1) x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, strides=(2, 2), block_id=2) x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3) x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, strides=(2, 2), block_id=4) x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, strides=(2, 2), block_id=6) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11) x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, strides=(2, 2), block_id=12) x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13) if include_top: if backend.image_data_format() == 'channels_first': shape = (int(1024 * alpha), 1, 1) else: shape = (1, 1, int(1024 * alpha)) x = layers.GlobalAveragePooling2D()(x) x = layers.Reshape(shape, name='reshape_1')(x) x = layers.Dropout(dropout, name='dropout')(x) x = layers.Conv2D(classes, (1, 1), padding='same', name='conv_preds')(x) x = layers.Reshape((classes, ), name='reshape_2')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Activation(activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='mobilenet_%0.2f_%s' % (alpha, rows)) # Load weights. if weights == 'imagenet': if alpha == 1.0: alpha_text = '1_0' elif alpha == 0.75: alpha_text = '7_5' elif alpha == 0.50: alpha_text = '5_0' else: alpha_text = '2_5' if include_top: model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows) weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file(model_name, weight_path, cache_subdir='models') else: model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows) weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file(model_name, weight_path, cache_subdir='models') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def Xception(input_shape=None): input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=299, min_size=71, data_format=backend.image_data_format(), require_flatten=True) img_input = layers.Input(shape=input_shape) channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1 x = layers.Conv2D(32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(img_input) x = layers.BatchNormalization(axis=channel_axis, name='block1_conv1_bn')(x) x = layers.Activation('relu', name='block1_conv1_act')(x) x = layers.Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block1_conv2_bn')(x) x = layers.Activation('relu', name='block1_conv2_act')(x) residual = layers.Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block2_sepconv1_bn')(x) x = layers.Activation('relu', name='block2_sepconv2_act')(x) x = layers.SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block2_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block2_pool')(x) x = layers.add([x, residual]) residual = layers.Conv2D(256, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block3_sepconv1_act')(x) x = layers.SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block3_sepconv1_bn')(x) x = layers.Activation('relu', name='block3_sepconv2_act')(x) x = layers.SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block3_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block3_pool')(x) x = layers.add([x, residual]) residual = layers.Conv2D(728, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block4_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block4_sepconv1_bn')(x) x = layers.Activation('relu', name='block4_sepconv2_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block4_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block4_pool')(x) x = layers.add([x, residual]) for i in range(8): residual = x prefix = 'block' + str(i + 5) x = layers.Activation('relu', name=prefix + '_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv1_bn')(x) x = layers.Activation('relu', name=prefix + '_sepconv2_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv2_bn')(x) x = layers.Activation('relu', name=prefix + '_sepconv3_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv3_bn')(x) x = layers.add([x, residual]) residual = layers.Conv2D(1024, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block13_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block13_sepconv1_bn')(x) x = layers.Activation('relu', name='block13_sepconv2_act')(x) x = layers.SeparableConv2D(1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block13_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block13_pool')(x) x = layers.add([x, residual]) x = layers.SeparableConv2D(1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block14_sepconv1_bn')(x) x = layers.Activation('relu', name='block14_sepconv1_act')(x) x = layers.SeparableConv2D(2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block14_sepconv2_bn')(x) x = layers.Activation('relu', name='block14_sepconv2_act')(x) x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation('softmax', None) x = layers.Dense(NUM_CLASSES, activation='softmax', name='predictions')(x) # Create model. model = training.Model(img_input, x, name='xception') return model
