def get_base(self): """Gets base architecture of Resnet 50 Model""" input_shape = (3,) + self.size img_input = Input(shape=input_shape) bn_axis = 1 x = Lambda(preprocess)(img_input) x = ZeroPadding2D((3, 3))(x) x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x) x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = Activation('relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b') x = identity_block(x, 3, [64, 64, 256], stage=2, block='c') x = conv_block(x, 3, [128, 128, 512], stage=3, block='a') for n in ['b','c','d']: x = identity_block(x, 3, [128, 128, 512], stage=3, block=n) x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') for n in ['b','c','d', 'e', 'f']: x = identity_block(x, 3, [256, 256, 1024], stage=4, block=n) 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') self.img_input = img_input self.model = Model(self.img_input, x) convert_all_kernels_in_model(self.model) self.model.load_weights(self.weights_file)
def __init__(self, player1='none', player2='none', record=False): self.board = np.concatenate((np.zeros((15, 15, 2)), np.ones((15, 15, 1))), 2) self.history = (([], []), ([], [])) self.record = record self.judge_model = load_model('gobang/judge.h5') if K.backend() == 'theano': convert_all_kernels_in_model(self.judge_model) self.players = [player1,player2] self.cur_player = 0 self.empty = 15*15
def test_convert_weights(): def get_model(shape, data_format): model = Sequential() model.add(Conv2D(filters=2, kernel_size=(4, 3), input_shape=shape, data_format=data_format)) model.add(Flatten()) model.add(Dense(5)) return model for data_format in ['channels_first', 'channels_last']: if data_format == 'channels_first': shape = (3, 5, 5) target_shape = (5, 5, 3) prev_shape = (2, 3, 2) flip = lambda x: np.flip(np.flip(x, axis=2), axis=3) transpose = lambda x: np.transpose(x, (0, 2, 3, 1)) target_data_format = 'channels_last' elif data_format == 'channels_last': shape = (5, 5, 3) target_shape = (3, 5, 5) prev_shape = (2, 2, 3) flip = lambda x: np.flip(np.flip(x, axis=1), axis=2) transpose = lambda x: np.transpose(x, (0, 3, 1, 2)) target_data_format = 'channels_first' model1 = get_model(shape, data_format) model2 = get_model(target_shape, target_data_format) conv = K.function([model1.input], [model1.layers[0].output]) x = np.random.random((1,) + shape) # Test equivalence of convert_all_kernels_in_model convout1 = conv([x])[0] layer_utils.convert_all_kernels_in_model(model1) convout2 = flip(conv([flip(x)])[0]) assert_allclose(convout1, convout2, atol=1e-5) # Test equivalence of convert_dense_weights_data_format out1 = model1.predict(x) layer_utils.convert_dense_weights_data_format( model1.layers[2], prev_shape, target_data_format) for (src, dst) in zip(model1.layers, model2.layers): dst.set_weights(src.get_weights()) out2 = model2.predict(transpose(x)) assert_allclose(out1, out2, atol=1e-5)
def __init__(self, inputs, blocks, weights=None, trainable=True, name='encoder'): inverse_pyramid = [] # convolutional block conv_blocks = blocks[:-1] for i, block in enumerate(conv_blocks): if i == 0: x = block(inputs) inverse_pyramid.append(x) elif i < len(conv_blocks) - 1: x = block(x) inverse_pyramid.append(x) else: x = block(x) # fully convolutional block fc_block = blocks[-1] y = fc_block(x) inverse_pyramid.append(y) outputs = list(reversed(inverse_pyramid)) super(Encoder, self).__init__( inputs=inputs, outputs=outputs) # load pre-trained weights if weights is not None: weights_path = get_file( '{}_weights_tf_dim_ordering_tf_kernels.h5'.format(name), weights, cache_subdir='models') layer_names = load_weights(self, weights_path) if K.image_data_format() == 'channels_first': layer_utils.convert_all_kernels_in_model(self) # Freezing basenet weights if trainable is False: for layer in self.layers: if layer.name in layer_names: layer.trainable = False
def create(self, size, include_top): input_shape = (3,)+size img_input = Input(shape=input_shape) bn_axis = 1 x = Lambda(self.vgg_preprocess)(img_input) x = ZeroPadding2D((3, 3))(x) x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x) x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = Activation('relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b') x = identity_block(x, 3, [64, 64, 256], stage=2, block='c') x = conv_block(x, 3, [128, 128, 512], stage=3, block='a') for n in ['b','c','d']: x = identity_block(x, 3, [128, 128, 512], stage=3, block=n) x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') for n in ['b','c','d', 'e', 'f']: x = identity_block(x, 3, [256, 256, 1024], stage=4, block=n) 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') if include_top: x = AveragePooling2D((7, 7), name='avg_pool')(x) x = Flatten()(x) x = Dense(1000, activation='softmax', name='fc1000')(x) fname = 'resnet50.h5' else: fname = 'resnet_nt.h5' self.img_input = img_input self.model = Model(self.img_input, x) convert_all_kernels_in_model(self.model) self.model.load_weights(get_file(fname, self.FILE_PATH+fname, cache_subdir='models'))
def VGG16(include_top=True, weights='vggface', input_tensor=None, input_shape=None, pooling=None, classes=2622): input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=48, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_1')( img_input) x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool1')(x) # Block 2 x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_1')( x) x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_2')( x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool2')(x) # Block 3 x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_1')( x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_2')( x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_3')( x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool3')(x) # Block 4 x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_1')( x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_2')( x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_3')( x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool4')(x) # Block 5 x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_1')( x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_2')( x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_3')( x) x = MaxPooling2D((2, 2), strides=(2, 2), name='pool5')(x) if include_top: # Classification block x = Flatten(name='flatten')(x) x = Dense(4096, name='fc6')(x) x = Activation('relu', name='fc6/relu')(x) x = Dense(4096, name='fc7')(x) x = Activation('relu', name='fc7/relu')(x) x = Dense(classes, name='fc8')(x) x = Activation('softmax', name='fc8/softmax')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='vggface_vgg16') # load weights if weights == 'vggface': if include_top: weights_path = get_file('rcmalli_vggface_tf_vgg16.h5', utils. VGG16_WEIGHTS_PATH, cache_subdir=utils.VGGFACE_DIR) else: weights_path = get_file('rcmalli_vggface_tf_notop_vgg16.h5', utils.VGG16_WEIGHTS_PATH_NO_TOP, cache_subdir=utils.VGGFACE_DIR) model.load_weights(weights_path, by_name=True) if K.backend() == 'theano': layer_utils.convert_all_kernels_in_model(model) if K.image_data_format() == 'channels_first': if include_top: maxpool = model.get_layer(name='pool5') shape = maxpool.output_shape[1:] dense = model.get_layer(name='fc6') layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first') if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image data format convention ' '(`image_data_format="channels_first"`). ' 'For best performance, set ' '`image_data_format="channels_last"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') return model
def 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) or "imagenet" (pre-training on ImageNet). input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 244)` (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 weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=197, data_format=K.image_data_format(), include_top=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor if K.image_data_format() == 'channels_last': bn_axis = 3 else: bn_axis = 1 x = ZeroPadding2D((3, 3))(img_input) x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x) x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = Activation('relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b') x = identity_block(x, 3, [64, 64, 256], stage=2, block='c') x = conv_block(x, 3, [128, 128, 512], stage=3, block='a') x = identity_block(x, 3, [128, 128, 512], stage=3, block='b') x = identity_block(x, 3, [128, 128, 512], stage=3, block='c') x = identity_block(x, 3, [128, 128, 512], stage=3, block='d') x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f') x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c') x = AveragePooling2D((7, 7), name='avg_pool')(x) if include_top: x = Flatten()(x) x = Dense(classes, activation='softmax', name='fc1000')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D()(x) elif pooling == 'max': x = GlobalMaxPooling2D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='resnet50') # load weights if weights == 'imagenet': if include_top: weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', md5_hash='a7b3fe01876f51b976af0dea6bc144eb') else: weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='a268eb855778b3df3c7506639542a6af') model.load_weights(weights_path) 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='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.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 SparseNet(input_shape=None, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1, nb_layers_per_block=-1, bottleneck=False, reduction=0.0, dropout_rate=0.0, weight_decay=1e-4, subsample_initial_block=False, include_top=True, weights=None, input_tensor=None, classes=10, activation='softmax'): '''Instantiate the SparseNet architecture, optionally loading weights pre-trained on CIFAR-10. 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 dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(32, 32, 3)` (with `channels_last` dim ordering) or `(3, 32, 32)` (with `channels_first` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. E.g. `(200, 200, 3)` would be one valid value. depth: number or layers in the DenseNet nb_dense_block: number of dense blocks to add to end (generally = 3) growth_rate: number of filters to add per dense block. Can be a single integer number or a list of numbers. If it is a list, length of list must match the length of `nb_layers_per_block` nb_filter: initial number of filters. -1 indicates initial number of filters is 2 * growth_rate nb_layers_per_block: number of layers in each dense block. Can be a -1, positive integer or a list. If -1, calculates nb_layer_per_block from the network depth. If positive integer, a set number of layers per dense block. If list, nb_layer is used as provided. Note that list size must be (nb_dense_block + 1) bottleneck: flag to add bottleneck blocks in between dense blocks reduction: reduction factor of transition blocks. Note : reduction value is inverted to compute compression. dropout_rate: dropout rate weight_decay: weight decay rate subsample_initial_block: Set to True to subsample the initial convolution and add a MaxPool2D before the dense blocks are added. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or 'imagenet' (pre-training on ImageNet).. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'. Note that if sigmoid is used, classes must be 1. # Returns A Keras model instance. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `cifar10` ' '(pre-training on CIFAR-10).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as ImageNet with `include_top`' ' as true, `classes` should be 1000') if activation not in ['softmax', 'sigmoid']: raise ValueError('activation must be one of "softmax" or "sigmoid"') if activation == 'sigmoid' and classes != 1: raise ValueError('sigmoid activation can only be used when classes = 1') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = _create_dense_net(classes, img_input, include_top, depth, nb_dense_block, growth_rate, nb_filter, nb_layers_per_block, bottleneck, reduction, dropout_rate, weight_decay, subsample_initial_block, activation) # Ensure that the 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='densenet') # load weights if weights == 'imagenet': weights_loaded = False if weights_loaded: if K.backend() == 'theano': convert_all_kernels_in_model(model) 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.') print("Weights for the model were loaded successfully") return model
