def D3GenerateModel(n_filter=16, number_of_class=2, input_shape=(16,144,144,1),activation_last='sigmoid', metrics=['mse', 'acc'],loss='mse', optimizer='adam',dropout=0.5, init='glorot_uniform'): filter_size =n_filter model = Sequential() model.add(layers.Conv3D(filters=filter_size, input_shape=input_shape, kernel_size=(3,3,3), strides=(1,1, 1), padding='valid', activation='selu')) model.add(layers.Conv3D(filters=filter_size*2, kernel_size=(3,3,3), strides=(1, 2,2), padding='valid', activation='selu')) model.add(layers.MaxPooling3D((1, 2,2), padding='valid')) model.add(layers.Conv3D(filters=filter_size*2, kernel_size=(3,3,3), strides=(1,1,1), padding='valid', activation='selu')) model.add(layers.Conv3D(filters=filter_size*4, kernel_size=(3,3,3), strides=(1, 2,2), padding='valid', activation='selu')) model.add(layers.MaxPooling3D((1, 2,2), padding='valid')) model.add(layers.Conv3D(filters=filter_size*4, kernel_size=(3,3,3), strides=(1,1, 1), padding='valid', activation='selu')) model.add(layers.Conv3D(filters=filter_size*8, kernel_size=(3,3,3), strides=(1, 2,2), padding='valid', activation='selu')) model.add(layers.MaxPooling3D((1,2, 2), padding='same')) model.add(layers.Conv3D(filters=filter_size*16, kernel_size=(3,3,3), strides=(1,1, 1), padding='same', activation='selu')) model.add(layers.Conv3D(filters=filter_size*32, kernel_size=(3,3,3), strides=(2,2, 2), padding='same', activation='selu')) #model.add(layers.MaxPooling2D((2, 2), padding='valid')) model.add(layers.GlobalMaxPooling3D()) #Encoder model.add(layers.Dense(512, activation='selu')) model.add(keras.layers.Dropout(0.5)) model.add(layers.Dense(256, activation='selu')) model.add(layers.Dense(2, activation='softmax'))#, kernel_regularizer=l2(0.01), bias_regularizer=l2(0.01))) model.summary() model.compile(optimizer=keras.optimizers.adam(lr=2e-6),loss='categorical_crossentropy', metrics=metrics) return model
def design_dnn(nb_features, input_shape, nb_levels, conv_size, nb_labels, feat_mult=1, pool_size=2, padding='same', activation='elu', final_layer='dense-sigmoid', conv_dropout=0, conv_maxnorm=0, nb_input_features=1, batch_norm=False, name=None, prefix=None, use_strided_convolution_maxpool=True, nb_conv_per_level=2): """ "deep" cnn with dense or global max pooling layer @ end... Could use sequential... """ model_name = name if model_name is None: model_name = 'model_1' if prefix is None: prefix = model_name ndims = len(input_shape) input_shape = tuple(input_shape) convL = getattr(KL, 'Conv%dD' % ndims) maxpool = KL.MaxPooling3D if len(input_shape) == 3 else KL.MaxPooling2D if isinstance(pool_size, int): pool_size = (pool_size,) * ndims # kwargs for the convolution layer conv_kwargs = {'padding': padding, 'activation': activation} if conv_maxnorm > 0: conv_kwargs['kernel_constraint'] = maxnorm(conv_maxnorm) # initialize a dictionary enc_tensors = {} # first layer: input name = '%s_input' % prefix enc_tensors[name] = KL.Input(shape=input_shape + (nb_input_features,), name=name) last_tensor = enc_tensors[name] # down arm: # add nb_levels of conv + ReLu + conv + ReLu. Pool after each of first nb_levels - 1 layers for level in range(nb_levels): for conv in range(nb_conv_per_level): if conv_dropout > 0: name = '%s_dropout_%d_%d' % (prefix, level, conv) enc_tensors[name] = KL.Dropout(conv_dropout)(last_tensor) last_tensor = enc_tensors[name] name = '%s_conv_%d_%d' % (prefix, level, conv) nb_lvl_feats = np.round(nb_features*feat_mult**level).astype(int) enc_tensors[name] = convL(nb_lvl_feats, conv_size, **conv_kwargs, name=name)(last_tensor) last_tensor = enc_tensors[name] # max pool if use_strided_convolution_maxpool: name = '%s_strided_conv_%d' % (prefix, level) enc_tensors[name] = convL(nb_lvl_feats, pool_size, **conv_kwargs, name=name)(last_tensor) last_tensor = enc_tensors[name] else: name = '%s_maxpool_%d' % (prefix, level) enc_tensors[name] = maxpool(pool_size=pool_size, name=name, padding=padding)(last_tensor) last_tensor = enc_tensors[name] # dense layer if final_layer == 'dense-sigmoid': name = "%s_flatten" % prefix enc_tensors[name] = KL.Flatten(name=name)(last_tensor) last_tensor = enc_tensors[name] name = '%s_dense' % prefix enc_tensors[name] = KL.Dense(1, name=name, activation="sigmoid")(last_tensor) elif final_layer == 'dense-tanh': name = "%s_flatten" % prefix enc_tensors[name] = KL.Flatten(name=name)(last_tensor) last_tensor = enc_tensors[name] name = '%s_dense' % prefix