def MobileNetV2XNNPACK(input_shape=None, alpha=1.0, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): """Instantiates the MobileNetV2 architecture. Reference: - [MobileNetV2: Inverted Residuals and Linear Bottlenecks]( https://arxiv.org/abs/1801.04381) (CVPR 2018) Optionally loads weights pre-trained on ImageNet. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.mobilenet_v2.preprocess_input` for an example. Arguments: input_shape: Optional shape tuple, to be specified if you would like to use a model with an input image resolution that is not (224, 224, 3). It should have exactly 3 inputs channels (224, 224, 3). You can also omit this option if you would like to infer input_shape from an input_tensor. If you choose to include both input_tensor and input_shape then input_shape will be used if they match, if the shapes do not match then we will throw an error. E.g. `(160, 160, 3)` would be one valid value. alpha: Float between 0 and 1. controls the width of the network. This is known as the width multiplier in the MobileNetV2 paper, but the name is kept for consistency with `applications.MobileNetV1` model in Keras. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. include_top: Boolean, whether to include the fully-connected layer at the top of the network. Defaults to `True`. weights: String, one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: String, optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: Integer, optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. **kwargs: For backwards compatibility only. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape or invalid alpha, rows when weights='imagenet' ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ global layers if 'layers' in kwargs: layers = kwargs.pop('layers') else: layers = VersionAwareLayers() if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') # Determine proper input shape and default size. # If both input_shape and input_tensor are used, they should match if input_shape is not None and input_tensor is not None: try: is_input_t_tensor = backend.is_keras_tensor(input_tensor) except ValueError: try: is_input_t_tensor = backend.is_keras_tensor( layer_utils.get_source_inputs(input_tensor)) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is not type input_tensor') if is_input_t_tensor: if backend.image_data_format == 'channels_first': if backend.int_shape(input_tensor)[1] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: if backend.int_shape(input_tensor)[2] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: raise ValueError('input_tensor specified: ', input_tensor, 'is not a keras tensor') # If input_shape is None, infer shape from input_tensor if input_shape is None and input_tensor is not None: try: backend.is_keras_tensor(input_tensor) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is type: ', type(input_tensor), 'which is not a valid type') if input_shape is None and not backend.is_keras_tensor(input_tensor): default_size = 224 elif input_shape is None and backend.is_keras_tensor(input_tensor): if backend.image_data_format() == 'channels_first': rows = backend.int_shape(input_tensor)[2] cols = backend.int_shape(input_tensor)[3] else: rows = backend.int_shape(input_tensor)[1] cols = backend.int_shape(input_tensor)[2] if rows == cols and rows in [96, 128, 160, 192, 224]: default_size = rows else: default_size = 224 # If input_shape is None and no input_tensor elif input_shape is None: default_size = 224 # If input_shape is not None, assume default size else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [96, 128, 160, 192, 224]: default_size = rows else: default_size = 224 input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if weights == 'imagenet': if alpha not in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]: raise ValueError('If imagenet weights are being loaded, ' 'alpha can be one of `0.35`, `0.50`, `0.75`, ' '`1.0`, `1.3` or `1.4` only.') if rows != cols or rows not in [96, 128, 160, 192, 224]: rows = 224 logging.warning('`input_shape` is undefined or non-square, ' 'or `rows` is not in [96, 128, 160, 192, 224].' ' Weights for input shape (224, 224) will be' ' loaded as the default.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1 first_block_filters = _make_divisible(32 * alpha, 8) # x = layers.ZeroPadding2D( # padding=imagenet_utils.correct_pad(img_input, 3), # name='Conv1_pad')(img_input) x = img_input x = layers.Conv2D(first_block_filters, kernel_size=3, strides=(2, 2), padding='same', use_bias=False, name='Conv1')(x) x = layers.BatchNormalization(axis=channel_axis, epsilon=1e-3, momentum=0.999, name='bn_Conv1')(x) x = layers.ReLU(6., name='Conv1_relu')(x) x = _inverted_res_block(x, filters=16, alpha=alpha, stride=1, expansion=1, block_id=0) x = _inverted_res_block(x, filters=24, alpha=alpha, stride=2, expansion=6, block_id=1) x = _inverted_res_block(x, filters=24, alpha=alpha, stride=1, expansion=6, block_id=2) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=2, expansion=6, block_id=3) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=4) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=5) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=2, expansion=6, block_id=6) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=7) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=8) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=9) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=10) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=11) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=12) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=2, expansion=6, block_id=13) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=14) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=15) x = _inverted_res_block(x, filters=320, alpha=alpha, stride=1, expansion=6, block_id=16) # no