1# Copyright 2016 The TensorFlow Authors. All Rights Reserved. 2# 3# Licensed under the Apache License, Version 2.0 (the "License"); 4# you may not use this file except in compliance with the License. 5# You may obtain a copy of the License at 6# 7# http://www.apache.org/licenses/LICENSE-2.0 8# 9# Unless required by applicable law or agreed to in writing, software 10# distributed under the License is distributed on an "AS IS" BASIS, 11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12# See the License for the specific language governing permissions and 13# limitations under the License. 14# ============================================================================== 15"""Contains the model definition for the OverFeat network. 16 17The definition for the network was obtained from: 18 OverFeat: Integrated Recognition, Localization and Detection using 19 Convolutional Networks 20 Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus and 21 Yann LeCun, 2014 22 http://arxiv.org/abs/1312.6229 23 24Usage: 25 with slim.arg_scope(overfeat.overfeat_arg_scope()): 26 outputs, end_points = overfeat.overfeat(inputs) 27 28@@overfeat 29""" 30 31from __future__ import absolute_import 32from __future__ import division 33from __future__ import print_function 34 35from tensorflow.contrib import layers 36from tensorflow.contrib.framework.python.ops import arg_scope 37from tensorflow.contrib.layers.python.layers import layers as layers_lib 38from tensorflow.contrib.layers.python.layers import regularizers 39from tensorflow.contrib.layers.python.layers import utils 40from tensorflow.python.ops import array_ops 41from tensorflow.python.ops import init_ops 42from tensorflow.python.ops import nn_ops 43from tensorflow.python.ops import variable_scope 44 45trunc_normal = lambda stddev: init_ops.truncated_normal_initializer(0.0, stddev) 46 47 48def overfeat_arg_scope(weight_decay=0.0005): 49 with arg_scope( 50 [layers.conv2d, layers_lib.fully_connected], 51 activation_fn=nn_ops.relu, 52 weights_regularizer=regularizers.l2_regularizer(weight_decay), 53 biases_initializer=init_ops.zeros_initializer()): 54 with arg_scope([layers.conv2d], padding='SAME'): 55 with arg_scope([layers_lib.max_pool2d], padding='VALID') as arg_sc: 56 return arg_sc 57 58 59def overfeat(inputs, 60 num_classes=1000, 61 is_training=True, 62 dropout_keep_prob=0.5, 63 spatial_squeeze=True, 64 scope='overfeat'): 65 """Contains the model definition for the OverFeat network. 66 67 The definition for the network was obtained from: 68 OverFeat: Integrated Recognition, Localization and Detection using 69 Convolutional Networks 70 Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus and 71 Yann LeCun, 2014 72 http://arxiv.org/abs/1312.6229 73 74 Note: All the fully_connected layers have been transformed to conv2d layers. 75 To use in classification mode, resize input to 231x231. To use in fully 76 convolutional mode, set spatial_squeeze to false. 77 78 Args: 79 inputs: a tensor of size [batch_size, height, width, channels]. 80 num_classes: number of predicted classes. 81 is_training: whether or not the model is being trained. 82 dropout_keep_prob: the probability that activations are kept in the dropout 83 layers during training. 84 spatial_squeeze: whether or not should squeeze the spatial dimensions of the 85 outputs. Useful to remove unnecessary dimensions for classification. 86 scope: Optional scope for the variables. 87 88 Returns: 89 the last op containing the log predictions and end_points dict. 90 91 """ 92 with variable_scope.variable_scope(scope, 'overfeat', [inputs]) as sc: 93 end_points_collection = sc.name + '_end_points' 94 # Collect outputs for conv2d, fully_connected and max_pool2d 95 with arg_scope( 96 [layers.conv2d, layers_lib.fully_connected, layers_lib.max_pool2d], 97 outputs_collections=end_points_collection): 98 net = layers.conv2d( 99 inputs, 64, [11, 11], 4, padding='VALID', scope='conv1') 100 net = layers_lib.max_pool2d(net, [2, 2], scope='pool1') 101 net = layers.conv2d(net, 256, [5, 5], padding='VALID', scope='conv2') 102 net = layers_lib.max_pool2d(net, [2, 2], scope='pool2') 103 net = layers.conv2d(net, 512, [3, 3], scope='conv3') 104 net = layers.conv2d(net, 1024, [3, 3], scope='conv4') 105 net = layers.conv2d(net, 1024, [3, 3], scope='conv5') 106 net = layers_lib.max_pool2d(net, [2, 2], scope='pool5') 107 with arg_scope( 108 [layers.conv2d], 109 weights_initializer=trunc_normal(0.005), 110 biases_initializer=init_ops.constant_initializer(0.1)): 111 # Use conv2d instead of fully_connected layers. 112 net = layers.conv2d(net, 3072, [6, 6], padding='VALID', scope='fc6') 113 net = layers_lib.dropout( 114 net, dropout_keep_prob, is_training=is_training, scope='dropout6') 115 net = layers.conv2d(net, 4096, [1, 1], scope='fc7') 116 net = layers_lib.dropout( 117 net, dropout_keep_prob, is_training=is_training, scope='dropout7') 118 net = layers.conv2d( 119 net, 120 num_classes, [1, 1], 121 activation_fn=None, 122 normalizer_fn=None, 123 biases_initializer=init_ops.zeros_initializer(), 124 scope='fc8') 125 # Convert end_points_collection into a end_point dict. 126 end_points = utils.convert_collection_to_dict(end_points_collection) 127 if spatial_squeeze: 128 net = array_ops.squeeze(net, [1, 2], name='fc8/squeezed') 129 end_points[sc.name + '/fc8'] = net 130 return net, end_points 131