enc_tensors[name] = KL.Dense(1, name=name)(last_tensor) last_tensor = enc_tensors[name] # Omittting BatchNorm for now, it seems to have a cpu vs gpu problem # https://github.com/tensorflow/tensorflow/pull/8906 # https://github.com/fchollet/keras/issues/5802 # name = '%s_%s_bn' % prefix # enc_tensors[name] = KL.BatchNormalization(axis=batch_norm, name=name)(last_tensor) # last_tensor = enc_tensors[name] name = '%s_%s_tanh' % prefix enc_tensors[name] = KL.Activation(activation="tanh", name=name)(last_tensor) elif final_layer == 'dense-softmax': name = "%s_flatten" % prefix enc_tensors[name] = KL.Flatten(name=name)(last_tensor) last_tensor = enc_tensors[name] name = '%s_dense' % prefix enc_tensors[name] = KL.Dense(nb_labels, name=name, activation="softmax")(last_tensor) # global max pooling layer elif final_layer == 'myglobalmaxpooling': name = '%s_batch_norm' % prefix enc_tensors[name] = KL.BatchNormalization(axis=batch_norm, name=name)(last_tensor) last_tensor = enc_tensors[name] name = '%s_global_max_pool' % prefix enc_tensors[name] = KL.Lambda(_global_max_nd, name=name)(last_tensor) last_tensor = enc_tensors[name] name = '%s_global_max_pool_reshape' % prefix enc_tensors[name] = KL.Reshape((1, 1), name=name)(last_tensor) last_tensor = enc_tensors[name] # cannot do activation in lambda layer. Could code inside, but will do extra lyaer name = '%s_global_max_pool_sigmoid' % prefix enc_tensors[name] = KL.Conv1D(1, 1, name=name, activation="sigmoid", use_bias=True)(last_tensor) elif final_layer == 'globalmaxpooling': name = '%s_conv_to_featmaps' % prefix enc_tensors[name] = KL.Conv3D(2, 1, name=name, activation="relu")(last_tensor) last_tensor = enc_tensors[name] name = '%s_global_max_pool' % prefix enc_tensors[name] = KL.GlobalMaxPooling3D(name=name)(last_tensor) last_tensor = enc_tensors[name] # cannot do activation in lambda layer. Could code inside, but will do extra lyaer name = '%s_global_max_pool_softmax' % prefix enc_tensors[name] = KL.Activation('softmax', name=name)(last_tensor) last_tensor = enc_tensors[name] # create the model model = Model(inputs=[enc_tensors['%s_input' % prefix]], outputs=[last_tensor], name=model_name) return model
def create_vgg16_3d(dense=False, batch_norm=True, weights=None, input_shape=(260, 100, 15, 1)): """ Creates slightly modified VGG16 model, ported to 3d with trainable BatchNormalization """ def create_conv(filter, kernel_size, name): def conv_wrapper(inp): x = layers.Conv3D(filter, kernel_size, padding='same', name=name)(inp) if batch_norm: x = layers.BatchNormalization()(x) x = layers.Activation('relu')(x) return x return conv_wrapper img_input = layers.Input(shape=input_shape, name='input') # block 1 x = create_conv(8, (3, 3, 3), name='block1_conv1')(img_input) x = create_conv(8, (3, 3, 3), name='block1_conv2')(x) x = layers.MaxPooling3D((2, 2, 2), strides=(2, 2, 2), name='block1_pool')(x) # block 2 x = create_conv(16, (3, 3, 3), name='block2_conv1')(x) x = create_conv(16, (3, 3, 3), name='block2_conv2')(x) x = layers.MaxPooling3D((2, 2, 2), strides=(2, 2, 2), name='block2_pool')(x) # block 3 x = create_conv(32, (3, 3, 3), name='block3_conv1')(x) x = create_conv(32, (3, 3, 3), name='block3_conv2')(x) x = create_conv(32, (3, 3, 3), name='block3_conv3')(x) x = layers.MaxPooling3D((2, 2, 2), strides=(2, 2, 2), name='block3_pool')(x) # block 4 x = create_conv(32, (3, 3, 3), name='block4_conv1')(x) x = create_conv(32, (3, 3, 3), name='block4_conv2')(x) x = create_conv(32, (3, 3, 3), name='block4_conv3')(x) # delete MaxPooling to allow for 5th block # block 5 x = create_conv(64, (3, 3, 3), name='block5_conv1')(x) x = create_conv(64, (3, 3, 3), name='block5_conv2')(x) x = create_conv(64, (3, 3, 3), name='block5_conv3')(x) if dense: x = layers.Flatten()(x) x = layers.Dense(4096)(x) x = layers.BatchNormalization()(x) x = layers.Dense(2048)(x) x = layers.BatchNormalization()(x) x = layers.Dense(1)(x) else: x = layers.GlobalMaxPooling3D()(x) model = models.Model(img_input, x, name='vgg16_3d') if weights is not None: model.load_weights(weights, by_name=True) return model