def ResNet50(include_top=True, weights='imagenet', input_tensor=None, bn_mode = 0): '''Instantiate the ResNet50 architecture, optionally loading weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments include_top: 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. xput of `layers.Input()`) to use as image input for the model. bn_mode: default 0, the mode for BatchNormalization # Returns A Keras model instance. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') # Determine proper input shape if K.image_dim_ordering() == 'th': if include_top: input_shape = (3, 224, 224) else: input_shape = (3, None, None) else: if include_top: input_shape = (224, 224, 3) else: input_shape = (None, None, 3) 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) else: img_input = input_tensor if K.image_dim_ordering() == 'tf': bn_axis = 3 else: bn_axis = 1 x = ZeroPadding2D((3, 3))(img_input) x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x) x = BatchNormalization(axis=bn_axis, name='bn_conv1', mode=bn_mode)(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), bn_mode=bn_mode) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', bn_mode=bn_mode) x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', bn_mode=bn_mode) x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', bn_mode=bn_mode) x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', bn_mode=bn_mode) x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', bn_mode=bn_mode) x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', bn_mode=bn_mode) x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', bn_mode=bn_mode) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b', bn_mode=bn_mode) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c', bn_mode=bn_mode) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d', bn_mode=bn_mode) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e', bn_mode=bn_mode) x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f', bn_mode=bn_mode) x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', bn_mode=bn_mode) x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', bn_mode=bn_mode) x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', bn_mode=bn_mode) x = AveragePooling2D((7, 7), name='avg_pool')(x) if include_top: x = Flatten()(x) x = Dense(1000, activation='softmax', name='fc1000')(x) model = Model(img_input, x) # load weights if weights == 'imagenet': print('K.image_dim_ordering:', K.image_dim_ordering()) if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file('resnet50_weights_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models', md5_hash='1c1f8f5b0c8ee28fe9d950625a230e1c') else: weights_path = get_file('resnet50_weights_th_dim_ordering_th_kernels_notop.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='f64f049c92468c9affcd44b0976cdafe') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models', md5_hash='a7b3fe01876f51b976af0dea6bc144eb') else: weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='a268eb855778b3df3c7506639542a6af') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def VGG16(include_top=True, weights='imagenet', input_tensor=None): '''Instantiate the VGG16 architecture, optionally loading weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments include_top: 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. # Returns A Keras model instance. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') # Determine proper input shape if K.image_dim_ordering() == 'th': if include_top: input_shape = (3, 224, 224) else: input_shape = (3, None, None) else: if include_top: input_shape = (224, 224, 3) else: input_shape = (None, None, 3) 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) else: img_input = input_tensor # Block 1 x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input) x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv1')(x) x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv1')(x) x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv2')(x) x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv3')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv1')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv2')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv3')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv1')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv2')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv3')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # 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(1000, activation='softmax', name='predictions')(x) # Create model model = Model(img_input, x) # load weights if weights == 'imagenet': print('K.image_dim_ordering:', K.image_dim_ordering()) if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file( 'vgg16_weights_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'vgg16_weights_th_dim_ordering_th_kernels_notop.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) #model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=["accuracy"]) # inputs = [K.learning_phase()] + model.inputs # _convout1_f = K.function(inputs, [model.layers[19].output]) # def convout1_f(X): # # The [0] is to disable the training phase flag # return _convout1_f([0] + [X]) # #convout1_f = theano.function([model.inputs(train=False)], f2.get_output(train=False)) # i = 4600 # img_path = 'images_vgg16/_537_5867.jpeg' # img = image.load_img(img_path, target_size=(224, 224)) # x1 = image.img_to_array(img) # x1 = np.expand_dims(x1, axis=0) # x1 = preprocess_input(x1) # #print 'Input image shape:', x1.shape # # Visualize the first layer of convolutions on an input image # C1 = convout1_f(x1) # print(np.shape(C1)) # #print np.shape(C1) # C1 = np.squeeze(C1) # print(np.shape(C1)) #print "C1 shape : ", C1.shape return model
def ResNet50(include_top=True, weights='imagenet', input_tensor=None): '''Instantiate the ResNet50 architecture, optionally loading weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments include_top: 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. xput of `layers.Input()`) to use as image input for the model. # Returns A Keras model instance. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') # Determine proper input shape if K.image_dim_ordering() == 'th': if include_top: input_shape = (3, 224, 224) else: input_shape = (3, None, None) else: if include_top: input_shape = (224, 224, 3) else: input_shape = (None, None, 3) 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) else: img_input = input_tensor if K.image_dim_ordering() == 'tf': bn_axis = 3 else: bn_axis = 1 x = ZeroPadding2D((3, 3))(img_input) x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x) x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x) x = Activation('relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1)) x = identity_block(x, 3, [64, 64, 256], stage=2, block='b') x = identity_block(x, 3, [64, 64, 256], stage=2, block='c') x = conv_block(x, 3, [128, 128, 512], stage=3, block='a') x = identity_block(x, 3, [128, 128, 512], stage=3, block='b') x = identity_block(x, 3, [128, 128, 512], stage=3, block='c') x = identity_block(x, 3, [128, 128, 512], stage=3, block='d') x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e') x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f') x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b') x = 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(1000, activation='softmax', name='fc1000')(x) model = Model(img_input, x) # load weights if weights == 'imagenet': print('K.image_dim_ordering:', K.image_dim_ordering()) if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file( 'resnet50_weights_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models', md5_hash='1c1f8f5b0c8ee28fe9d950625a230e1c') else: weights_path = get_file( 'resnet50_weights_th_dim_ordering_th_kernels_notop.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='f64f049c92468c9affcd44b0976cdafe') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file( 'resnet50_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models', md5_hash='a7b3fe01876f51b976af0dea6bc144eb') else: weights_path = get_file( 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='a268eb855778b3df3c7506639542a6af') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def Inception_Inflated3d(include_top=True, weights=None, input_tensor=None, input_shape=None, dropout_prob=0.0, endpoint_logit=True, classes=4): """Instantiates the Inflated 3D Inception v1 architecture. Optionally loads weights pre-trained on Kinetics. 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 frame(image) size for this model is 224x224. # Arguments include_top: whether to include the the classification layer at the top of the network. weights: one of `None` (random initialization) or 'kinetics_only' (pre-training on Kinetics dataset only). or 'imagenet_and_kinetics' (pre-training on ImageNet and Kinetics datasets). 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 `(NUM_FRAMES, 224, 224, 3)` (with `channels_last` data format) or `(NUM_FRAMES, 3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels. NUM_FRAMES should be no smaller than 8. The authors used 64 frames per example for training and testing on kinetics dataset Also, Width and height should be no smaller than 32. E.g. `(64, 150, 150, 3)` would be one valid value. dropout_prob: optional, dropout probability applied in dropout layer after global average pooling layer. 0.0 means no dropout is applied, 1.0 means dropout is applied to all features. Note: Since Dropout is applied just before the classification layer, it is only useful when `include_top` is set to True. endpoint_logit: (boolean) optional. If True, the model's forward pass will end at producing logits. Otherwise, softmax is applied after producing the logits to produce the class probabilities prediction. Setting this parameter to True is particularly useful when you want to combine results of rgb model and optical flow model. - `True` end model forward pass at logit output - `False` go further after logit to produce softmax predictions Note: This parameter is only useful when `include_top` is set to True. 