def reduction_a(net, k, l, m, n): with tf.compat.v1.variable_scope('Branch_0'): tower_conv = slim.conv2d(net, n, 3, stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.compat.v1.variable_scope('Branch_1'): tower_conv1_0 = slim.conv2d(net, k, 1, scope='Conv2d_0a_1x1') tower_conv1_1 = slim.conv2d(tower_conv1_0, l, 3, scope='Conv2d_0b_3x3') tower_conv1_2 = slim.conv2d(tower_conv1_1, m, 3, stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.compat.v1.variable_scope('Branch_2'): tower_pool = slim.max_pool2d(net, 3, stride=2, padding='VALID', scope='MaxPool_1a_3x3') net = tf.concat([tower_conv, tower_conv1_2, tower_pool], 3) return net
def block17(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None): """Builds the 17x17 resnet block.""" with tf.variable_scope(scope, 'Block17', [net], reuse=reuse): with tf.variable_scope('Branch_0'): tower_conv = slim.conv2d(net, 192, 1, scope='Conv2d_1x1') with tf.variable_scope('Branch_1'): tower_conv1_0 = slim.conv2d(net, 128, 1, scope='Conv2d_0a_1x1') tower_conv1_1 = slim.conv2d(tower_conv1_0, 160, [1, 7], scope='Conv2d_0b_1x7') tower_conv1_2 = slim.conv2d(tower_conv1_1, 192, [7, 1], scope='Conv2d_0c_7x1') mixed = tf.concat(axis=3, values=[tower_conv, tower_conv1_2]) up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None, activation_fn=None, scope='Conv2d_1x1') scaled_up = up * scale if activation_fn == tf.nn.relu6: # Use clip_by_value to simulate bandpass activation. scaled_up = tf.clip_by_value(scaled_up, -6.0, 6.0) net += scaled_up if activation_fn: net = activation_fn(net) return net
def block_reduction_a(inputs, scope=None, reuse=None): """Builds Reduction-A block for Inception v4 network.""" # By default use stride=1 and SAME padding with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d], stride=1, padding='SAME'): with tf.variable_scope(scope, 'BlockReductionA', [inputs], reuse=reuse): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(inputs, 384, [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(inputs, 192, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 224, [3, 3], scope='Conv2d_0b_3x3') branch_1 = slim.conv2d(branch_1, 256, [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.max_pool2d(inputs, [3, 3], stride=2, padding='VALID', scope='MaxPool_1a_3x3') return tf.concat(axis=3, values=[branch_0, branch_1, branch_2])
def lenet(images, num_classes=10, is_training=False, dropout_keep_prob=0.5, prediction_fn=slim.softmax, scope='LeNet'): """Creates a variant of the LeNet model. Note that since the output is a set of 'logits', the values fall in the interval of (-infinity, infinity). Consequently, to convert the outputs to a probability distribution over the characters, one will need to convert them using the softmax function: logits = lenet.lenet(images, is_training=False) probabilities = tf.nn.softmax(logits) predictions = tf.argmax(logits, 1) Args: images: A batch of `Tensors` of size [batch_size, height, width, channels]. num_classes: the number of classes in the dataset. If 0 or None, the logits layer is omitted and the input features to the logits layer are returned instead. is_training: specifies whether or not we're currently training the model. This variable will determine the behaviour of the dropout layer. dropout_keep_prob: the percentage of activation values that are retained. prediction_fn: a function to get predictions out of logits. scope: Optional variable_scope. Returns: net: a 2D Tensor with the logits (pre-softmax activations) if num_classes is a non-zero integer, or the inon-dropped-out nput to the logits layer if num_classes is 0 or None. end_points: a dictionary from components of the network to the corresponding activation. """ end_points = {} with tf.variable_scope(scope, 