def _dense_block(inputs, num_layers, num_filters, growth_rate, grow_num_filters=True, scope=None, outputs_collections=None, filter_type=None, verbose=None): with tf.variable_scope(scope, 'dense_blockx', [inputs]) as sc: net = inputs end_point = 'conv_block' + str(num_layers) net = attention_filter.add_attention_filter(net, end_point, verbose=verbose, filter_type=filter_type) if grow_num_filters: num_filters += growth_rate net = slim.utils.collect_named_outputs(outputs_collections, sc.name, net) return net, num_filters
def inception_v1_base(inputs, final_endpoint='Mixed_5c', include_root_block=True, scope='InceptionV1'): """Defines the Inception V1 base 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/pdf/1409.4842v1.pdf. Args: inputs: a tensor of size [batch_size, height, width, channels]. final_endpoint: specifies the endpoint to construct the network up to. It can be one of ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b', 'Mixed_5c']. If include_root_block is False, ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3', 'MaxPool_3a_3x3'] will not be available. include_root_block: If True, include the convolution and max-pooling layers before the inception modules. If False, excludes those layers. scope: Optional variable_scope. Returns: A dictionary from components of the network to the corresponding activation. Raises: ValueError: if final_endpoint is not set to one of the predefined values. """ end_points = {} with tf.variable_scope(scope, 'InceptionV1', [inputs]): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=trunc_normal(0.01)): with slim.arg_scope([slim.conv2d, slim.max_pool2d], stride=1, padding='SAME'): end_point = 'Mixed_5c' net = inputs net = attention_filter.add_attention_filter(net, end_point) # atten_var = tf.get_variable("atten_" + end_point, [net.shape[1], net.shape[2], 1], dtype=tf.float32, # initializer=tf.contrib.layers.xavier_initializer()) # print(atten_var) # atten_var_norm = atten_var / tf.norm(atten_var) # atten_var_gate = tf.Variable(False, name="gate_" + end_point) # net = tf.cond(atten_var_gate, lambda: tf.multiply(atten_var_norm, net), lambda: tf.identity(net)) end_points[end_point] = net if final_endpoint == end_point: return net, end_points raise ValueError('Unknown final endpoint %s' % final_endpoint)
def resnet_v2(inputs, blocks, num_classes=None, is_training=True, global_pool=True, output_stride=None, include_root_block=True, spatial_squeeze=True, filter_type=None, verbose=None, reuse=None, scope=None): """Generator for v2 (preactivation) ResNet models. This function generates a family of ResNet v2 models. See the resnet_v2_*() methods for specific model instantiations, obtained by selecting different block instantiations that produce ResNets of various depths. Training for image classification on Imagenet is usually done with [224, 224] inputs, resulting in [7, 7] feature maps at the output of the last ResNet block for the ResNets defined in [1] that have nominal stride equal to 32. However, for dense prediction tasks we advise that one uses inputs with spatial dimensions that are multiples of 32 plus 1, e.g., [321, 321]. In this case the feature maps at the ResNet output will have spatial shape [(height - 1) / output_stride + 1, (width - 1) / output_stride + 1] and corners exactly aligned with the input image corners, which greatly facilitates alignment of the features to the image. Using as input [225, 225] images results in [8, 8] feature maps at the output of the last ResNet block. For dense prediction tasks, the ResNet needs to run in fully-convolutional (FCN) mode and global_pool needs to be set to False. The ResNets in [1, 2] all have nominal stride equal to 32 and a good choice in FCN mode is to use output_stride=16 in order to increase the density of the computed features at small computational and memory overhead, cf. http://arxiv.org/abs/1606.00915. Args: inputs: A tensor of size [batch, height_in, width_in, channels]. blocks: A list of length equal to the number of ResNet blocks. Each element is a resnet_utils.Block object describing the units in the block. num_classes: Number of predicted classes for classification tasks. If 0 or None, we return the features before the logit layer. is_training: whether batch_norm layers are in training mode. global_pool: If True, we perform global average pooling before computing the logits. Set to True for image classification, False for dense prediction. output_stride: If None, then the output will be computed at the nominal network stride. If output_stride is not None, it specifies the requested ratio of input to output spatial resolution. include_root_block: If True, include the initial convolution followed by max-pooling, if False excludes it. If excluded, `inputs` should be the results of an activation-less convolution. spatial_squeeze: if True, logits is of shape [B, C], if false logits is of shape [B, 1, 1, C], where B is batch_size and C is number of classes. To use this parameter, the input images must be smaller than 300x300 pixels, in which case the output logit layer does not contain spatial information and can be removed. reuse: whether or not the network and its variables should be reused. To be able to reuse 'scope' must be given. scope: Optional variable_scope. Returns: net: A rank-4 tensor of size [batch, height_out, width_out, channels_out]. If global_pool is False, then height_out and width_out are reduced by a factor of output_stride compared to the respective height_in and width_in, else both height_out and width_out equal one. If num_classes is 0 or None, then net is the output of the last ResNet block, potentially after global average pooling. If num_classes is a non-zero integer, net contains the pre-softmax activations. end_points: A dictionary from components of the network to the corresponding activation. Raises: ValueError: If the target output_stride is not valid. """ with