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 WEIGHTS_NAME or weights is None or os.path.exists(weights)): raise ValueError( 'The `weights` argument should be either ' '`None` (random initialization) or %s' % str(WEIGHTS_NAME) + ' ' 'or a valid path to a file containing `weights` values') if weights in WEIGHTS_NAME and include_top and classes != 400: raise ValueError( 'If using `weights` as one of these %s, with `include_top`' ' as true, `classes` should be 400' % str(WEIGHTS_NAME)) # Determine proper input shape # input_shape = _obtain_input_shape( # input_shape, # default_frame_size=512, # # default_frame_size=224, # min_frame_size=512, # # default_num_frames=64, # default_num_frames=32, # min_num_frames=8, # 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_first': channel_axis = 1 else: channel_axis = 4 img_input = input_shape # Downsampling via convolution (spatial and temporal) x = conv3d_bn(img_input, 64, 7, 7, 7, strides=(2, 2, 2), padding='same', name='Conv3d_1a_7x7') # Downsampling (spatial only) x = MaxPooling3D((1, 3, 3), strides=(1, 2, 2), padding='same', name='MaxPool2d_2a_3x3')(x) x = conv3d_bn(x, 64, 1, 1, 1, strides=(1, 1, 1), padding='same', name='Conv3d_2b_1x1') x = conv3d_bn(x, 192, 3, 3, 3, strides=(1, 1, 1), padding='same', name='Conv3d_2c_3x3') # Downsampling (spatial only) x = MaxPooling3D((1, 3, 3), strides=(1, 2, 2), padding='same', name='MaxPool2d_3a_3x3')(x) # Mixed 3b branch_0 = conv3d_bn(x, 64, 1, 1, 1, padding='same', name='Conv3d_3b_0a_1x1') branch_1 = conv3d_bn(x, 96, 1, 1, 1, padding='same', name='Conv3d_3b_1a_1x1') branch_1 = conv3d_bn(branch_1, 128, 3, 3, 3, padding='same', name='Conv3d_3b_1b_3x3') branch_2 = conv3d_bn(x, 16, 1, 1, 1, padding='same', name='Conv3d_3b_2a_1x1') branch_2 = conv3d_bn(branch_2, 32, 3, 3, 3, padding='same', name='Conv3d_3b_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_3b_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 32, 1, 1, 1, padding='same', name='Conv3d_3b_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_3b') # Mixed 3c branch_0 = conv3d_bn(x, 128, 1, 1, 1, padding='same', name='Conv3d_3c_0a_1x1') branch_1 = conv3d_bn(x, 128, 1, 1, 1, padding='same', name='Conv3d_3c_1a_1x1') branch_1 = conv3d_bn(branch_1, 192, 3, 3, 3, padding='same', name='Conv3d_3c_1b_3x3') branch_2 = conv3d_bn(x, 32, 1, 1, 1, padding='same', name='Conv3d_3c_2a_1x1') branch_2 = conv3d_bn(branch_2, 96, 3, 3, 3, padding='same', name='Conv3d_3c_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_3c_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 64, 1, 1, 1, padding='same', name='Conv3d_3c_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_3c') # Downsampling (spatial and temporal) x = MaxPooling3D((3, 3, 3), strides=(2, 2, 2), padding='same', name='MaxPool2d_4a_3x3')(x) # Mixed 4b branch_0 = conv3d_bn(x, 192, 1, 1, 1, padding='same', name='Conv3d_4b_0a_1x1') branch_1 = conv3d_bn(x, 96, 1, 1, 1, padding='same', name='Conv3d_4b_1a_1x1') branch_1 = conv3d_bn(branch_1, 208, 3, 3, 3, padding='same', name='Conv3d_4b_1b_3x3') branch_2 = conv3d_bn(x, 16, 1, 1, 1, padding='same', name='Conv3d_4b_2a_1x1') branch_2 = conv3d_bn(branch_2, 48, 3, 3, 3, padding='same', name='Conv3d_4b_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_4b_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 64, 1, 1, 1, padding='same', name='Conv3d_4b_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_4b') # Mixed 4c branch_0 = conv3d_bn(x, 160, 1, 1, 1, padding='same', name='Conv3d_4c_0a_1x1') branch_1 = conv3d_bn(x, 112, 1, 1, 1, padding='same', name='Conv3d_4c_1a_1x1') branch_1 = conv3d_bn(branch_1, 224, 3, 3, 3, padding='same', name='Conv3d_4c_1b_3x3') branch_2 = conv3d_bn(x, 24, 1, 1, 1, padding='same', name='Conv3d_4c_2a_1x1') branch_2 = conv3d_bn(branch_2, 64, 3, 3, 3, padding='same', name='Conv3d_4c_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_4c_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 64, 1, 1, 1, padding='same', name='Conv3d_4c_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_4c') # Mixed 4d branch_0 = conv3d_bn(x, 128, 1, 1, 1, padding='same', name='Conv3d_4d_0a_1x1') branch_1 = conv3d_bn(x, 128, 1, 1, 1, padding='same', name='Conv3d_4d_1a_1x1') branch_1 = conv3d_bn(branch_1, 256, 3, 3, 3, padding='same', name='Conv3d_4d_1b_3x3') branch_2 = conv3d_bn(x, 24, 1, 1, 1, padding='same', name='Conv3d_4d_2a_1x1') branch_2 = conv3d_bn(branch_2, 64, 3, 3, 3, padding='same', name='Conv3d_4d_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_4d_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 64, 1, 1, 1, padding='same', name='Conv3d_4d_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_4d') # Mixed 4e branch_0 = conv3d_bn(x, 112, 1, 1, 1, padding='same', name='Conv3d_4e_0a_1x1') branch_1 = conv3d_bn(x, 144, 1, 1, 1, padding='same', name='Conv3d_4e_1a_1x1') branch_1 = conv3d_bn(branch_1, 288, 3, 3, 3, padding='same', name='Conv3d_4e_1b_3x3') branch_2 = conv3d_bn(x, 32, 1, 1, 1, padding='same', name='Conv3d_4e_2a_1x1') branch_2 = conv3d_bn(branch_2, 64, 3, 3, 3, padding='same', name='Conv3d_4e_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_4e_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 64, 1, 1, 1, padding='same', name='Conv3d_4e_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_4e') # Mixed 4f branch_0 = conv3d_bn(x, 256, 1, 1, 1, padding='same', name='Conv3d_4f_0a_1x1') branch_1 = conv3d_bn(x, 160, 1, 1, 1, padding='same', name='Conv3d_4f_1a_1x1') branch_1 = conv3d_bn(branch_1, 320, 3, 3, 3, padding='same', name='Conv3d_4f_1b_3x3') branch_2 = conv3d_bn(x, 32, 1, 1, 1, padding='same', name='Conv3d_4f_2a_1x1') branch_2 = conv3d_bn(branch_2, 128, 3, 3, 3, padding='same', name='Conv3d_4f_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_4f_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 128, 1, 1, 1, padding='same', name='Conv3d_4f_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_4f') # Downsampling (spatial and temporal) x = MaxPooling3D((2, 2, 2), strides=(2, 2, 2), padding='same', name='MaxPool2d_5a_2x2')(x) # Mixed 5b branch_0 = conv3d_bn(x, 256, 1, 1, 1, padding='same', name='Conv3d_5b_0a_1x1') branch_1 = conv3d_bn(x, 160, 1, 1, 1, padding='same', name='Conv3d_5b_1a_1x1') branch_1 = conv3d_bn(branch_1, 320, 3, 3, 3, padding='same', name='Conv3d_5b_1b_3x3') branch_2 = conv3d_bn(x, 32, 1, 1, 1, padding='same', name='Conv3d_5b_2a_1x1') branch_2 = conv3d_bn(branch_2, 128, 3, 3, 3, padding='same', name='Conv3d_5b_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_5b_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 128, 1, 1, 1, padding='same', name='Conv3d_5b_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_5b') # Mixed 5c branch_0 = conv3d_bn(x, 384, 1, 1, 1, padding='same', name='Conv3d_5c_0a_1x1') branch_1 = conv3d_bn(x, 192, 1, 1, 1, padding='same', name='Conv3d_5c_1a_1x1') branch_1 = conv3d_bn(branch_1, 384, 3, 3, 3, padding='same', name='Conv3d_5c_1b_3x3') branch_2 = conv3d_bn(x, 48, 1, 1, 1, padding='same', name='Conv3d_5c_2a_1x1') branch_2 = conv3d_bn(branch_2, 128, 3, 3, 3, padding='same', name='Conv3d_5c_2b_3x3') branch_3 = MaxPooling3D((3, 3, 3), strides=(1, 1, 1), padding='same', name='MaxPool2d_5c_3a_3x3')(x) branch_3 = conv3d_bn(branch_3, 128, 1, 1, 1, padding='same', name='Conv3d_5c_3b_1x1') x = layers.concatenate([branch_0, branch_1, branch_2, branch_3], axis=channel_axis, name='Mixed_5c') if include_top: # Classification block x = AveragePooling3D((2, 7, 7), strides=(1, 1, 1), padding='valid', name='global_avg_pool')(x) x = Dropout(dropout_prob)(x) x = conv3d_bn(x, classes, 1, 1, 1, padding='same', use_bias=True, use_activation_fn=False, use_bn=False, name='Conv3d_6a_1x1') num_frames_remaining = int(x.shape[1]) x = Reshape((num_frames_remaining, classes))(x) # logits (raw scores for each class) x = Lambda(lambda x: K.mean(x, axis=1, keepdims=False), output_shape=lambda s: (s[0], s[2]))(x) if not endpoint_logit: x = Activation('softmax', name='prediction')(x) else: h = int(x.shape[2]) w = int(x.shape[3]) # x = AveragePooling3D((2, h, w), strides=(1, 1, 1), padding='valid', name='global_avg_pool')(x) inputs = img_input # create model model = Model(inputs, x, name='i3d_inception') # load weights if weights in WEIGHTS_NAME: if weights == WEIGHTS_NAME[0]: # rgb_kinetics_only if include_top: weights_url = WEIGHTS_PATH['rgb_kinetics_only'] model_name = 'i3d_inception_rgb_kinetics_only.h5' else: weights_url = WEIGHTS_PATH_NO_TOP['rgb_kinetics_only'] model_name = 'i3d_inception_rgb_kinetics_only_no_top.h5' elif weights == WEIGHTS_NAME[1]: # flow_kinetics_only if include_top: weights_url = WEIGHTS_PATH['flow_kinetics_only'] model_name = 'i3d_inception_flow_kinetics_only.h5' else: weights_url = WEIGHTS_PATH_NO_TOP['flow_kinetics_only'] model_name = 'i3d_inception_flow_kinetics_only_no_top.h5' elif weights == WEIGHTS_NAME[2]: # rgb_imagenet_and_kinetics if include_top: weights_url = WEIGHTS_PATH['rgb_imagenet_and_kinetics'] model_name = 'i3d_inception_rgb_imagenet_and_kinetics.h5' else: weights_url = WEIGHTS_PATH_NO_TOP['rgb_imagenet_and_kinetics'] model_name = 'i3d_inception_rgb_imagenet_and_kinetics_no_top.h5' elif weights == WEIGHTS_NAME[3]: # flow_imagenet_and_kinetics if include_top: weights_url = WEIGHTS_PATH['flow_imagenet_and_kinetics'] model_name = 'i3d_inception_flow_imagenet_and_kinetics.h5' else: weights_url = WEIGHTS_PATH_NO_TOP['flow_imagenet_and_kinetics'] model_name = 'i3d_inception_flow_imagenet_and_kinetics_no_top.h5' downloaded_weights_path = get_file(model_name, weights_url, cache_subdir='models') model.load_weights(downloaded_weights_path) if K.backend() == 'theano': layer_utils.convert_all_kernels_in_model(model) 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 DenseNet(input_shape=None, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1, nb_layers_per_block=-1, bottleneck=False, reduction=0.0, dropout_rate=0.0, weight_decay=1e-4, subsample_initial_block=False, include_top=True, weights=None, input_tensor=None, pooling=None, classes=10, activation='softmax', transition_pooling='avg'): '''Instantiate the DenseNet architecture. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments 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` dim ordering) or `(3, 224, 224)` (with `channels_first` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. E.g. `(224, 224, 3)` would be one valid value. depth: number or layers in the DenseNet nb_dense_block: number of dense blocks to add to end growth_rate: number of filters to add per dense block nb_filter: initial number of filters. -1 indicates initial number of filters will default to 2 * growth_rate nb_layers_per_block: number of layers in each dense block. Can be a -1, positive integer or a list. If -1, calculates nb_layer_per_block from the network depth. If positive integer, a set number of layers per dense block. If list, nb_layer is used as provided. Note that list size must be nb_dense_block bottleneck: flag to add bottleneck blocks in between dense blocks reduction: reduction factor of transition blocks. Note : reduction value is inverted to compute compression. dropout_rate: dropout rate weight_decay: weight decay rate subsample_initial_block: Changes model type to suit different datasets. Should be set to True for ImageNet, and False for CIFAR datasets. When set to True, the initial convolution will be strided and adds a MaxPooling2D before the initial dense block. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or 'imagenet' (pre-training on ImageNet).. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. 