def InceptionResNetV2R2(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, **kwargs): """Instantiates the Inception-ResNet v2 architecture. Optionally loads weights pre-trained on ImageNet. Note that the data format convention used by the model is the one specified in your Keras config at `~/.keras/keras.json`. # Arguments include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. input_shape: optional shape tuple, only to be specified if `include_top` is `False` (otherwise the input shape has to be `(299, 299, 3)` (with `'channels_last'` data format) or `(3, 299, 299)` (with `'channels_first'` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g. `(150, 150, 3)` would be one valid value. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `'avg'` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `'max'` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is `True`, and if no `weights` argument is specified. # Returns A Keras `Model` instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. """ global backend, layers, models, keras_utils # backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs) from keras import backend, layers, models from keras import utils as keras_utils if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top`' ' as true, `classes` should be 1000') # Determine proper input shape # input_shape = _obtain_input_shape( # input_shape, # default_size=299, # min_size=75, # data_format=backend.image_data_format(), # require_flatten=include_top, # weights=weights) input_shape = input_shape #(96, 120, 86, 2) if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor # Stem block output: 21 x 27 x 19 x 256 x = conv3d_bn(img_input, 48, 3, padding='valid') x = conv3d_bn(x, 64, 3) x1 = layers.MaxPooling3D(3, strides=2)(x) x2 = conv3d_bn(x, 64, 3, 2, padding='valid') channel_axis = 1 if backend.image_data_format() == 'channels_first' else 4 x = layers.Concatenate(axis=channel_axis)([x1, x2]) #nKernal = 128 x1 = conv3d_bn(x, 64, 1) x1 = conv3d_bn(x1, 96, 3, padding='valid') x2 = conv3d_bn(x, 64, 1) x2 = conv3d_bn(x2, 64, [1, 7, 1]) x2 = conv3d_bn(x2, 64, [1, 1, 7]) x2 = conv3d_bn(x2, 64, [7, 1, 1]) x2 = conv3d_bn(x2, 96, 3, padding='valid') x = layers.Concatenate(axis=channel_axis)([x1, x2]) #nKernal = 192 x1 = conv3d_bn(x, 128, 3, 2, padding='valid') x2 = layers.MaxPooling3D(3, strides=2, padding='valid', name='StemEnd')(x) x = layers.Concatenate(axis=channel_axis)([x1, x2]) #nKernal = 320 # 2x block35 (Inception-ResNet-A block) output: 21 x 27 x 19 x 320 for block_idx in range(1, 3): x = inception_resnet_block( x, scale=0.17, # scale=0.1, # reduce to 0.1 to avoid instability block_type='block35', block_idx=block_idx) # Mixed 6a (Reduction-A block) output: 10 x 13 x 9 x 640 branch_0 = conv3d_bn(x, 160, 3, strides=2, padding='valid') branch_1 = conv3d_bn(x, 128, 1) branch_1 = conv3d_bn(branch_1, 128, 3) branch_1 = conv3d_bn(branch_1, 160, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling3D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_pool] channel_axis = 1 if backend.image_data_format() == 'channels_first' else 4 x = layers.Concatenate(axis=channel_axis, name='mixed_6a')(branches) # 4x block17 (Inception-ResNet-B block) output: 10 x 13 x 9 x 640 for block_idx in range(1, 5): x = inception_resnet_block(x, scale=0.1, block_type='block17', block_idx=block_idx) # Mixed 7a (Reduction-B block): 4 x 6 x 4 x 1408 branch_0 = conv3d_bn(x, 192, 1) branch_0 = conv3d_bn(branch_0, 224, 3, strides=2, padding='valid') branch_1 = conv3d_bn(x, 192, 1) branch_1 = conv3d_bn(branch_1, 288, 3, strides=2, padding='valid') branch_2 = conv3d_bn(x, 192, 1) branch_2 = conv3d_bn(branch_2, 224, 3) branch_2 = conv3d_bn(branch_2, 256, 3, strides=2, padding='valid') branch_pool = layers.MaxPooling3D(3, strides=2, padding='valid')(x) branches = [branch_0, branch_1, branch_2, branch_pool] x = layers.Concatenate(axis=channel_axis, name='mixed_7a')(branches) # 2x block8 (Inception-ResNet-C block): 4 x 6 x 4 x 1408 for block_idx in range(1, 2): x = inception_resnet_block( x, scale=0.2, # scale=0.1, # reduce to 0.1 to avoid instability block_type='block8', block_idx=block_idx) x = inception_resnet_block(x, scale=1., activation=None, block_type='block8', block_idx=5) # Final convolution block: 4 x 6 x 4 x 512 x = conv3d_bn(x, 512, 1, name='conv_7b') if include_top: # Classification block x = layers.GlobalAveragePooling3D(name='avg_pool')(x) x = layers.Dense(classes, activation='softmax', name='predictions')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling3D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling3D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = keras_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name='inception_resnet_v2_3D') # Load weights. if weights == 