tf.variable_scope(scope, 'resnet_v2', [inputs], reuse=reuse) as sc: end_points_collection = sc.original_name_scope + '_end_points' with slim.arg_scope( [slim.conv2d, bottleneck, resnet_utils.stack_blocks_dense], outputs_collections=end_points_collection): with slim.arg_scope([slim.batch_norm], is_training=is_training): net = inputs end_points = slim.utils.convert_collection_to_dict( end_points_collection) print(net) end_point = 'resnet_v2_50' net = attention_filter.add_attention_filter( net, end_point, verbose=verbose, filter_type=filter_type) if global_pool: # Global average pooling. net = tf.reduce_mean(net, [1, 2], name='pool5', keep_dims=True) end_points['global_pool'] = net if num_classes: net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, normalizer_fn=None, scope='logits') end_points[sc.name + '/logits'] = net if spatial_squeeze: net = tf.squeeze(net, [1, 2], name='SpatialSqueeze') end_points[sc.name + '/spatial_squeeze'] = net end_points['predictions'] = slim.softmax( net, scope='predictions') return net, end_points
def inception_v1_base(inputs, final_endpoint='Mixed_5c', include_root_block=True, filter_type=None, verbose=None, scope='InceptionV1'): """Defines the Inception V1 base 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/pdf/1409.4842v1.pdf. Args: inputs: a tensor of size [batch_size, height, width, channels]. final_endpoint: specifies the endpoint to construct the network up to. It can be one of ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b', 'Mixed_5c']. If include_root_block is False, ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3', 'MaxPool_3a_3x3'] will not be available. include_root_block: If True, include the convolution and max-pooling layers before the inception modules. If False, excludes those layers. scope: Optional variable_scope. Returns: A dictionary from components of the network to the corresponding activation. Raises: ValueError: if final_endpoint is not set to one of the predefined values. """ end_points = {} with tf.variable_scope(scope, 'InceptionV1', [inputs]): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=trunc_normal(0.01)): with slim.arg_scope([slim.conv2d, slim.max_pool2d], stride=1, padding='SAME'): net = inputs if include_root_block: end_point = 'Conv2d_1a_7x7' net = slim.conv2d(inputs, 64, [7, 7], stride=2, scope=end_point) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'MaxPool_2a_3x3' net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Conv2d_2b_1x1' net = slim.conv2d(net, 64, [1, 1], scope=end_point) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Conv2d_2c_3x3' net = slim.conv2d(net, 192, [3, 3], scope=end_point) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'MaxPool_3a_3x3' net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Mixed_3b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 96, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 128, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 16, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 32, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 32, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Mixed_3c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 192, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'MaxPool_4a_3x3' net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Mixed_4b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 96, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 208, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 16, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 48, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Mixed_4c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 112, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 224, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 24, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if final_endpoint == end_point: return net, end_points net = attention_filter.add_attention_filter( net, end_point, verbose=verbose, filter_type=filter_type) end_point = 'Mixed_4d' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 256, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 24, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Mixed_4e' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 112, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 144, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 288, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) net = attention_filter.add_attention_filter( net, end_point, verbose=verbose, filter_type=filter_type) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Mixed_4f' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 256, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 320, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) net = attention_filter.add_attention_filter( net, end_point, verbose=verbose, filter_type=filter_type) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'MaxPool_5a_2x2' net = slim.max_pool2d(net, [2, 2], stride=2, scope=end_point) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Mixed_5b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 256, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 320, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0a_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) net = attention_filter.add_attention_filter( net, end_point, verbose=verbose, filter_type=filter_type) end_points[end_point] = net if final_endpoint == end_point: return net, end_points end_point = 'Mixed_5c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 384, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1') net = tf.concat( axis=3, values=[branch_0, branch_1, branch_2, branch_3]) net = attention_filter.add_attention_filter( net, end_point, verbose=verbose, filter_type=filter_type) end_points[end_point] = net if final_endpoint == end_point: return net, end_points raise ValueError('Unknown final endpoint %s' % final_endpoint)