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. activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'. Note that if sigmoid is used, classes must be 1. transition_pooling: `avg` for avg pooling (default), `max` for max pooling, None for no pooling during scale transition blocks. Please note that this default differs from the DenseNetFCN paper in accordance with the DenseNet paper. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as ImageNet with `include_top` ' 'as true, `classes` should be 1000') if activation not in ['softmax', 'sigmoid']: raise ValueError('activation must be one of "softmax" or "sigmoid"') if activation == 'sigmoid' and classes != 1: raise ValueError('sigmoid activation can only be used when classes = 1') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = __create_dense_net(classes, img_input, include_top, depth, nb_dense_block, growth_rate, nb_filter, nb_layers_per_block, bottleneck, reduction, dropout_rate, weight_decay, subsample_initial_block, pooling, activation, transition_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 # Create model. model = Model(inputs, x, name='densenet') # load weights if weights == 'imagenet': weights_loaded = False if (depth == 121) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \ (bottleneck is True) and (reduction == 0.5) and (subsample_initial_block): if include_top: weights_path = get_file('DenseNet-BC-121-32.h5', DENSENET_121_WEIGHTS_PATH, cache_subdir='models', md5_hash='a439dd41aa672aef6daba4ee1fd54abd') else: weights_path = get_file('DenseNet-BC-121-32-no-top.h5', DENSENET_121_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='55e62a6358af8a0af0eedf399b5aea99') model.load_weights(weights_path, by_name=True) weights_loaded = True if (depth == 161) and (nb_dense_block == 4) and (growth_rate == 48) and (nb_filter == 96) and \ (bottleneck is True) and (reduction == 0.5) and (subsample_initial_block): if include_top: weights_path = get_file('DenseNet-BC-161-48.h5', DENSENET_161_WEIGHTS_PATH, cache_subdir='models', md5_hash='6c326cf4fbdb57d31eff04333a23fcca') else: weights_path = get_file('DenseNet-BC-161-48-no-top.h5', DENSENET_161_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='1a9476b79f6b7673acaa2769e6427b92') model.load_weights(weights_path, by_name=True) weights_loaded = True if (depth == 169) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \ (bottleneck is True) and (reduction == 0.5) and (subsample_initial_block): if include_top: weights_path = get_file('DenseNet-BC-169-32.h5', DENSENET_169_WEIGHTS_PATH, cache_subdir='models', md5_hash='914869c361303d2e39dec640b4e606a6') else: weights_path = get_file('DenseNet-BC-169-32-no-top.h5', DENSENET_169_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='89c19e8276cfd10585d5fadc1df6859e') model.load_weights(weights_path, by_name=True) weights_loaded = True if weights_loaded: if K.backend() == 'theano': convert_all_kernels_in_model(model) 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.') print("Weights for the model were loaded successfully") return model
def alexnet_model(weights_path=None): """ Returns a keras model for AlexNet, achieving roughly 80% at ImageNet2012 validation set Model and weights from https://github.com/heuritech/convnets-keras/blob/master/convnetskeras/convnets.py and only slightly modified to work with TF backend """ #K.set_image_dim_ordering('th') keras.backend.set_image_data_format('channels_first') inputs = Input(shape=(3, 227, 227)) conv_1 = Conv2D(96, 11, strides=4, activation='relu', name='conv_1')(inputs) conv_2 = MaxPooling2D((3, 3), strides=(2, 2))(conv_1) conv_2 = cross_channel_normalization(name="convpool_1")(conv_2) conv_2 = ZeroPadding2D((2, 2))(conv_2) """ conv_2 = merge([ Conv2D(128, 5, activation="relu", name='conv_2_' + str(i + 1)) (split_tensor(ratio_split=2, id_split=i)(conv_2) ) for i in range(2)], mode='concat', concat_axis=1, name="conv_2") """ conv_2 = Concatenate(axis=1, name="conv_2")([ Conv2D(128, 5, activation="relu", name='conv_2_' + str(i + 1))(split_tensor(ratio_split=2, id_split=i)(conv_2)) for i in range(2) ]) conv_3 = MaxPooling2D((3, 3), strides=(2, 2))(conv_2) conv_3 = cross_channel_normalization()(conv_3) conv_3 = ZeroPadding2D((1, 1))(conv_3) conv_3 = Conv2D(384, 3, activation='relu', name='conv_3')(conv_3) conv_4 = ZeroPadding2D((1, 1))(conv_3) """ conv_4 = merge([ Conv2D(192, 3, activation="relu", name='conv_4_' + str(i + 1))( split_tensor(ratio_split=2, id_split=i)(conv_4) ) for i in range(2)], mode='concat', concat_axis=1, name="conv_4") """ conv_4 = Concatenate(axis=1, name="conv_4")([ Conv2D(192, 3, activation="relu", name='conv_4_' + str(i + 1))(split_tensor(ratio_split=2, id_split=i)(conv_4)) for i in range(2) ]) conv_5 = ZeroPadding2D((1, 1))(conv_4) """ conv_5 = merge([ Conv2D(128, 3, activation="relu", name='conv_5_' + str(i + 1))( split_tensor(ratio_split=2, id_split=i)(conv_5) ) for i in range(2)], mode='concat', concat_axis=1, name="conv_5") """ conv_5 = Concatenate(axis=1, name="conv_5")([ Conv2D(128, 3, activation="relu", name='conv_5_' + str(i + 1))(split_tensor(ratio_split=2, id_split=i)(conv_5)) for i in range(2) ]) dense_1 = MaxPooling2D((3, 3), strides=(2, 2), name="convpool_5")(conv_5) dense_1 = Flatten(name="flatten")(dense_1) dense_1 = Dense(4096, activation='relu', name='dense_1')(dense_1) dense_2 = Dropout(0.5)(dense_1) dense_2 = Dense(4096, activation='relu', name='dense_2')(dense_2) dense_3 = Dropout(0.5)(dense_2) dense_3 = Dense(1000, name='dense_3')(dense_3) prediction = Activation("softmax", name="softmax")(dense_3) m = Model(input=inputs, output=prediction) if weights_path is None: weights_path = 'alexnet_weights.h5' m.load_weights(weights_path) # Model was trained using Theano backend # This changes convolutional kernels from TF to TH, great accuracy improvement convert_all_kernels_in_model(m) # sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True) # m.compile(optimizer=sgd, loss='mse') return m
def InceptionV1(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1001): """Instantiates the Inception v1 architecture. This architecture is defined in: Going deeper with convolutions Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich. http://arxiv.org/abs/1409.4842v1 Optionally loads weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_data_format="channels_last"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The data format convention used by the model is the one specified in your Keras config file. Note that the default input image size for this model is 224x224. Arguments: include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or "imagenet" (pre-training on ImageNet). input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 224)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 139. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Returns: A Keras model instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') if weights == 'imagenet' and include_top and classes != 1001: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1001') # Determine proper input shape input_shape = _obtain_input_shape( input_shape, #default_size=299, default_size=224, min_size=139, data_format=K.image_data_format(), require_flatten=False) # include_top=include_top) 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 # 'Sequential bit at start' x = img_input x = conv2d_bn(x, 64, 7, 7, strides=(2, 2), padding='same', name='Conv2d_1a_7x7') x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='MaxPool_2a_3x3')(x) x = conv2d_bn(x, 64, 1, 1, strides=(1, 1), padding='same', name='Conv2d_2b_1x1') x = conv2d_bn(x, 192, 3, 3, strides=(1, 1), padding='same', name='Conv2d_2c_3x3') x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='MaxPool_3a_3x3')(x) # Now the '3' level inception units x = concatenated_block(x, (( 64,), ( 96,128), (16, 32), ( 32,)), channel_axis, 'Mixed_3b') x = concatenated_block(x, ((128,), (128,192), (32, 96), ( 64,)), channel_axis, 'Mixed_3c') x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='MaxPool_4a_3x3')(x) # Now the '4' level inception units x = concatenated_block(x, ((192,), ( 96,208), (16, 48), ( 64,)), channel_axis, 'Mixed_4b') x = concatenated_block(x, ((160,), (112,224), (24, 64), ( 64,)), channel_axis, 'Mixed_4c') x = concatenated_block(x, ((128,), (128,256), (24, 64), ( 64,)), channel_axis, 'Mixed_4d') x = concatenated_block(x, ((112,), (144,288), (32, 64), ( 64,)), channel_axis, 'Mixed_4e') x = concatenated_block(x, ((256,), (160,320), (32,128), (128,)), channel_axis, 'Mixed_4f') x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='MaxPool_5a_2x2')(x) # Now the '5' level inception units x = concatenated_block(x, ((256,), (160,320), (32,128), (128,)), channel_axis, 'Mixed_5b') x = concatenated_block(x, ((384,), (192,384), (48,128), (128,)), channel_axis, 'Mixed_5c') if include_top: # Classification block # 'AvgPool_0a_7x7' x = AveragePooling2D((7, 7), strides=(1, 1), padding='valid')(x) # 'Dropout_0b' x = Dropout(0.2)(x) # slim has keep_prob (@0.8), keras uses drop_fraction #logits = conv2d_bn(x, classes, 1, 1, strides=(1, 1), padding='valid', name='Logits', # normalizer=False, activation=None, ) # Write out the logits explictly, since it is pretty different x = Conv2D(classes, (1, 1), strides=(1,1), padding='valid', use_bias=True, name='Logits')(x) x = Flatten(name='Logits_flat')(x) #x = x[:, 1:] # ??Shift up so that first class ('blank background') vanishes # Would be more efficient to strip off position[0] from the weights+bias terms directly in 'Logits' x = Activation('softmax', name='Predictions')(x) else: if pooling == 'avg': x = GlobalAveragePooling2D(name='global_pooling')(x) elif pooling == 'max': x = GlobalMaxPooling2D( name='global_pooling')(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Finally : Create model model = Model(inputs, x, name='inception_v1') # LOAD model weights if weights == 'imagenet': if K.image_data_format() == 'channels_first': if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image data format convention ' '(`image_data_format="channels_first"`). ' 'For best performance, set ' '`image_data_format="channels_last"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') if include_top: weights_path = get_file( 'inception_v1_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models', md5_hash='723bf2f662a5c07db50d28c8d35b626d') else: weights_path = get_file( 'inception_v1_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='6fa8ecdc5f6c402a59909437f0f5c975') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def ResNet152(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, large_input=False, pooling=None, classes=1000): """Instantiate the ResNet152 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. large_input: if True, then the input shape expected will be `(448, 448, 3)` (with `channels_last` data format) or `(3, 448, 448)` (with `channels_first` data format). (default False) 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') eps = 1.1e-5 if large_input: img_size = 448 else: img_size = 224 # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=img_size, min_size=197, 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 # handle dimension ordering for different backends if K.image_dim_ordering() == 'tf': bn_axis = 3 else: bn_axis = 1 x = ZeroPadding2D((3, 3), name='conv1_zeropadding')(img_input) x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=False)(x) x = BatchNormalization(epsilon=eps, axis=bn_axis, name='bn_conv1')(x) x = Scale(axis=bn_axis, name='scale_conv1')(x) x = Activation('relu', name='conv1_relu')(x) x = MaxPooling2D((3, 3), strides=(2, 2), name='pool1')(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') for i in range(1, 8): x = identity_block(x, 3, [128, 128, 512], stage=3, block='b' + str(i)) x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a') for i in range(1, 36): x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b' + str(i)) 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') if large_input: x = AveragePooling2D((14, 14), name='avg_pool')(x) else: x = AveragePooling2D((7, 7), name='avg_pool')(x) # include classification layer by default, not included for feature extraction 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='resnet152') # load weights if weights == 'imagenet': if include_top: weights_path = get_file('resnet152_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH) else: weights_path = get_file('resnet152_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP) model.load_weights(weights_path, by_name=True) 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.') return model
