def InceptionV3(include_top=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 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 139. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if 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=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 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 include_top: # Classification block x = GlobalAveragePooling2D(name='avg_pool')(x) x = Dense(classes, activation='softmax', name='predictions')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='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 include_top: weights_path = WEIGHTS_PATH else: weights_path = WEIGHTS_PATH_NO_TOP model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def SqueezeNet(input_tensor=None, input_shape=None, weights='imagenet', classes=1000): 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 classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') input_shape = _obtain_input_shape(input_shape, default_size=227, min_size=48, data_format=K.image_data_format(), require_flatten=True) 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 = Convolution2D(64, (3, 3), strides=(2, 2), padding='valid', name='conv1')(img_input) x = Activation('relu', name='relu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=16, expand=64) x = fire_module(x, fire_id=3, squeeze=16, expand=64) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool3')(x) x = fire_module(x, fire_id=4, squeeze=32, expand=128) x = fire_module(x, fire_id=5, squeeze=32, expand=128) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool5')(x) x = fire_module(x, fire_id=6, squeeze=48, expand=192) x = fire_module(x, fire_id=7, squeeze=48, expand=192) x = fire_module(x, fire_id=8, squeeze=64, expand=256) x = fire_module(x, fire_id=9, squeeze=64, expand=256) x = Dropout(0.5, name='drop9')(x) x = Convolution2D(classes, (1, 1), padding='valid', name='conv10')(x) x = Activation('relu', name='relu_conv10')(x) x = GlobalAveragePooling2D()(x) out = Activation('softmax', name='loss')(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 model = Model(inputs, out, name='squeezenet') # load weights if weights == 'imagenet': weights_path = get_file('squeezenet_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') model.load_weights(weights_path) 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.') return model
def SqueezeNet(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the SqueezeNet architecture. """ # 检查weight与分类设置是否正确 如果权重不再其中报错 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 classes != 1000: # raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') # 设置图像尺寸,类似caffe中的transform # Determine proper input shape input_shape = _obtain_input_shape( input_shape, default_size=227, min_size=48, # 模型所能接受的最小长宽 data_format=K.image_data_format(), # 数据的使用格式 require_flatten=include_top) # 是否通过一个Flatten层再连接到分类器 # 数据简单处理,resize if input_tensor is None: img_input = Input(shape=input_shape) #转为矩阵数据 # 这里的Input是keras的格式,可以用于转换 else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # 如果是tensor的数据格式,需要两步走: 先判断是否是keras指定的数据类型,is_keras_tensor # 然后get_source_inputs(input_tensor) # 编写网络结构,prototxt # Block 1 卷积 激活函数 池化 x = Convolution2D(64, (3, 3), strides=(2, 2), padding='valid', name='conv1')(img_input) #合理张量 x = Activation('relu', name='relu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) # Block 2 fire的 x = fire_module(x, fire_id=2, squeeze=16, expand=64) x = fire_module(x, fire_id=3, squeeze=16, expand=64) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool3')(x) # Block 3 x = fire_module(x, fire_id=4, squeeze=32, expand=128) x = fire_module(x, fire_id=5, squeeze=32, expand=128) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool5')(x) # Block 4 x = fire_module(x, fire_id=6, squeeze=48, expand=192) x = fire_module(x, fire_id=7, squeeze=48, expand=192) x = fire_module(x, fire_id=8, squeeze=64, expand=256) x = fire_module(x, fire_id=9, squeeze=64, expand=256) if include_top: # It's not obvious where to cut the network... # Could do the 8th or 9th layer... some work recommends cutting earlier layers. x = Dropout(0.5, name='drop9')(x) #dropout是指在深度学习网络的训练过程中,对于神经网络单元,按照一定的概率将其暂时从网络中丢弃 #好像dropout=0.8是每次随机80%的神经元失效 x = Convolution2D(classes, (1, 1), padding='valid', name='conv10')(x) #卷积 classes过滤器个数 x = Activation('relu', name='relu_conv10')(x) x = GlobalAveragePooling2D()(x) x = Activation('softmax', name='loss')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = GlobalMaxPooling2D()(x) elif