alpha applied to last conv as stated in the paper: # if the width multiplier is greater than 1 we # increase the number of output channels if alpha > 1.0: last_block_filters = _make_divisible(1280 * alpha, 8) else: last_block_filters = 1280 x = layers.Conv2D(last_block_filters, kernel_size=1, use_bias=False, name='Conv_1')(x) x = layers.BatchNormalization(axis=channel_axis, epsilon=1e-3, momentum=0.999, name='Conv_1_bn')(x) x = layers.ReLU(6., name='out_relu')(x) if include_top: # Use XNNPACK compatible average pooling # x = layers.GlobalAveragePooling2D()(x) x = layers.AveragePooling2D(pool_size=(7, 7))(x) imagenet_utils.validate_activation(classifier_activation, weights) # x = layers.Dense(classes, activation=classifier_activation, # name='predictions')(x) # Implement the top dense layer as a convolution, so that we don't need to remove spatial dims x = layers.Conv2D(classes, kernel_size=1, name='predictions')(x) x = layers.Softmax()(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows)) # Load weights. if weights == 'imagenet': if include_top: model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + str(alpha) + '_' + str(rows) + '.h5') weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file(model_name, weight_path, cache_subdir='models') else: model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + str(alpha) + '_' + str(rows) + '_no_top' + '.h5') weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file(model_name, weight_path, cache_subdir='models') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def SmallResNet(stack_fn, preact, use_bias, model_name='resnet', include_top=True, input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 x = layers.Conv2D(64, 3, padding='same', use_bias=use_bias, name='conv1_conv')(img_input) if not preact: x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1_bn')(x) x = layers.Activation('relu', name='conv1_relu')(x) x = stack_fn(x) if preact: x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='post_bn')(x) x = layers.Activation('relu', name='post_relu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name=model_name) return model
def Xception( include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', ): """Instantiates the Xception architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Note that the default input image size for this model is 299x299. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.xception.preprocess_input` for an example. Arguments: include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(299, 299, 3)`. It should have exactly 3 inputs channels, and width and height should be no smaller than 71. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=299, min_size=71, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1 x = layers.Conv2D(32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(img_input) x = layers.BatchNormalization(axis=channel_axis, name='block1_conv1_bn')(x) x = layers.Activation('relu', name='block1_conv1_act')(x) x = layers.Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block1_conv2_bn')(x) x = layers.Activation('relu', name='block1_conv2_act')(x) residual = layers.Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block2_sepconv1_bn')(x) x = layers.Activation('relu', name='block2_sepconv2_act')(x) x = layers.SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block2_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block2_pool')(x) x = layers.add([x, residual]) residual = layers.Conv2D(256, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block3_sepconv1_act')(x) x = layers.SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block3_sepconv1_bn')(x) x = layers.Activation('relu', name='block3_sepconv2_act')(x) x = layers.SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block3_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block3_pool')(x) x = layers.add([x, residual]) residual = layers.Conv2D(728, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block4_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block4_sepconv1_bn')(x) x = layers.Activation('relu', name='block4_sepconv2_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block4_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block4_pool')(x) x = layers.add([x, residual]) for i in range(8): residual = x prefix = 'block' + str(i + 5) x = layers.Activation('relu', name=prefix + '_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv1_bn')(x) x = layers.Activation('relu', name=prefix + '_sepconv2_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv2_bn')(x) x = layers.Activation('relu', name=prefix + '_sepconv3_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(x) x = layers.BatchNormalization(axis=channel_axis, name=prefix + '_sepconv3_bn')(x) x = layers.add([x, residual]) residual = layers.Conv2D(1024, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x) residual = layers.BatchNormalization(axis=channel_axis)(residual) x = layers.Activation('relu', name='block13_sepconv1_act')(x) x = layers.SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block13_sepconv1_bn')(x) x = layers.Activation('relu', name='block13_sepconv2_act')(x) x = layers.SeparableConv2D(1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block13_sepconv2_bn')(x) x = layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block13_pool')(x) x = layers.add([x, residual]) x = layers.SeparableConv2D(1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x) x = layers.BatchNormalization(axis=channel_axis, name='block14_sepconv1_bn')(x) x = layers.Activation('relu', name='block14_sepconv1_act')(x) x = layers.SeparableConv2D(2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x) x = layers.BatchNormalization(axis=channel_axis, name='block14_sepconv2_bn')(x) x = layers.Activation('relu', name='block14_sepconv2_act')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='xception') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'xception_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models', file_hash='0a58e3b7378bc2990ea3b43d5981f1f6') else: weights_path = data_utils.get_file( 'xception_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='b0042744bf5b25fce3cb969f33bebb97') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def Darknet53(input_shape=None, input_tensor=None, include_top=False, weights='imagenet', pooling=None, classes=1000, classifier_activation='softmax', **kwargs): """Generate darknet53 model for Imagenet classification.""" 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=416, # multiple of 32 only min_size=28, data_format=K.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = Input(shape=input_shape) else: img_input = input_tensor x = darknet_body(img_input) if include_top: model_name = 'darknet53' x = AveragePooling2D(pool_size=(3, 3), strides=None, padding='same')(x) x = Conv2D( classes, (1, 1), padding='same', activation=classifier_activation)( x) else: model_name = 'darknet53_headless' if pooling == 'avg': x = GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = 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 = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name=model_name) # Load weights. if weights == 'imagenet': if include_top: url = 'https://segmind-data.s3.ap-south-1.amazonaws.com/edge/transfer-learning/classification/darknet53_weights.h5' # noqa: E501 else: url = 'https://segmind-data.s3.ap-south-1.amazonaws.com/edge/transfer-learning/classification/darknet53_notop_weights.h5' # noqa: E501 weights_file = get_file('darknet53_weights.h5', url) file_path = os.path.join(weights_file) model.load_weights(file_path) elif weights is not None: model.load_weights(weights) return model
def MobileNet(input_shape=None, alpha=1.0, depth_multiplier=1, dropout=1e-3, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): global layers if 'layers' in kwargs: layers = kwargs.pop('layers') else: layers = VersionAwareLayers() if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) 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') # Determine proper input shape and default size. if input_shape is None: default_size = 224 else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [128, 160, 192, 224]: default_size = rows else: default_size = 224 input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if weights == 'imagenet': if depth_multiplier != 1: raise ValueError('If imagenet weights are being loaded, ' 'depth multiplier must be 1') if alpha not in [0.25, 0.50, 0.75, 1.0]: raise ValueError('If imagenet weights are being loaded, ' 'alpha can be one of' '`0.25`, `0.50`, `0.75` or `1.0` only.') if rows != cols or rows not in [128, 160, 192, 224]: rows = 224 logging.warning('`input_shape` is undefined or non-square, ' 'or `rows` is not in [128, 160, 192, 224]. ' 'Weights for input shape (224, 224) will be' ' loaded as the default.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = _conv_block(img_input, 32, strides=(2, 2), block_id=0) x = _conv_block(x, 64, block_id=1) x = _conv_block(x, 128, strides=(2, 2), block_id=2) x = _conv_block(x, 128, block_id=3) x = _conv_block(x, 256, strides=(2, 2), block_id=4) x = _conv_block(x, 256, block_id=5) x = _conv_block(x, 512, strides=(2, 2), block_id=6) x = _conv_block(x, 512, block_id=7) x = _conv_block(x, 512, block_id=8) x = _conv_block(x, 512, block_id=9) x = _conv_block(x, 512, block_id=10) x = _conv_block(x, 512, block_id=11) x = _conv_block(x, 1024, strides=(2, 2), block_id=12) x = _conv_block(x, 1024, block_id=13) if include_top: if backend.image_data_format() == 'channels_first': shape = (int(1024 * alpha), 1, 1) else: shape = (1, 1, int(1024 * alpha)) x = layers.GlobalAveragePooling2D()(x) x = layers.Reshape(shape, name='reshape_1')(x) x = layers.Dropout(dropout, name='dropout')(x) x = layers.Conv2D(classes, (1, 1), padding='same', name='conv_preds')(x) x = layers.Reshape((classes, ), name='reshape_2')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Activation(activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='mobilenet_%0.2f_%s' % (alpha, rows)) # Load weights. if weights == 'imagenet': if alpha == 1.0: alpha_text = '1_0' elif alpha == 0.75: alpha_text = '7_5' elif alpha == 0.50: alpha_text = '5_0' else: alpha_text = '2_5' if include_top: model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows) weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file(model_name, weight_path, cache_subdir='models') else: model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows) weight_path = BASE_WEIGHT_PATH + model_name weights_path = data_utils.get_file(model_name, weight_path, cache_subdir='models') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def