def VGG16_Avg(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, 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 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=48, dim_ordering=K.image_dim_ordering(), include_top=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input) x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x) x = AveragePooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv1')(x) x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv2')(x) x = AveragePooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv1')(x) x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv2')(x) x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv3')(x) x = AveragePooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv1')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv2')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv3')(x) x = AveragePooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv1')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv2')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv3')(x) x = AveragePooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # 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) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='vgg16') # load weights if weights == 'imagenet': if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels_notop.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def create_model(nb_classes=1000, input_shape=None, input_tensor=None, weights=None): 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 nb_classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `nb_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(nb_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.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 create_model(classes=10, input_shape=None, config=None, depth=28, width=8, dropout_rate=0.0, include_top=True, weights=None, input_tensor=None): """ Create wide resnet. Instantiate the Wide Residual Network architecture, optionally loading weights pre-trained on CIFAR-10. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. Parameters ---------- 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. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(32, 32, 3)` (with `tf` dim ordering) or `(3, 32, 32)` (with `th` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. E.g. `(200, 200, 3)` would be one valid value. depth: number or layers in the DenseNet width: multiplier to the ResNet width (number of filters) dropout_rate: dropout rate include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or "cifar10" (pre-training on CIFAR-10).. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. # Returns A Keras model instance. """ if weights not in {'cifar10', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `cifar10` ' '(pre-training on CIFAR-10).') if weights == 'cifar10' and include_top and classes != 10: raise ValueError('If using `weights` as CIFAR 10 with `include_top`' ' as true, `classes` should be 10') if (depth - 4) % 6 != 0: raise ValueError('Depth of the network must be such that (depth - 4)' 'should be divisible by 6.') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_dim_ordering(), include_top=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = __create_wide_residual_network(classes, img_input, include_top, depth, width, dropout_rate) # 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='wide-resnet') # load weights if weights == 'cifar10': if (depth == 28) and (width == 8) and (dropout_rate == 0.0): # Default parameters match. Weights for this model exist: if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file(('wide_resnet_28_8_th_dim_ordering' '_th_kernels.h5'), TH_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file(('wide_resnet_28_8_th_dim_ordering' '_th_kernels_no_top.h5'), TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet ' ' youare using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file(('wide_resnet_28_8_tf_dim_ordering' '_tf_kernels.h5'), TF_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file(('wide_resnet_28_8_tf_dim_ordering' '_tf_kernels_no_top.h5'), TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
weights = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights) if K.backend() == 'tensorflow' and K.image_dim_ordering() == "th": warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) print('Model loaded.') # get the symbolic outputs of each "key" layer (we gave them unique names). outputs_dict = dict([(layer.name, layer.output) for layer in model.layers]) shape_dict = dict([(layer.name, layer.output_shape) for layer in model.layers]) # compute the neural style loss # first we need to define 4 util functions # Improvement 1 # the gram matrix of an image tensor (feature-wise outer product) using shifted activations def gram_matrix(x): assert K.ndim(x) == 3
def MusicTaggerCRNN(weights='msd', input_tensor=None, include_top=True): '''Instantiate the MusicTaggerCRNN architecture, optionally loading weights pre-trained on Million Song Dataset. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. For preparing mel-spectrogram input, see `audio_conv_utils.py` in [applications](https://github.com/fchollet/keras/tree/master/keras/applications). You will need to install [Librosa](http://librosa.github.io/librosa/) to use it. # Arguments weights: one of `None` (random initialization) or "msd" (pre-training on ImageNet). input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. include_top: whether to include the 1 fully-connected layer (output layer) at the top of the network. If False, the network outputs 32-dim features. # Returns A Keras model instance. ''' if weights not in {'msd', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `msd` ' '(pre-training on Million Song Dataset).') # Determine proper input shape if K.image_dim_ordering() == 'th': input_shape = (1, 96, 1366) else: input_shape = (96, 1366, 1) if input_tensor is None: melgram_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): melgram_input = Input(tensor=input_tensor, shape=input_shape) else: melgram_input = input_tensor # Determine input axis if K.image_dim_ordering() == 'th': channel_axis = 1 freq_axis = 2 time_axis = 3 else: channel_axis = 3 freq_axis = 1 time_axis = 2 # Input block x = ZeroPadding2D(padding=(0, 37))(melgram_input) x = BatchNormalization(axis=time_axis, name='bn_0_freq')(x) # Conv block 1 x = Convolution2D(64, 3, 3, border_mode='same', name='conv1')(x) x = BatchNormalization(axis=channel_axis, mode=0, name='bn1')(x) x = ELU()(x) x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(x) # Conv block 2 x = Convolution2D(128, 3, 3, border_mode='same', name='conv2')(x) x = BatchNormalization(axis=channel_axis, mode=0, name='bn2')(x) x = ELU()(x) x = MaxPooling2D(pool_size=(3, 3), strides=(3, 3), name='pool2')(x) # Conv block 3 x = Convolution2D(128, 3, 3, border_mode='same', name='conv3')(x) x = BatchNormalization(axis=channel_axis, mode=0, name='bn3')(x) x = ELU()(x) x = MaxPooling2D(pool_size=(4, 4), strides=(4, 4), name='pool3')(x) # Conv block 4 x = Convolution2D(128, 3, 3, border_mode='same', name='conv4')(x) x = BatchNormalization(axis=channel_axis, mode=0, name='bn4')(x) x = ELU()(x) x = MaxPooling2D(pool_size=(4, 4), strides=(4, 4), name='pool4')(x) # reshaping if K.image_dim_ordering() == 'th': x = Permute((3, 1, 2))(x) x = Reshape((15, 128))(x) # GRU block 1, 2, output x = GRU(32, return_sequences=True, name='gru1')(x) x = GRU(32, return_sequences=False, name='gru2')(x) if include_top: x = Dense(50, activation='sigmoid', name='output')(x) # Create model model = Model(melgram_input, x) if weights is None: return model else: # Load weights if K.image_dim_ordering() == 'tf': weights_path = get_file('music_tagger_crnn_weights_tf_kernels_tf_dim_ordering.h5', TF_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('music_tagger_crnn_weights_tf_kernels_th_dim_ordering.h5', TH_WEIGHTS_PATH, cache_subdir='models') model.load_weights(weights_path, by_name=True) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def VGG16Reg(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, l2_reg=0, classes=1000): """Instantiate the VGG16 architecture, optionally loading weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments include_top: 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 `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `tf` dim ordering) or `(3, 224, 244)` (with `th` dim ordering). 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. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. """ if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=48, dim_ordering=K.image_dim_ordering(), include_top=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Block 1 x = Convolution2D(64, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block1_conv1')(img_input) x = Convolution2D(64, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block1_conv2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = Convolution2D(128, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block2_conv1')(x) x = Convolution2D(128, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block2_conv2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = Convolution2D(256, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block3_conv1')(x) x = Convolution2D(256, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block3_conv2')(x) x = Convolution2D(256, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block3_conv3')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = Convolution2D(512, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block4_conv1')(x) x = Convolution2D(512, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block4_conv2')(x) x = Convolution2D(512, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block4_conv3')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = Convolution2D(512, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block5_conv1')(x) x = Convolution2D(512, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block5_conv2')(x) x = Convolution2D(512, 3, 3, W_regularizer=l2(l2_reg), activation='relu', border_mode='same', name='block5_conv3')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # 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) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='vgg16') # load weights if weights == 'imagenet': if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels_notop.