pooling == None: pass else: raise ValueError("Unknown argument for 'pooling'=" + pooling) # 调整数据 # 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) # get_source_inputs 返回计算需要的数据列表,List of input tensors. # 如果是tensor的数据格式,需要两步走: # 先判断是否是keras指定的数据类型,is_keras_tensor # 然后get_source_inputs(input_tensor) else: inputs = img_input # 创建模型 # Create model. model = Model(inputs, x, name='squeezenet') # 加载权重 # load weights if weights == 'imagenet': if include_top: weights_path = get_file( 'squeezenet_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'squeezenet_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) # backend() 返回当前后端 Theano是一个Python库,专门用于定义、优化、求值数学表达 if K.backend() == 'theano': layer_utils.convert_all_kernels_in_model(model) 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.') return model
def ResNet50(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the ResNet50 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 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 197. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=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), strides=(2, 2), padding='same', name='conv1')(img_input) x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = Activation('relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b') x = identity_block(x, 3, [64, 64, 256], stage=2, block='c') x = conv_block(x, 3, [128, 128, 512], stage=3, block='a') x = identity_block(x, 3, [128, 128, 512], stage=3, block='b') x = identity_block(x, 3, [128, 128, 512], stage=3, block='c') x = identity_block(x, 3, [128, 128, 512], stage=3, block='d') x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f') x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c') x = AveragePooling2D((7, 7), name='avg_pool')(x) if include_top: x = Flatten()(x) x = Dense(classes, activation='softmax', name='fc1000')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='resnet50') # load weights if weights == 'imagenet': if include_top: weights_path = WEIGHTS_PATH else: weights_path = WEIGHTS_PATH_NO_TOP 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='fc1000') 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 Xception(include_top=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 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 layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. RuntimeError: If attempting to run this model with a backend that does not support separable convolutions. """ if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') 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=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 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 include_top: 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 include_top: weights_path = WEIGHTS_PATH else: weights_path = WEIGHTS_PATH_NO_TOP model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) if old_data_format: K.set_image_data_format(old_data_format) return model
def SqueezeNet(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000): """Instantiates the SqueezeNet architecture. """ 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 classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') print input_shape input_shape = _obtain_input_shape(input_shape, default_size=64, min_size=48, data_format=K.image_data_format(), include_top=True) #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 x = Convolution2D(64, (3, 3), strides=(2, 2), padding='valid', name='conv1')(img_input) x = Activation('relu', name='relu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=16, expand=64) x = fire_module(x, fire_id=3, squeeze=16, expand=64) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool3')(x) x = fire_module(x, fire_id=4, squeeze=32, expand=128) x = fire_module(x, fire_id=5, squeeze=32, expand=128) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool5')(x) x = fire_module(x, fire_id=6, squeeze=48, expand=192) x = fire_module(x, fire_id=7, squeeze=48, expand=192) x = fire_module(x, fire_id=8, squeeze=64, expand=256) x = fire_module(x, fire_id=9, squeeze=64, expand=256) if include_top: # It's not obvious where to cut the network... # Could do the 8th or 9th layer... some work recommends cutting earlier layers. x = Dropout(0.5, name='drop9')(x) x = Convolution2D(classes, (1, 1), padding='valid', name='conv10')(x) x = Activation('relu', name='relu_conv10')(x) x = GlobalAveragePooling2D()(x) x = Activation('softmax', name='loss')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = GlobalMaxPooling2D()(x) elif pooling == None: pass else: raise ValueError("Unknown argument for 'pooling'=" + pooling) # 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 model = Model(inputs, x, name='squeezenet') # load weights if weights == 'imagenet': if include_top: weights_path = get_file( 'squeezenet_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'squeezenet_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 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 SqueezeNet( input_tensor=None, input_shape=None, weights='imagenet', classes=1000, use_bn_on_input=False, # to avoid preprocessing first_stride=2, last_activation='softmax', load_by_name=False, sn_name=''): """ The implementation of SqueezeNet in Keras :param input_tensor: :param input_shape: :param weights: :param classes: :param use_bn_on_input: :param first_stride: :param last_activation: the activation of the last layer :param load_by_name: load the layers by name :return: >>> m = SqueezeNet(input_shape = (48, 48, 3), weights = 'imagenet') >>> m.summary() # doctest: +NORMALIZE_WHITESPACE ____________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ==================================================================================================== input_1 (InputLayer) (None, 48, 48, 3) 0 ____________________________________________________________________________________________________ conv1 (Conv2D) (None, 23, 23, 64) 1792 input_1[0][0] ____________________________________________________________________________________________________ relu_conv1 (Activation) (None, 23, 23, 64) 0 conv1[0][0] ____________________________________________________________________________________________________ pool1 (MaxPooling2D) (None, 11, 11, 64) 0 relu_conv1[0][0] ____________________________________________________________________________________________________ fire2/squeeze1x1 (Conv2D) (None, 11, 11, 16) 1040 pool1[0][0] ____________________________________________________________________________________________________ fire2/relu_squeeze1x1 (Activatio (None, 11, 11, 16) 0 fire2/squeeze1x1[0][0] ____________________________________________________________________________________________________ fire2/expand1x1 (Conv2D) (None, 11, 11, 64) 1088 fire2/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire2/expand3x3 (Conv2D) (None, 11, 11, 64) 9280 fire2/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire2/relu_expand1x1 (Activation (None, 11, 11, 64) 0 fire2/expand1x1[0][0] ____________________________________________________________________________________________________ fire2/relu_expand3x3 (Activation (None, 11, 11, 64) 0 fire2/expand3x3[0][0] ____________________________________________________________________________________________________ fire2/concat (Concatenate) (None, 11, 11, 128) 0 fire2/relu_expand1x1[0][0] fire2/relu_expand3x3[0][0] ____________________________________________________________________________________________________ fire3/squeeze1x1 (Conv2D) (None, 11, 11, 16) 2064 fire2/concat[0][0] ____________________________________________________________________________________________________ fire3/relu_squeeze1x1 (Activatio (None, 11, 11, 16) 0 fire3/squeeze1x1[0][0] ____________________________________________________________________________________________________ fire3/expand1x1 (Conv2D) (None, 11, 11, 64) 1088 fire3/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire3/expand3x3 (Conv2D) (None, 11, 11, 64) 9280 fire3/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire3/relu_expand1x1 (Activation (None, 11, 11, 64) 0 fire3/expand1x1[0][0] ____________________________________________________________________________________________________ fire3/relu_expand3x3 (Activation (None, 11, 11, 64) 0 fire3/expand3x3[0][0] ____________________________________________________________________________________________________ fire3/concat (Concatenate) (None, 11, 11, 128) 0 fire3/relu_expand1x1[0][0] fire3/relu_expand3x3[0][0] ____________________________________________________________________________________________________ pool3 (MaxPooling2D) (None, 5, 5, 128) 0 fire3/concat[0][0] ____________________________________________________________________________________________________ fire4/squeeze1x1 (Conv2D) (None, 5, 5, 32) 4128 pool3[0][0] ____________________________________________________________________________________________________ fire4/relu_squeeze1x1 (Activatio (None, 5, 5, 32) 0 fire4/squeeze1x1[0][0] ____________________________________________________________________________________________________ fire4/expand1x1 (Conv2D) (None, 5, 5, 128) 4224 fire4/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire4/expand3x3 (Conv2D) (None, 5, 5, 128) 36992 fire4/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire4/relu_expand1x1 (Activation (None, 5, 5, 128) 0 fire4/expand1x1[0][0] ____________________________________________________________________________________________________ fire4/relu_expand3x3 (Activation (None, 5, 5, 128) 0 fire4/expand3x3[0][0] ____________________________________________________________________________________________________ fire4/concat (Concatenate) (None, 5, 5, 256) 0 fire4/relu_expand1x1[0][0] fire4/relu_expand3x3[0][0] ____________________________________________________________________________________________________ fire5/squeeze1x1 (Conv2D) (None, 5, 5, 32) 8224 fire4/concat[0][0] ____________________________________________________________________________________________________ fire5/relu_squeeze1x1 (Activatio (None, 5, 5, 32) 0 fire5/squeeze1x1[0][0] ____________________________________________________________________________________________________ fire5/expand1x1 (Conv2D) (None, 5, 5, 128) 4224 fire5/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire5/expand3x3 (Conv2D) (None, 5, 5, 128) 36992 fire5/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire5/relu_expand1x1 (Activation (None, 5, 5, 128) 0 fire5/expand1x1[0][0] ____________________________________________________________________________________________________ fire5/relu_expand3x3 (Activation (None, 5, 5, 128) 0 fire5/expand3x3[0][0] ____________________________________________________________________________________________________ fire5/concat (Concatenate) (None, 5, 5, 256) 0 fire5/relu_expand1x1[0][0] fire5/relu_expand3x3[0][0] ____________________________________________________________________________________________________ pool5 (MaxPooling2D) (None, 2, 2, 256) 0 fire5/concat[0][0] ____________________________________________________________________________________________________ fire6/squeeze1x1 (Conv2D) (None, 2, 2, 48) 12336 pool5[0][0] ____________________________________________________________________________________________________ fire6/relu_squeeze1x1 (Activatio (None, 2, 2, 48) 0 fire6/squeeze1x1[0][0] ____________________________________________________________________________________________________ fire6/expand1x1 (Conv2D) (None, 2, 2, 192) 9408 fire6/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire6/expand3x3 (Conv2D) (None, 2, 2, 192) 83136 fire6/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire6/relu_expand1x1 (Activation (None, 2, 2, 192) 0 fire6/expand1x1[0][0] ____________________________________________________________________________________________________ fire6/relu_expand3x3 (Activation (None, 2, 2, 192) 0 fire6/expand3x3[0][0] ____________________________________________________________________________________________________ fire6/concat (Concatenate) (None, 2, 2, 384) 0 fire6/relu_expand1x1[0][0] fire6/relu_expand3x3[0][0] ____________________________________________________________________________________________________ fire7/squeeze1x1 (Conv2D) (None, 2, 2, 48) 18480 fire6/concat[0][0] ____________________________________________________________________________________________________ fire7/relu_squeeze1x1 (Activatio (None, 2, 2, 48) 0 fire7/squeeze1x1[0][0] ____________________________________________________________________________________________________ fire7/expand1x1 (Conv2D) (None, 2, 2, 192) 9408 fire7/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire7/expand3x3 (Conv2D) (None, 2, 2, 192) 83136 fire7/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire7/relu_expand1x1 (Activation (None, 2, 2, 192) 0 fire7/expand1x1[0][0] ____________________________________________________________________________________________________ fire7/relu_expand3x3 (Activation (None, 2, 2, 192) 0 fire7/expand3x3[0][0] ____________________________________________________________________________________________________ fire7/concat (Concatenate) (None, 2, 2, 384) 0 fire7/relu_expand1x1[0][0] fire7/relu_expand3x3[0][0] ____________________________________________________________________________________________________ fire8/squeeze1x1 (Conv2D) (None, 2, 2, 64) 24640 