VGG19(require_flatten=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the VGG19 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. The data format convention used by the model is the one specified in your Keras config file. # Arguments require_flatten: whether to include the 3 fully-connected layers 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 `require_flatten` 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 `require_flatten` 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 `require_flatten` 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 require_flatten and classes != 1000: raise ValueError( 'If using `weights` as imagenet with `require_flatten`' ' as true, `classes` should be 1000') # 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=require_flatten) 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='block1_conv1')(img_input) x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x) x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv4')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv4')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv4')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if require_flatten: # Classification block x = Flatten(name='flatten')(x) x = Dense(4096, activation='relu', name='fc1')(x) x = Dense(4096, activation='relu', name='fc2')(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='vgg19') # load weights if weights == 'imagenet': if require_flatten: weights_path = get_file( 'vgg19_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'vgg19_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 require_flatten: 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.') return model
def InceptionV3(require_flatten=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the Inception v3 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. 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. Arguments: require_flatten: 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 `require_flatten` 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 `require_flatten` 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 `require_flatten` 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 require_flatten and classes != 1000: raise ValueError( 'If using `weights` as imagenet with `require_flatten`' ' 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=require_flatten) if input_tensor is None: img_input = Input(shape=input_shape) else: img_input = Input(tensor=input_tensor, shape=input_shape) 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') # 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') # 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') # 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') # 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') # 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' + str(5 + i)) # mixed 7: 17 x 17 x 768 branch1x1 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(branch7x7, 192, 1, 7) branch7x7 = conv2d_bn(branch7x7, 192, 7, 1) branch7x7dbl = conv2d_bn(x, 192, 1, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool], axis=channel_axis, name='mixed7') # mixed 8: 8 x 8 x 1280 branch3x3 = conv2d_bn(x, 192, 1, 1) branch3x3 = conv2d_bn(branch3x3, 320, 3, 3, strides=(2, 2), padding='valid') branch7x7x3 = conv2d_bn(x, 192, 1, 1) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid') branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x) x = layers.concatenate([branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8') # mixed 9: 8 x 8 x 2048 for i in range(2): branch1x1 = conv2d_bn(x, 320, 1, 1) branch3x3 = conv2d_bn(x, 384, 1, 1) branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3) branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1) branch3x3 = layers.concatenate([branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i)) branch3x3dbl = conv2d_bn(x, 448, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3) branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3) branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1) branch3x3dbl = layers.concatenate([branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis) branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate( [branch1x1, branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed' + str(9 + i)) if require_flatten: # 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='inception_v3') # load 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 require_flatten: weights_path = get_file( 'inception_v3_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', md5_hash='9a0d58056eeedaa3f26cb7ebd46da564') else: weights_path = get_file( 'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='bcbd6486424b2319ff4ef7d526e38f63') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def ResNet(stack_fn, preact, use_bias, model_name='resnet', include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', **kwargs): global layers if 'layers' in kwargs: layers = kwargs.pop('layers') else: layers = VersionAwareLayers() if kwargs: raise ValueError('Unknown argument(s): %s' % (kwargs, )) 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') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1 # x = layers.ZeroPadding2D( # padding=((3, 3), (3, 3)), name='conv1_pad')(img_input) x = layers.Conv2D(64, 