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def DenseNet(input_shape=None, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1, nb_layers_per_block=-1, bottleneck=False, reduction=0.0, dropout_rate=0.0, weight_decay=1e-4, subsample_initial_block=False, include_top=True, weights=None, input_tensor=None, classes=10, activation='softmax'): '''Instantiate the DenseNet architecture, optionally loading weights pre-trained on CIFAR-10. 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 dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(32, 32, 3)` (with `channels_last` dim ordering) or `(3, 32, 32)` (with `channels_first` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. E.g. `(200, 200, 3)` would be one valid value. depth: number or layers in the DenseNet nb_dense_block: number of dense blocks to add to end (generally = 3) growth_rate: number of filters to add per dense block nb_filter: initial number of filters. -1 indicates initial number of filters is 2 * growth_rate nb_layers_per_block: number of layers in each dense block. Can be a -1, positive integer or a list. If -1, calculates nb_layer_per_block from the network depth. If positive integer, a set number of layers per dense block. If list, nb_layer is used as provided. Note that list size must be (nb_dense_block + 1) bottleneck: flag to add bottleneck blocks in between dense blocks reduction: reduction factor of transition blocks. Note : reduction value is inverted to compute compression. dropout_rate: dropout rate weight_decay: weight decay rate subsample_initial_block: Set to True to subsample the initial convolution and add a MaxPool2D before the dense blocks are added. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or 'imagenet' (pre-training on ImageNet).. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'. Note that if sigmoid is used, classes must be 1. # Returns A Keras model instance. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `cifar10` ' '(pre-training on CIFAR-10).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as ImageNet with `include_top`' ' as true, `classes` should be 1000') if activation not in ['softmax', 'sigmoid']: raise ValueError('activation must be one of "softmax" or "sigmoid"') if activation == 'sigmoid' and classes != 1: raise ValueError('sigmoid activation can only be used when classes = 1') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = __create_dense_net(classes, img_input, include_top, depth, nb_dense_block, growth_rate, nb_filter, nb_layers_per_block, bottleneck, reduction, dropout_rate, weight_decay, subsample_initial_block, activation) # Ensure that the 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='densenet') # load weights if weights == 'imagenet': weights_loaded = False if (depth == 121) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \ (bottleneck is True) and (reduction == 0.5) and (dropout_rate == 0.0) and (subsample_initial_block): if include_top: weights_path = get_file('DenseNet-BC-121-32.h5', DENSENET_121_WEIGHTS_PATH, cache_subdir='models', md5_hash='a439dd41aa672aef6daba4ee1fd54abd') else: weights_path = get_file('DenseNet-BC-121-32-no-top.h5', DENSENET_121_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='55e62a6358af8a0af0eedf399b5aea99') model.load_weights(weights_path) weights_loaded = True if (depth == 161) and (nb_dense_block == 4) and (growth_rate == 48) and (nb_filter == 96) and \ (bottleneck is True) and (reduction == 0.5) and (dropout_rate == 0.0) and (subsample_initial_block): if include_top: weights_path = get_file('DenseNet-BC-161-48.h5', DENSENET_161_WEIGHTS_PATH, cache_subdir='models', md5_hash='6c326cf4fbdb57d31eff04333a23fcca') else: weights_path = get_file('DenseNet-BC-161-48-no-top.h5', DENSENET_161_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='1a9476b79f6b7673acaa2769e6427b92') model.load_weights(weights_path) weights_loaded = True if (depth == 169) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \ (bottleneck is True) and (reduction == 0.5) and (dropout_rate == 0.0) and (subsample_initial_block): if include_top: weights_path = get_file('DenseNet-BC-169-32.h5', DENSENET_169_WEIGHTS_PATH, cache_subdir='models', md5_hash='914869c361303d2e39dec640b4e606a6') else: weights_path = get_file('DenseNet-BC-169-32-no-top.h5', DENSENET_169_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='89c19e8276cfd10585d5fadc1df6859e') model.load_weights(weights_path) weights_loaded = True if weights_loaded: if K.backend() == 'theano': convert_all_kernels_in_model(model) 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.') print("Weights for the model were loaded successfully") return model
def __init__(self, model_path='model.h5'): self.model = load_model(model_path) self.kill_model = load_model('gobang/judge_kill.h5') if K.backend() == 'theano': convert_all_kernels_in_model(self.model) convert_all_kernels_in_model(self.kill_model)
def DECODER(include_top=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 include_top: 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 `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 244)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 48. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ img_input = Input(shape=(7, 7, 512)) # Block 5 x = Conv2D(512, (3, 3), activation='relu', padding='same', name='dblock5_conv4')(img_input) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='dblock5_conv3')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='dblock5_conv2')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='dblock5_conv1')(x) x = UpSampling2D((2, 2), name='dblock5_pool')(x) # Block 4 x = Conv2D(512, (3, 3), activation='relu', padding='same', name='dblock4_conv4')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='dblock4_conv3')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='dblock4_conv2')(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='dblock4_conv1')(x) x = UpSampling2D((2, 2), name='dblock4_pool')(x) # Block 3 x = Conv2D(256, (3, 3), activation='relu', padding='same', name='dblock3_conv4')(x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='dblock3_conv3')(x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='dblock3_conv2')(x) x = Conv2D(256, (3, 3), activation='relu', padding='same', name='dblock3_conv1')(x) x = UpSampling2D((2, 2), name='dblock3_pool')(x) # Block 2 x = Conv2D(128, (3, 3), activation='relu', padding='same', name='dblock2_conv2')(x) x = Conv2D(128, (3, 3), activation='relu', padding='same', name='dblock2_conv1')(x) x = UpSampling2D((2, 2), name='dblock2_pool')(x) # Block 1 x = Conv2D(64, (3, 3), activation='relu', padding='same', name='dblock1_conv2')(x) x = Conv2D(64, (3, 3), activation='relu', padding='same', name='dblock1_conv1')(x) x = UpSampling2D((2, 2), name='dblock1_pool')(x) x = Conv2D(3, (3, 3), activation='relu', padding='same', name='dblock0_conv1')(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='decoder') # load weights if weights == 'imagenet': if include_top: 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 include_top: maxpool = model.get_layer(name='block5_pool') shape = maxpool.output_shape[1:] dense = model.get_layer(name='fc1') layer_utils.convert_dense_weights_data_format( dense, shape, 'channels_first') if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image data format convention ' '(`image_data_format="channels_first"`). ' 'For best performance, set ' '`image_data_format="channels_last"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') return model
def DilationNet(dataset, input_shape=None, apply_softmax=True, pretrained=True, input_tensor=None, classes=None): """ Instantiate the Dilation network architecture, optionally loading weights pre-trained on a dataset in the set (cityscapes, voc12, kitti, camvid). Note that pre-trained model is only available for Theano dim ordering. The model and the weights should be compatible with both TensorFlow and Theano backends. # Arguments dataset: choose among (cityscapes, voc12, kitti, camvid). input_shape: shape tuple. It should have exactly 3 inputs channels, and the axis ordering should be coherent with what specified in your keras.json (e.g. use (3, 512, 512) for 'th' and (512, 512, 3) for 'tf'). None will default to dataset specific sizes. apply_softmax: whether to apply softmax or return logits. pretrained: boolean. If `True`, loads weights coherently with input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. classes: optional number of segmentation classes. If pretrained is True, it should be coherent with the dataset chosen. # Returns A Keras model instance. """ if dataset not in {'cityscapes', 'voc12', 'kitti', 'camvid'}: raise ValueError('The `dataset` argument should be one among ' '(cityscapes, voc12, kitti, camvid)') if classes is not None: if classes != CONFIG[dataset]['classes'] and pretrained: raise ValueError('Cannot load pretrained model for dataset `{}` ' 'with {} classes'.format(dataset, classes)) else: classes = CONFIG[dataset]['classes'] if input_shape is None: input_shape = CONFIG[dataset]['input_shape'] # get the model if dataset == 'cityscapes': model = get_dilation_model_cityscapes(input_shape=input_shape, apply_softmax=apply_softmax, input_tensor=input_tensor, classes=classes) elif dataset == 'voc12': model = get_dilation_model_voc(input_shape=input_shape, apply_softmax=apply_softmax, input_tensor=input_tensor, classes=classes) elif dataset == 'kitti': model = get_dilation_model_kitti(input_shape=input_shape, apply_softmax=apply_softmax, input_tensor=input_tensor, classes=classes) elif dataset == 'camvid': model = get_dilation_model_camvid(input_shape=input_shape, apply_softmax=apply_softmax, input_tensor=input_tensor, classes=classes) # load weights if pretrained: if K.image_dim_ordering() == 'th': weights_path = get_file(CONFIG[dataset]['weights_file'], CONFIG[dataset]['weights_url'], cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: raise NotImplementedError('Pretrained DilationNet model is not available with ' 'tensorflow dim ordering') return model
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) or "imagenet" (pre-training on ImageNet). input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(299, 299, 3)` (with `channels_last` data format) or `(3, 299, 299)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 139. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Returns: A Keras model instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=299, min_size=139, data_format=K.image_data_format(), require_flatten=False) 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 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 = 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
first_dense = True nb_last_conv = 0 for dirpath in [ "th-kernels-channels-first-dim-ordering/", "tf-kernels-channels-first-dim-ordering/", "th-kernels-channels-last-dim-ordering/" ]: if not os.path.exists(dirpath): os.makedirs(dirpath) # Converts (tensorflow kernels, tf dim ordering) to (theano kernels, tf dim ordering) K.set_image_dim_ordering('th') for weight_fn in model_weights: tf_dim_model.load_weights(weight_fn) convert_all_kernels_in_model(tf_dim_model) tf_dim_model.save_weights("th-kernels-channels-last-dim-ordering/%s" % weight_fn, overwrite=True) print("Done th-kernels-channels-last-dim-ordering %s" % weight_fn) # Converts (tensorflow kernels, tf dim ordering) to (theano kernels, th dim ordering) K.set_image_dim_ordering('tf') for weight_fn in model_weights: tf_dim_model.load_weights(weight_fn) # tf-kernels-tf-dim convert_all_kernels_in_model(tf_dim_model) # th-kernels-tf-dim count_dense = 0 for layer in tf_dim_model.layers: if layer.__class__.__name__ == "Dense":