fire7/concat[0][0] ____________________________________________________________________________________________________ fire8/relu_squeeze1x1 (Activatio (None, 2, 2, 64) 0 fire8/squeeze1x1[0][0] ____________________________________________________________________________________________________ fire8/expand1x1 (Conv2D) (None, 2, 2, 256) 16640 fire8/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire8/expand3x3 (Conv2D) (None, 2, 2, 256) 147712 fire8/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire8/relu_expand1x1 (Activation (None, 2, 2, 256) 0 fire8/expand1x1[0][0] ____________________________________________________________________________________________________ fire8/relu_expand3x3 (Activation (None, 2, 2, 256) 0 fire8/expand3x3[0][0] ____________________________________________________________________________________________________ fire8/concat (Concatenate) (None, 2, 2, 512) 0 fire8/relu_expand1x1[0][0] fire8/relu_expand3x3[0][0] ____________________________________________________________________________________________________ fire9/squeeze1x1 (Conv2D) (None, 2, 2, 64) 32832 fire8/concat[0][0] ____________________________________________________________________________________________________ fire9/relu_squeeze1x1 (Activatio (None, 2, 2, 64) 0 fire9/squeeze1x1[0][0] ____________________________________________________________________________________________________ fire9/expand1x1 (Conv2D) (None, 2, 2, 256) 16640 fire9/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire9/expand3x3 (Conv2D) (None, 2, 2, 256) 147712 fire9/relu_squeeze1x1[0][0] ____________________________________________________________________________________________________ fire9/relu_expand1x1 (Activation (None, 2, 2, 256) 0 fire9/expand1x1[0][0] ____________________________________________________________________________________________________ fire9/relu_expand3x3 (Activation (None, 2, 2, 256) 0 fire9/expand3x3[0][0] ____________________________________________________________________________________________________ fire9/concat (Concatenate) (None, 2, 2, 512) 0 fire9/relu_expand1x1[0][0] fire9/relu_expand3x3[0][0] ____________________________________________________________________________________________________ drop9 (Dropout) (None, 2, 2, 512) 0 fire9/concat[0][0] ____________________________________________________________________________________________________ conv10 (Conv2D) (None, 2, 2, 1000) 513000 drop9[0][0] ____________________________________________________________________________________________________ relu_conv10 (Activation) (None, 2, 2, 1000) 0 conv10[0][0] ____________________________________________________________________________________________________ gap (GlobalAveragePooling2D) (None, 1000) 0 relu_conv10[0][0] ____________________________________________________________________________________________________ loss (Activation) (None, 1000) 0 gap[0][0] ==================================================================================================== Total params: 1,235,496 Trainable params: 1,235,496 Non-trainable params: 0 ____________________________________________________________________________________________________ """ 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 classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') input_shape = _obtain_input_shape(input_shape, default_size=227, min_size=48, data_format=K.image_data_format(), require_flatten=False) if input_tensor is None: raw_img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): raw_img_input = Input(tensor=input_tensor, shape=input_shape) else: raw_img_input = input_tensor if use_bn_on_input: img_input = BatchNormalization()(raw_img_input) else: img_input = raw_img_input x = Convolution2D(64, (3, 3), strides=(first_stride, first_stride), padding='valid', name='conv1{}'.format(sn_name))(img_input) x = Activation('relu', name='relu_conv1{}'.format(sn_name))(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1{}'.format(sn_name))(x) x = fire_module(x, fire_id=2, squeeze=16, expand=64, fire_name=sn_name) x = fire_module(x, fire_id=3, squeeze=16, expand=64, fire_name=sn_name) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool3{}'.format(sn_name))(x) x = fire_module(x, fire_id=4, squeeze=32, expand=128, fire_name=sn_name) x = fire_module(x, fire_id=5, squeeze=32, expand=128, fire_name=sn_name) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool5{}'.format(sn_name))(x) x = fire_module(x, fire_id=6, squeeze=48, expand=192, fire_name=sn_name) x = fire_module(x, fire_id=7, squeeze=48, expand=192, fire_name=sn_name) x = fire_module(x, fire_id=8, squeeze=64, expand=256, fire_name=sn_name) x = fire_module(x, fire_id=9, squeeze=64, expand=256, fire_name=sn_name) x = Dropout(0.5, name='drop9{}'.format(sn_name))(x) x = Convolution2D(classes, (1, 1), padding='valid', name='conv10{}'.format(sn_name))(x) x = Activation('relu', name='relu_conv10{}'.format(sn_name))(x) x = GlobalAveragePooling2D(name='gap{}'.format(sn_name))(x) out = Activation(last_activation, name='loss{}'.format(sn_name))(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 = raw_img_input model = Model(inputs, out, name='squeezenet{}'.format(sn_name)) # load weights if weights == 'imagenet': weights_path = get_file( 'squeezenet_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') model.load_weights(weights_path, by_name=load_by_name) if K.backend() == 'theano': layer_utils.convert_all_kernels_in_model(model) 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.') return model
def __init__(self, units, activation='tanh', recurrent_activation='hard_sigmoid', use_bias=True, kernel_initializer='glorot_uniform', recurrent_initializer='orthogonal', bias_initializer='zeros', kernel_regularizer=None, recurrent_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, recurrent_constraint=None, bias_constraint=None, dropout=0., recurrent_dropout=0., implementation=1, return_sequences=False, return_state=False, go_backwards=False, stateful=False, unroll=False, reset_after=False, **kwargs): if implementation == 0: warnings.warn('`implementation=0` has been deprecated, ' 'and now defaults to `implementation=1`.' 'Please update your layer call.') if K.backend() == 'theano' and (dropout or recurrent_dropout): warnings.warn( 'RNN dropout is no longer supported with the Theano backend ' 'due to technical limitations. ' 'You can either set `dropout` and `recurrent_dropout` to 0, ' 'or use the TensorFlow backend.') dropout = 0. recurrent_dropout = 0. cell = GRUCell(units, activation=activation, recurrent_activation=recurrent_activation, use_bias=use_bias, kernel_initializer=kernel_initializer, recurrent_initializer=recurrent_initializer, bias_initializer=bias_initializer, kernel_regularizer=kernel_regularizer, recurrent_regularizer=recurrent_regularizer, bias_regularizer=bias_regularizer, kernel_constraint=kernel_constraint, recurrent_constraint=recurrent_constraint, bias_constraint=bias_constraint, dropout=dropout, recurrent_dropout=recurrent_dropout, implementation=implementation, reset_after=reset_after) super(AttGRU, self).__init__(cell, return_sequences=return_sequences, return_state=return_state, go_backwards=go_backwards, stateful=stateful, unroll=unroll, **kwargs) self.activity_regularizer = regularizers.get(activity_regularizer)
def SqueezeNet(input_tensor=None, input_shape=None, weights='imagenet', classes=1000): 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 classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') input_shape = _obtain_input_shape(input_shape, default_size=227, min_size=48, data_format=K.image_data_format(), include_top=True) 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 = Convolution2D(64, (3, 3), strides=(2, 2), padding='valid', name='conv1')(img_input) x = Activation('relu', name='relu_conv1')(x) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x) x = fire_module(x, fire_id=2, squeeze=16, expand=64) x = fire_module(x, fire_id=3, squeeze=16, expand=64) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool3')(x) x = fire_module(x, fire_id=4, squeeze=32, expand=128) x = fire_module(x, fire_id=5, squeeze=32, expand=128) x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool5')(x) x = fire_module(x, fire_id=6, squeeze=48, expand=192) x = fire_module(x, fire_id=7, squeeze=48, expand=192) x = fire_module(x, fire_id=8, squeeze=64, expand=256) x = fire_module(x, fire_id=9, squeeze=64, expand=256) x = Dropout(0.5, name='drop9')(x) x = Convolution2D(classes, (1, 1), padding='valid', name='conv10')(x) x = Activation('relu', name='relu_conv10')(x) x = GlobalAveragePooling2D()(x) out = Activation('softmax', name='loss')(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 model = Model(inputs, out, name='squeezenet') # load weights if weights == 'imagenet': weights_path = get_file('squeezenet_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') model.load_weights(weights_path) 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.') return model