3, strides=1, padding='SAME', use_bias=use_bias, kernel_initializer='glorot_normal', name='conv1_conv')(img_input) if not preact: x = layers.BatchNormalization(axis=bn_axis, epsilon=2.001e-5, momentum=0.9, name='conv1_bn')(x) x = layers.PReLU(shared_axes=[1, 2], alpha_initializer='glorot_normal', name='conv1_prelu')(x) # x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x) # x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x) x = stack_fn(x) if preact: x = layers.BatchNormalization(axis=bn_axis, epsilon=2.001e-5, momentum=0.9, name='post_bn')(x) x = layers.PReLU(shared_axes=[1, 2], alpha_initializer='glorot_normal', name='post_prelu')(x) if include_top: x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D(name='avg_pool')(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D(name='max_pool')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name=model_name) # Load weights. if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES): if include_top: file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5' file_hash = WEIGHTS_HASHES[model_name][0] else: file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5' file_hash = WEIGHTS_HASHES[model_name][1] weights_path = data_utils.get_file(file_name, BASE_WEIGHTS_PATH + file_name, cache_subdir='models', file_hash=file_hash) model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def NASNet(input_shape=None, penultimate_filters=4032, num_blocks=6, stem_block_filters=96, skip_reduction=True, filter_multiplier=2, include_top=True, weights=None, input_tensor=None, pooling=None, classes=1000, default_size=None, classifier_activation='softmax'): """Instantiates a NASNet model. Reference: - [Learning Transferable Architectures for Scalable Image Recognition]( https://arxiv.org/abs/1707.07012) (CVPR 2018) Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.nasnet.preprocess_input` for an example. Arguments: input_shape: Optional shape tuple, the input shape is by default `(331, 331, 3)` for NASNetLarge and `(224, 224, 3)` for NASNetMobile. It should have exactly 3 input channels, and width and height should be no smaller than 32. E.g. `(224, 224, 3)` would be one valid value. penultimate_filters: Number of filters in the penultimate layer. NASNet models use the notation `NASNet (N @ P)`, where: - N is the number of blocks - P is the number of penultimate filters num_blocks: Number of repeated blocks of the NASNet model. NASNet models use the notation `NASNet (N @ P)`, where: - N is the number of blocks - P is the number of penultimate filters stem_block_filters: Number of filters in the initial stem block skip_reduction: Whether to skip the reduction step at the tail end of the network. filter_multiplier: Controls the width of the network. - If `filter_multiplier` < 1.0, proportionally decreases the number of filters in each layer. - If `filter_multiplier` > 1.0, proportionally increases the number of filters in each layer. - If `filter_multiplier` = 1, default number of filters from the paper are used at each layer. include_top: Whether to include the fully-connected layer at the top of the network. weights: `None` (random initialization) or `imagenet` (ImageNet weights) input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: Optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. default_size: Specifies the default image size of the model classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: In case of invalid argument for `weights`, invalid input shape or invalid `penultimate_filters` value. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or file_io.file_exists_v2(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') if (isinstance(input_shape, tuple) and None in input_shape and weights == 'imagenet'): raise ValueError('When specifying the input shape of a NASNet' ' and loading `ImageNet` weights, ' 'the input_shape argument must be static ' '(no None entries). Got: `input_shape=' + str(input_shape) + '`.') if default_size is None: default_size = 331 # Determine proper input shape and default size. input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=default_size, min_size=32, data_format=backend.image_data_format(), require_flatten=True, weights=weights) if backend.image_data_format() != 'channels_last': logging.warning( 'The NASNet family of models is only available ' 'for the input data format "channels_last" ' '(width, height, channels). ' 'However your settings specify the default ' 'data format "channels_first" (channels, width, height).' ' You should set `image_data_format="channels_last"` ' 'in your Keras config located at ~/.keras/keras.json. ' 'The model being returned right now will expect inputs ' 'to follow the "channels_last" data format.') backend.set_image_data_format('channels_last') old_data_format = 'channels_first' else: old_data_format = None if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if penultimate_filters % (24 * (filter_multiplier**2)) != 0: raise ValueError( 'For NASNet-A models, the `penultimate_filters` must be a multiple ' 'of 24 * (`filter_multiplier` ** 2). Current value: %d' % penultimate_filters) channel_dim = 1 if backend.image_data_format() == 'channels_first' else -1 filters = penultimate_filters // 24 x = layers.Conv2D(stem_block_filters, (3, 3), strides=(2, 2), padding='valid', use_bias=False, name='stem_conv1', kernel_initializer='he_normal')(img_input) x = layers.BatchNormalization(axis=channel_dim, momentum=0.9997, epsilon=1e-3, name='stem_bn1')(x) p = None x, p = _reduction_a_cell(x, p, filters // (filter_multiplier**2), block_id='stem_1') x, p = _reduction_a_cell(x, p, filters // filter_multiplier, block_id='stem_2') for i in range(num_blocks): x, p = _normal_a_cell(x, p, filters, block_id='%d' % (i)) x, p0 = _reduction_a_cell(x, p, filters * filter_multiplier, block_id='reduce_%d' % (num_blocks)) p = p0 if not skip_reduction else p for i in range(num_blocks): x, p = _normal_a_cell(x, p, filters * filter_multiplier, block_id='%d' % (num_blocks + i + 1)) x, p0 = _reduction_a_cell(x, p, filters * filter_multiplier**2, block_id='reduce_%d' % (2 * num_blocks)) p = p0 if not skip_reduction else p for i in range(num_blocks): x, p = _normal_a_cell(x, p, filters * filter_multiplier**2, block_id='%d' % (2 * num_blocks + i + 1)) x = layers.Activation('relu')(x) if include_top: x = layers.GlobalAveragePooling2D()(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input model = training.Model(inputs, x, name='NASNet') # Load weights. if weights == 'imagenet': if default_size == 224: # mobile version if include_top: weights_path = data_utils.get_file( 'nasnet_mobile.h5', NASNET_MOBILE_WEIGHT_PATH, cache_subdir='models', file_hash='020fb642bf7360b370c678b08e0adf61') else: weights_path = data_utils.get_file( 'nasnet_mobile_no_top.h5', NASNET_MOBILE_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='1ed92395b5b598bdda52abe5c0dbfd63') model.load_weights(weights_path) elif default_size == 331: # large version if include_top: weights_path = data_utils.get_file( 'nasnet_large.h5', NASNET_LARGE_WEIGHT_PATH, cache_subdir='models', file_hash='11577c9a518f0070763c2b964a382f17') else: weights_path = data_utils.get_file( 'nasnet_large_no_top.h5', NASNET_LARGE_WEIGHT_PATH_NO_TOP, cache_subdir='models', file_hash='d81d89dc07e6e56530c4e77faddd61b5') model.load_weights(weights_path) else: raise ValueError( 'ImageNet weights can only be loaded with NASNetLarge' ' or NASNetMobile') elif weights is not None: model.load_weights(weights) if old_data_format: backend.set_image_data_format(old_data_format) return model
def InceptionV3( include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax', ): """Instantiates the Inception v3 architecture. Reference paper: - [Rethinking the Inception Architecture for Computer Vision]( http://arxiv.org/abs/1512.00567) (CVPR 2016) Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in the `tf.keras.backend.image_data_format()`. Caution: Be sure to properly pre-process your inputs to the application. Please see `applications.inception_v3.preprocess_input` for an example. Arguments: include_top: Boolean, whether to include the fully-connected layer at the top, as the last layer of the network. Default to `True`. weights: One of `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded. Default to `imagenet`. input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. `input_tensor` is useful for sharing inputs between multiple different networks. Default to None. input_shape: Optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(299, 299, 3)` (with `channels_last` data format) or `(3, 299, 299)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g. `(150, 150, 3)` would be one valid value. `input_shape` will be ignored if the `input_tensor` is provided. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` (default) means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Default to 1000. classifier_activation: A `str` or callable. The activation function to use on the "top" layer. Ignored unless `include_top=True`. Set `classifier_activation=None` to return the logits of the "top" layer. Returns: A `keras.Model` instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. ValueError: if `classifier_activation` is not `softmax` or `None` when using a pretrained top layer. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=299, min_size=75, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if backend.image_data_format() == 'channels_first': channel_axis = 1 else: channel_axis = 3 x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid') x = conv2d_bn(x, 32, 3, 3, padding='valid') x = conv2d_bn(x, 64, 3, 3) x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv2d_bn(x, 80, 1, 1, padding='valid') x = conv2d_bn(x, 192, 3, 3, padding='valid') x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) # mixed 0: 35 x 35 x 256 branch1x1 = conv2d_bn(x, 64, 1, 1) branch5x5 = conv2d_bn(x, 48, 1, 1) branch5x5 = conv2d_bn(branch5x5, 64, 5, 5) branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 32, 1, 1) x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed0') # mixed 1: 35 x 35 x 288 branch1x1 = conv2d_bn(x, 64, 1, 1) branch5x5 = conv2d_bn(x, 48, 1, 1) branch5x5 = conv2d_bn(branch5x5, 64, 5, 5) branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1, 1) x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed1') # mixed 2: 35 x 35 x 288 branch1x1 = conv2d_bn(x, 64, 1, 1) branch5x5 = conv2d_bn(x, 48, 1, 1) branch5x5 = conv2d_bn(branch5x5, 64, 5, 5) branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 64, 1, 1) x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed2') # mixed 3: 17 x 17 x 768 branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid') branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid') branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) x = layers.concatenate([branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3') # mixed 4: 17 x 17 x 768 branch1x1 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(x, 128, 1, 1) branch7x7 = conv2d_bn(branch7x7, 128, 1, 7) branch7x7 = conv2d_bn(branch7x7, 192, 7, 1) branch7x7dbl = conv2d_bn(x, 128, 1, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7) branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool], axis=channel_axis, name='mixed4') # mixed 5, 6: 17 x 17 x 768 for i in range(2): branch1x1 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(x, 160, 1, 1) branch7x7 = conv2d_bn(branch7x7, 160, 1, 7) branch7x7 = conv2d_bn(branch7x7, 192, 7, 1) branch7x7dbl = conv2d_bn(x, 160, 1, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7) branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate( [branch1x1, branch7x7, branch7x7dbl, branch_pool], axis=channel_axis, name='mixed' + str(5 + i)) # mixed 7: 17 x 17 x 768 branch1x1 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(x, 192, 1, 1) branch7x7 = conv2d_bn(branch7x7, 192, 1, 7) branch7x7 = conv2d_bn(branch7x7, 192, 7, 1) branch7x7dbl = conv2d_bn(x, 192, 1, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1) branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool], axis=channel_axis, name='mixed7') # mixed 8: 8 x 8 x 1280 branch3x3 = conv2d_bn(x, 192, 1, 1) branch3x3 = conv2d_bn(branch3x3, 320, 3, 3, strides=(2, 2), padding='valid') branch7x7x3 = conv2d_bn(x, 192, 1, 1) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1) branch7x7x3 = conv2d_bn(branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid') branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x) x = layers.concatenate([branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8') # mixed 9: 8 x 8 x 2048 for i in range(2): branch1x1 = conv2d_bn(x, 320, 1, 1) branch3x3 = conv2d_bn(x, 384, 1, 1) branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3) branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1) branch3x3 = layers.concatenate([branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i)) branch3x3dbl = conv2d_bn(x, 448, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3) branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3) branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1) branch3x3dbl = layers.concatenate([branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis) branch_pool = layers.AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = layers.concatenate( [branch1x1, branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed' + str(9 + i)) if include_top: # Classification block x = layers.GlobalAveragePooling2D(name='avg_pool')(x) imagenet_utils.validate_activation(classifier_activation, weights) x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='inception_v3') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'inception_v3_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', file_hash='9a0d58056eeedaa3f26cb7ebd46da564') else: weights_path = data_utils.get_file( 'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='bcbd6486424b2319ff4ef7d526e38f63') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def VGG16(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the VGG16 model. By default, it loads weights pre-trained on ImageNet. Check 'weights' for other options. This model can be built both with 'channels_first' data format (channels, height, width) or 'channels_last' data format (height, width, channels). The default input size for this model is 224x224. Arguments: include_top: whether to include the 3 fully-connected layers at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 input channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Returns: A Keras model instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = imagenet_utils.obtain_input_shape( input_shape, default_size=224, min_size=32, data_format=backend.image_data_format(), require_flatten=include_top, weights=weights) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input) x = layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x) x = layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x) x = layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x) x = layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x) x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # Classification block x = layers.Flatten(name='flatten')(x) x = layers.Dense(4096, activation='relu', name='fc1')(x) x = layers.Dense(4096, activation='relu', name='fc2')(x) x = layers.Dense(classes, activation='softmax', name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling2D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = layer_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = training.Model(inputs, x, name='vgg16') # Load weights. if weights == 'imagenet': if include_top: weights_path = data_utils.get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', file_hash='64373286793e3c8b2b4e3219cbf3544b') else: weights_path = data_utils.get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', file_hash='6d6bbae143d832006294945121d1f1fc') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def 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