def VGG19(include_top=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 include_top: 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 `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or `(3, 224, 244)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 48. E.g. `(200, 200, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=48, data_format=K.image_data_format(), include_top=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # 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 include_top: # 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 include_top: 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 include_top: maxpool = model.get_layer(name='block5_pool') shape = maxpool.output_shape[1:] dense = model.get_layer(name='fc1') layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first') if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image data format convention ' '(`image_data_format="channels_first"`). ' 'For best performance, set ' '`image_data_format="channels_last"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') return model
def InceptionV3(include_top=True, weights='imagenet', input_tensor=None): '''Instantiate the Inception v3 architecture, optionally loading weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering 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 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. # Returns A Keras model instance. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') # Determine proper input shape if K.image_dim_ordering() == 'th': if include_top: input_shape = (3, 299, 299) else: input_shape = (3, None, None) else: if include_top: input_shape = (299, 299, 3) else: input_shape = (None, None, 3) 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) else: img_input = input_tensor if K.image_dim_ordering() == 'th': channel_axis = 1 else: channel_axis = 3 x = conv2d_bn(img_input, 32, 3, 3, subsample=(2, 2), border_mode='valid') x = conv2d_bn(x, 32, 3, 3, border_mode='valid') x = conv2d_bn(x, 64, 3, 3) x = MaxPooling2D((3, 3), strides=(2, 2))(x) x = conv2d_bn(x, 80, 1, 1, border_mode='valid') x = conv2d_bn(x, 192, 3, 3, border_mode='valid') x = MaxPooling2D((3, 3), strides=(2, 2))(x) # mixed 0, 1, 2: 35 x 35 x 256 for i in range(3): 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), border_mode='same')(x) branch_pool = conv2d_bn(branch_pool, 32, 1, 1) x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool], mode='concat', concat_axis=channel_axis, name='mixed' + str(i)) # mixed 3: 17 x 17 x 768 branch3x3 = conv2d_bn(x, 384, 3, 3, subsample=(2, 2), border_mode='valid') branch3x3dbl = conv2d_bn(x, 64, 1, 1) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3) branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, subsample=(2, 2), border_mode='valid') branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x) x = merge([branch3x3, branch3x3dbl, branch_pool], mode='concat', concat_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), border_mode='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_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), border_mode='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_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, 160, 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), border_mode='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_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, subsample=(2, 2), border_mode='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, subsample=(2, 2), border_mode='valid') branch_pool = AveragePooling2D((3, 3), strides=(2, 2))(x) x = merge([branch3x3, branch7x7x3, branch_pool], mode='concat', concat_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 = merge([branch3x3_1, branch3x3_2], mode='concat', concat_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 = merge([branch3x3dbl_1, branch3x3dbl_2], mode='concat', concat_axis=channel_axis) branch_pool = AveragePooling2D( (3, 3), strides=(1, 1), border_mode='same')(x) branch_pool = conv2d_bn(branch_pool, 192, 1, 1) x = merge([branch1x1, branch3x3, branch3x3dbl, branch_pool], mode='concat', concat_axis=channel_axis, name='mixed' + str(9 + i)) if include_top: # Classification block x = AveragePooling2D((8, 8), strides=(8, 8), name='avg_pool')(x) x = Flatten(name='flatten')(x) x = Dense(1000, activation='softmax', name='predictions')(x) # Create model model = Model(img_input, x) # load weights if weights == 'imagenet': if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file('inception_v3_weights_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models', md5_hash='b3baf3070cc4bf476d43a2ea61b0ca5f') else: weights_path = get_file('inception_v3_weights_th_dim_ordering_th_kernels_notop.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='79aaa90ab4372b4593ba3df64e142f05') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file('inception_v3_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models', md5_hash='fe114b3ff2ea4bf891e9353d1bbfb32f') else: weights_path = get_file('inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models', md5_hash='2f3609166de1d967d1a481094754f691') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def VGG19(include_top=True, weights='imagenet', input_tensor=None): '''Instantiate the VGG19 architecture, optionally loading weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments include_top: 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. # Returns A Keras model instance. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') # Determine proper input shape if K.image_dim_ordering() == 'th': if include_top: input_shape = (3, 224, 224) else: input_shape = (3, None, None) else: if include_top: input_shape = (224, 224, 3) else: input_shape = (None, None, 3) 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) else: img_input = input_tensor # Block 1 x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv1')(img_input) x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='block1_conv2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x) # Block 2 x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv1')(x) x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='block2_conv2')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x) # Block 3 x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv1')(x) x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv2')(x) x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv3')(x) x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='block3_conv4')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x) # Block 4 x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv1')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv2')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv3')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block4_conv4')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x) # Block 5 x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv1')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv2')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv3')(x) x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='block5_conv4')(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: # 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(1000, activation='softmax', name='predictions')(x) # Create model model = Model(img_input, x) # load weights if weights == 'imagenet': print('K.image_dim_ordering:', K.image_dim_ordering()) if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file('vgg19_weights_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('vgg19_weights_th_dim_ordering_th_kernels_notop.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
def salcnn_VGG16_dilation(include_top=False, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, 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 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=48, 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 # 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 = 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 = MaxPooling2D((2, 2), strides=(1, 1), padding='same', name='block4_pool')(x) # strides=(2, 2) # 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_conv1', dilation_rate=(2, 2))(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2', dilation_rate=(2, 2))(x) x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3', dilation_rate=(2, 2))(x) # x = MaxPooling2D((2, 2), strides=(1, 1), padding='same', name='block5_pool')(x) # strides=(2, 2) if include_top: # 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='salcnn_vgg16_dilation') # load weights if weights == 'imagenet': if include_top: weights_path = get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path, 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='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 VGG16(weights='imagenet'): '''Instantiate the VGG16 architecture, optionally loading weights pre-trained on ImageNet. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments include_top: whether to include the 3 fully-connected layers at the top of the network. weights: one of `deep_gllim` (fine tunned weights) or "imagenet" (pre-training on ImageNet). # Returns A Keras model instance. ''' # if weights not in {'imagenet', 'deep_gllim'}: # raise ValueError('The `weights` argument should be either ' # '`imagenet` (pre-training on ImageNet)' # 'or `deep_gllim` (fine tunned weights).') # Determine proper input shape if K.image_data_format() == 'th': INPUT_SHAPE = (3, 224, 224) else: INPUT_SHAPE = (224, 224, 3) model = Sequential() model.add(ZeroPadding2D((1, 1), input_shape=INPUT_SHAPE)) model.add(Convolution2D(64, 3, 3, activation='relu', trainable=False)) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(64, 3, 3, activation='relu', trainable=False)) model.add(MaxPooling2D((2, 2), strides=(2, 2))) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(128, 3, 3, activation='relu', trainable=False)) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(128, 3, 3, activation='relu', trainable=False)) model.add(MaxPooling2D((2, 2), strides=(2, 2))) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(256, 3, 3, activation='relu', trainable=False)) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(256, 3, 3, activation='relu', trainable=False)) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(256, 3, 3, activation='relu', trainable=False)) model.add(MaxPooling2D((2, 2), strides=(2, 2))) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(512, 3, 3, activation='relu', trainable=False)) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(512, 3, 3, activation='relu', trainable=False)) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(512, 3, 3, activation='relu', trainable=False)) model.add(MaxPooling2D((2, 2), strides=(2, 2))) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(512, 3, 3, activation='relu', trainable=False)) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(512, 3, 3, activation='relu', trainable=False)) model.add(ZeroPadding2D((1, 1))) model.add(Convolution2D(512, 3, 3, activation='relu', trainable=False)) model.add(MaxPooling2D((2, 2), strides=(2, 2))) model.add(Flatten()) model.add(Dense(4096, activation='relu', trainable=True)) model.add(Dropout(0.5)) model.add(Dense(4096, activation='relu', trainable=True)) model.add(Dropout(0.5)) model.add(Dense(1000, activation='softmax', trainable=True)) # load weights if weights == 'imagenet': if K.image_data_format() == 'th': print("LOAD: " + WEIGHTS_PATH) weights_path = WEIGHTS_PATH model.load_weights(weights_path) model.pop() # remove softmax layer model.pop() # remove dropout if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: weights_path = get_file( 'vgg16_weights_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models') model.load_weights(weights_path) model.pop() # remove softmax layer model.pop() # remove dropout if K.backend() == 'theano': convert_all_kernels_in_model(model) elif weights == 'deep_gllim': if K.image_data_format() == 'th': weights_path = TH_WEIGHTS_PATH_DEEP_GLLIM model.load_weights(weights_path) model.pop() # remove softmax layer model.pop() # remove dropout if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: weights_path = TF_WEIGHTS_PATH_DEEP_GLLIM model.load_weights(weights_path) model.pop() # remove softmax layer model.pop() # remove dropout if K.backend() == 'theano': convert_all_kernels_in_model(model) elif weights == 'deep_gllim_PCA_BN': model.pop() # remove softmax layer model.pop() # remove dropout model.add(Dense(512, activation='linear', trainable=False)) model.add(BatchNormalization()) weights_path = TH_WEIGHTS_PATH_DEEP_GLLIM_PCA_BN model.load_weights(weights_path) model.pop() # remove BN return model