'imagenet': if include_top: fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5' weights_path = keras_utils.get_file( fname, BASE_WEIGHT_URL + fname, cache_subdir='models', file_hash='e693bd0210a403b3192acc6073ad2e96') else: fname = ('inception_resnet_v2_weights_' 'tf_dim_ordering_tf_kernels_notop.h5') weights_path = keras_utils.get_file( fname, BASE_WEIGHT_URL + fname, cache_subdir='models', file_hash='d19885ff4a710c122648d3b5c3b684e4') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def MobileNet(input_shape=None, alpha=1.0, depth_multiplier=1, dropout=1e-3, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000, **kwargs): """Instantiates the MobileNet architecture. # Arguments input_shape: optional shape tuple, only to be specified if `include_top` is False (otherwise the input shape has to be `(224, 224, 3)` (with `channels_last` data format) or (3, 224, 224) (with `channels_first` data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. `(200, 200, 3)` would be one valid value. alpha: controls the width of the network. This is known as the width multiplier in the MobileNet paper. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. depth_multiplier: depth multiplier for depthwise convolution. This is called the resolution multiplier in the MobileNet paper. dropout: dropout rate include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape. RuntimeError: If attempting to run this model with a backend that does not support separable convolutions. """ global backend, layers, models, keras_utils backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') # Determine proper input shape and default size. if input_shape is None: default_size = 224 else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [128, 160, 192, 224]: default_size = rows else: default_size = 224 if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if weights == 'imagenet': if depth_multiplier != 1: raise ValueError('If imagenet weights are being loaded, ' 'depth multiplier must be 1') if alpha not in [0.25, 0.50, 0.75, 1.0]: raise ValueError('If imagenet weights are being loaded, ' 'alpha can be one of' '`0.25`, `0.50`, `0.75` or `1.0` only.') if rows != cols or rows not in [128, 160, 192, 224]: rows = 224 warnings.warn('`input_shape` is undefined or non-square, ' 'or `rows` is not in [128, 160, 192, 224]. ' 'Weights for input shape (224, 224) will be' ' loaded as the default.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor x = _conv_block(img_input, 32, alpha, strides=(2, 2, 2)) x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1) x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, strides=(2, 2, 2), block_id=2) x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3) x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, strides=(2, 2, 2), block_id=4) x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, strides=(2, 2, 2), block_id=6) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10) x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11) x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, strides=(2, 2, 2), block_id=12) x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13) if include_top: if backend.image_data_format() == 'channels_first': shape = (int(1024 * alpha), 1, 1, 1) else: shape = (1, 1, 1, int(1024 * alpha)) x = layers.GlobalAveragePooling3D()(x) x = layers.Reshape(shape, name='reshape_1')(x) x = layers.Dropout(dropout, name='dropout')(x) x = layers.Conv3D(classes, (1, 1, 1), padding='same', name='conv_preds')(x) x = layers.Reshape((classes, ), name='reshape_2')(x) x = layers.Activation('softmax', name='act_softmax')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling3D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling3D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = keras_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name='mobilenet_%0.2f_%s' % (alpha, rows)) # Load weights. if weights == 'imagenet': if alpha == 1.0: alpha_text = '1_0' elif alpha == 0.75: alpha_text = '7_5' elif alpha == 0.50: alpha_text = '5_0' else: alpha_text = '2_5' if include_top: model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows) weight_path = BASE_WEIGHT_PATH + model_name weights_path = keras_utils.get_file(model_name, weight_path, cache_subdir='models') else: model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows) weight_path = BASE_WEIGHT_PATH + model_name weights_path = keras_utils.get_file(model_name, weight_path, cache_subdir='models') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model