def VGG16_AVG(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, 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 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=48, data_format=K.image_data_format(), include_top=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # 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 = AveragePooling2D((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 = AveragePooling2D((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 = AveragePooling2D((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 = AveragePooling2D((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 = AveragePooling2D((2, 2), strides=(2, 2), name='block5_pool')(x) if include_top: 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) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = Model(inputs, x, name='vgg16') # load weights if weights == 'imagenet': if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('vgg16_weights_th_dim_ordering_th_kernels_notop.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels.h5', WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
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) or "imagenet" (pre-training on ImageNet). input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(299, 299, 3)` (with `channels_last` data format) or `(3, 299, 299)` (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 139. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional layer. - `avg` means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. Returns: A Keras model instance. Raises: ValueError: in case of invalid argument for `weights`, or invalid input shape. """ if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `imagenet` ' '(pre-training on ImageNet).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as imagenet with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape input_shape = _obtain_input_shape( input_shape, default_size=299, min_size=139, data_format=K.image_data_format(), include_top=include_top) 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 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 = 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 WideResidualNetwork(depth=28, width=8, dropout_rate=0.0, include_top=True, weights='cifar10', input_tensor=None, input_shape=None, classes=10): """Instantiate the Wide Residual Network architecture, optionally loading weights pre-trained on CIFAR-10. Note that when using TensorFlow, for best performance you should set `image_dim_ordering="tf"` in your Keras config at ~/.keras/keras.json. The model and the weights are compatible with both TensorFlow and Theano. The dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments depth: number or layers in the DenseNet width: multiplier to the ResNet width (number of filters) dropout_rate: dropout rate include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or "cifar10" (pre-training on CIFAR-10).. 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 `(32, 32, 3)` (with `tf` dim ordering) or `(3, 32, 32)` (with `th` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. E.g. `(200, 200, 3)` would be one valid value. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. """ if weights not in {'cifar10', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `cifar10` ' '(pre-training on CIFAR-10).') if weights == 'cifar10' and include_top and classes != 10: raise ValueError('If using `weights` as CIFAR 10 with `include_top`' ' as true, `classes` should be 10') if (depth - 4) % 6 != 0: raise ValueError('Depth of the network must be such that (depth - 4)' 'should be divisible by 6.') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_dim_ordering(), include_top=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = __create_wide_residual_network(classes, img_input, include_top, depth, width, dropout_rate) # 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='wide-resnet') # load weights if weights == 'cifar10': if (depth == 28) and (width == 8) and (dropout_rate == 0.0): # Default parameters match. Weights for this model exist: if K.image_dim_ordering() == 'th': if include_top: weights_path = get_file( 'wide_resnet_28_8_th_dim_ordering_th_kernels.h5', TH_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'wide_resnet_28_8_th_dim_ordering_th_kernels_no_top.h5', TH_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'tensorflow': warnings.warn( 'You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) else: if include_top: weights_path = get_file( 'wide_resnet_28_8_tf_dim_ordering_tf_kernels.h5', TF_WEIGHTS_PATH, cache_subdir='models') else: weights_path = get_file( 'wide_resnet_28_8_tf_dim_ordering_tf_kernels_no_top.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights_path) if K.backend() == 'theano': convert_all_kernels_in_model(model) return model
weights = get_file('vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_19_WEIGHTS_PATH_NO_TOP, cache_subdir='models') else: weights = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', TF_WEIGHTS_PATH_NO_TOP, cache_subdir='models') model.load_weights(weights) if K.backend() == 'tensorflow' and K.image_dim_ordering() == "th": warnings.warn('You are using the TensorFlow backend, yet you ' 'are using the Theano ' 'image dimension ordering convention ' '(`image_dim_ordering="th"`). ' 'For best performance, set ' '`image_dim_ordering="tf"` in ' 'your Keras config ' 'at ~/.keras/keras.json.') convert_all_kernels_in_model(model) print('Model loaded.') # get the symbolic outputs of each "key" layer (we gave them unique names). outputs_dict = dict([(layer.name, layer.output) for layer in model.layers]) shape_dict = dict([(layer.name, layer.output_shape) for layer in model.layers]) # compute the neural style loss # first we need to define 4 util functions # the gram matrix of an image tensor (feature-wise outer product) def gram_matrix(x): assert K.ndim(x) == 3 if K.image_dim_ordering() == "th": features = K.batch_flatten(x)
def SparseNet(input_shape=None, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1, nb_layers_per_block=-1, bottleneck=False, reduction=0.0, dropout_rate=0.0, subsample_initial_block=False, include_top=True, weights=None, input_tensor=None, classes=1, activation='softmax'): '''Instantiate the SparseNet architecture, optionally loading weights pre-trained on CIFAR-10. 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 dimension ordering convention used by the model is the one specified in your Keras config file. # Arguments input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(32, 32, 3)` (with `channels_last` dim ordering) or `(3, 32, 32)` (with `channels_first` dim ordering). It should have exactly 3 inputs channels, and width and height should be no smaller than 8. E.g. `(200, 200, 3)` would be one valid value. depth: number or layers in the DenseNet nb_dense_block: number of dense blocks to add to end (generally = 3) growth_rate: number of filters to add per dense block. Can be a single integer number or a list of numbers. If it is a list, length of list must match the length of `nb_layers_per_block` nb_filter: initial number of filters. -1 indicates initial number of filters is 2 * growth_rate nb_layers_per_block: number of layers in each dense block. Can be a -1, positive integer or a list. If -1, calculates nb_layer_per_block from the network depth. If positive integer, a set number of layers per dense block. If list, nb_layer is used as provided. Note that list size must be (nb_dense_block + 1) bottleneck: flag to add bottleneck blocks in between dense blocks reduction: reduction factor of transition blocks. Note : reduction value is inverted to compute compression. dropout_rate: dropout rate weight_decay: weight decay rate subsample_initial_block: Set to True to subsample the initial convolution and add a MaxPool2D before the dense blocks are added. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization) or 'imagenet' (pre-training on ImageNet).. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'. Note that if sigmoid is used, classes must be 1. # Returns A Keras model instance. ''' if weights not in {'imagenet', None}: raise ValueError('The `weights` argument should be either ' '`None` (random initialization) or `cifar10` ' '(pre-training on CIFAR-10).') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError('If using `weights` as ImageNet with `include_top`' ' as true, `classes` should be 1000') if activation not in ['softmax', 'sigmoid']: raise ValueError('activation must be one of "softmax" or "sigmoid"') if activation == 'sigmoid' and classes != 1: raise ValueError( 'sigmoid activation can only be used when classes = 1') # Determine proper input shape input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_data_format(), require_flatten=include_top) if input_tensor is None: img_input = Input(shape=input_shape) else: if not K.is_keras_tensor(input_tensor): img_input = Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor img_input = Input(shape=(280, 280, 16, 1), name='data') #####wds x = _create_dense_net(classes, img_input, include_top, depth, nb_dense_block, growth_rate, nb_filter, nb_layers_per_block, bottleneck, reduction, dropout_rate, subsample_initial_block, activation) # 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='densenet') # model.compile(optimizer=SGD(lr = 1e-4, momentum = 0.9), loss = 'binary_crossentropy', metrics= [y_t, y_pre, Acc] ) # model.compile(optimizer=Adam(lr=1e-3), loss='binary_crossentropy', metrics=[y_t, y_pre, Acc]) # load weights if weights == 'imagenet': weights_loaded = False if weights_loaded: if K.backend() == 'theano': convert_all_kernels_in_model(model) 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.') print("Weights for the model were loaded successfully") 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