def MobileNetV2(input_shape=None, alpha=1.0, include_top=True, weights='imagenet', input_tensor=None, pooling=None, classes=1000, **kwargs): """Instantiates the MobileNetV2 architecture. # Arguments input_shape: optional shape tuple, to be specified if you would like to use a model with an input img resolution that is not (224, 224, 3). It should have exactly 3 inputs channels (224, 224, 3). You can also omit this option if you would like to infer input_shape from an input_tensor. If you choose to include both input_tensor and input_shape then input_shape will be used if they match, if the shapes do not match then we will throw an error. E.g. `(160, 160, 3)` would be one valid value. alpha: controls the width of the network. This is known as the width multiplier in the MobileNetV2 paper, but the name is kept for consistency with MobileNetV1 in Keras. - If `alpha` < 1.0, proportionally decreases the number of filters in each layer. - If `alpha` > 1.0, proportionally increases the number of filters in each layer. - If `alpha` = 1, default number of filters from the paper are used at each layer. include_top: whether to include the fully-connected layer at the top of the network. weights: one of `None` (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. input_tensor: optional Keras tensor (i.e. output of `layers.Input()`) to use as image input for the model. pooling: Optional pooling mode for feature extraction when `include_top` is `False`. - `None` means that the output of the model will be the 4D tensor output of the last convolutional block. - `avg` means that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor. - `max` means that global max pooling will be applied. classes: optional number of classes to classify images into, only to be specified if `include_top` is True, and if no `weights` argument is specified. # Returns A Keras model instance. # Raises ValueError: in case of invalid argument for `weights`, or invalid input shape or invalid alpha, rows when weights='imagenet' """ global backend, layers, models, keras_utils backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs) if not (weights in {'imagenet', None} or os.path.exists(weights)): raise ValueError('The `weights` argument should be either ' '`None` (random initialization), `imagenet` ' '(pre-training on ImageNet), ' 'or the path to the weights file to be loaded.') if weights == 'imagenet' and include_top and classes != 1000: raise ValueError( 'If using `weights` as `"imagenet"` with `include_top` ' 'as true, `classes` should be 1000') # Determine proper input shape and default size. # If both input_shape and input_tensor are used, they should match if input_shape is not None and input_tensor is not None: try: is_input_t_tensor = backend.is_keras_tensor(input_tensor) except ValueError: try: is_input_t_tensor = backend.is_keras_tensor( keras_utils.get_source_inputs(input_tensor)) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is not type input_tensor') if is_input_t_tensor: if backend.image_data_format == 'channels_first': if backend.int_shape(input_tensor)[1] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: if backend.int_shape(input_tensor)[2] != input_shape[1]: raise ValueError( 'input_shape: ', input_shape, 'and input_tensor: ', input_tensor, 'do not meet the same shape requirements') else: raise ValueError('input_tensor specified: ', input_tensor, 'is not a keras tensor') # If input_shape is None, infer shape from input_tensor if input_shape is None and input_tensor is not None: try: backend.is_keras_tensor(input_tensor) except ValueError: raise ValueError('input_tensor: ', input_tensor, 'is type: ', type(input_tensor), 'which is not a valid type') if input_shape is None and not backend.is_keras_tensor(input_tensor): default_size = 224 elif input_shape is None and backend.is_keras_tensor(input_tensor): if backend.image_data_format() == 'channels_first': rows = backend.int_shape(input_tensor)[2] cols = backend.int_shape(input_tensor)[3] else: rows = backend.int_shape(input_tensor)[1] cols = backend.int_shape(input_tensor)[2] if rows == cols and rows in [96, 128, 160, 192, 224]: default_size = rows else: default_size = 224 # If input_shape is None and no input_tensor elif input_shape is None: default_size = 224 # If input_shape is not None, assume default size else: if backend.image_data_format() == 'channels_first': rows = input_shape[1] cols = input_shape[2] else: rows = input_shape[0] cols = input_shape[1] if rows == cols and rows in [96, 128, 160, 192, 224]: default_size = rows else: default_size = 224 if backend.image_data_format() == 'channels_last': row_axis, col_axis = (0, 1) else: row_axis, col_axis = (1, 2) rows = input_shape[row_axis] cols = input_shape[col_axis] if weights == 'imagenet': if alpha not in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]: raise ValueError('If imagenet weights are being loaded, ' 'alpha can be one of `0.35`, `0.50`, `0.75`, ' '`1.0`, `1.3` or `1.4` only.') if rows != cols or rows not in [96, 128, 160, 192, 224]: rows = 224 warnings.warn('`input_shape` is undefined or non-square, ' 'or `rows` is not in [96, 128, 160, 192, 224].' ' Weights for input shape (224, 224) will be' ' loaded as the default.') if input_tensor is None: img_input = layers.Input(shape=input_shape) else: if not backend.is_keras_tensor(input_tensor): img_input = layers.Input(tensor=input_tensor, shape=input_shape) else: img_input = input_tensor channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1 first_block_filters = _make_divisible(32 * alpha, 8) x = layers.ZeroPadding3D(padding=correct_pad(backend, img_input, 3), name='Conv1_pad')(img_input) x = layers.Conv3D(first_block_filters, kernel_size=3, strides=(2, 2, 2), padding='valid', use_bias=False, name='Conv1')(x) x = layers.BatchNormalization(axis=channel_axis, epsilon=1e-3, momentum=0.999, name='bn_Conv1')(x) x = layers.ReLU(6., name='Conv1_relu')(x) x = _inverted_res_block(x, filters=16, alpha=alpha, stride=1, expansion=1, block_id=0) x = _inverted_res_block(x, filters=24, alpha=alpha, stride=2, expansion=6, block_id=1) x = _inverted_res_block(x, filters=24, alpha=alpha, stride=1, expansion=6, block_id=2) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=2, expansion=6, block_id=3) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=4) x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=5) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=2, expansion=6, block_id=6) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=7) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=8) x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=9) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=10) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=11) x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=12) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=2, expansion=6, block_id=13) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=14) x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=15) x = _inverted_res_block(x, filters=320, alpha=alpha, stride=1, expansion=6, block_id=16) # no alpha applied to last conv as stated in the paper: # if the width multiplier is greater than 1 we # increase the number of output channels if alpha > 1.0: last_block_filters = _make_divisible(1280 * alpha, 8) else: last_block_filters = 1280 x = layers.Conv3D(last_block_filters, kernel_size=1, use_bias=False, name='Conv_1')(x) x = layers.BatchNormalization(axis=channel_axis, epsilon=1e-3, momentum=0.999, name='Conv_1_bn')(x) x = layers.ReLU(6., name='out_relu')(x) if include_top: x = layers.GlobalAveragePooling3D()(x) x = layers.Dense(classes, activation='softmax', use_bias=True, name='Logits')(x) else: if pooling == 'avg': x = layers.GlobalAveragePooling3D()(x) elif pooling == 'max': x = layers.GlobalMaxPooling3D()(x) # Ensure that the model takes into account # any potential predecessors of `input_tensor`. if input_tensor is not None: inputs = keras_utils.get_source_inputs(input_tensor) else: inputs = img_input # Create model. model = models.Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows)) # Load weights. if weights == 'imagenet': if include_top: model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + str(alpha) + '_' + str(rows) + '.h5') weight_path = BASE_WEIGHT_PATH + model_name weights_path = keras_utils.get_file(model_name, weight_path, cache_subdir='models') else: model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' + str(alpha) + '_' + str(rows) + '_no_top' + '.h5') weight_path = BASE_WEIGHT_PATH + model_name weights_path = keras_utils.get_file(model_name, weight_path, cache_subdir='models') model.load_weights(weights_path) elif weights is not None: model.load_weights(weights) return model