'LeNet', [images]): net = end_points['conv1'] = slim.conv2d(images, 32, [5, 5], scope='conv1') net = end_points['pool1'] = slim.max_pool2d(net, [2, 2], 2, scope='pool1') net = end_points['conv2'] = slim.conv2d(net, 64, [5, 5], scope='conv2') net = end_points['pool2'] = slim.max_pool2d(net, [2, 2], 2, scope='pool2') net = slim.flatten(net) end_points['Flatten'] = net net = end_points['fc3'] = slim.fully_connected(net, 1024, scope='fc3') if not num_classes: return net, end_points net = end_points['dropout3'] = slim.dropout( net, dropout_keep_prob, is_training=is_training, scope='dropout3') logits = end_points['Logits'] = slim.fully_connected( net, num_classes, activation_fn=None, scope='fc4') end_points['Predictions'] = prediction_fn(logits, scope='Predictions') return logits, end_points
def block_inception_c(inputs, scope=None, reuse=None): """Builds Inception-C block for Inception v4 network.""" # By default use stride=1 and SAME padding with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d], stride=1, padding='SAME'): with tf.variable_scope(scope, 'BlockInceptionC', [inputs], reuse=reuse): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(inputs, 256, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(inputs, 384, [1, 1], scope='Conv2d_0a_1x1') branch_1 = tf.concat(axis=3, values=[ slim.conv2d(branch_1, 256, [1, 3], scope='Conv2d_0b_1x3'), slim.conv2d(branch_1, 256, [3, 1], scope='Conv2d_0c_3x1') ]) with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(inputs, 384, [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, 448, [3, 1], scope='Conv2d_0b_3x1') branch_2 = slim.conv2d(branch_2, 512, [1, 3], scope='Conv2d_0c_1x3') branch_2 = tf.concat(axis=3, values=[ slim.conv2d(branch_2, 256, [1, 3], scope='Conv2d_0d_1x3'), slim.conv2d(branch_2, 256, [3, 1], scope='Conv2d_0e_3x1') ]) with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(inputs, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d(branch_3, 256, [1, 1], scope='Conv2d_0b_1x1') return tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
def _imagenet_stem(inputs, hparams, stem_cell): """Stem used for models trained on ImageNet.""" num_stem_cells = 2 # 149 x 149 x 32 num_stem_filters = int(32 * hparams.stem_multiplier) net = slim.conv2d(inputs, num_stem_filters, [3, 3], stride=2, scope='conv0', padding='VALID') net = slim.batch_norm(net, scope='conv0_bn') # Run the reduction cells cell_outputs = [None, net] filter_scaling = 1.0 / (hparams.filter_scaling_rate**num_stem_cells) for cell_num in range(num_stem_cells): net = stem_cell(net, scope='cell_stem_{}'.format(cell_num), filter_scaling=filter_scaling, stride=2, prev_layer=cell_outputs[-2], cell_num=cell_num) cell_outputs.append(net) filter_scaling *= hparams.filter_scaling_rate return net, cell_outputs
def conv2d_same(inputs, num_outputs, kernel_size, stride, rate=1, scope=None): """Strided 2-D convolution with 'SAME' padding. When stride > 1, then we do explicit zero-padding, followed by conv2d with 'VALID' padding. Note that net = conv2d_same(inputs, num_outputs, 3, stride=stride) is equivalent to net = slim.conv2d(inputs, num_outputs, 3, stride=1, padding='SAME') net = subsample(net, factor=stride) whereas net = slim.conv2d(inputs, num_outputs, 3, stride=stride, padding='SAME') is different when the input's height or width is even, which is why we add the current function. For more details, see ResnetUtilsTest.testConv2DSameEven(). Args: inputs: A 4-D tensor of size [batch, height_in, width_in, channels]. num_outputs: An integer, the number of output filters. kernel_size: An int with the kernel_size of the filters. stride: An integer, the output stride. rate: An integer, rate for atrous convolution. scope: Scope. Returns: output: A 4-D tensor of size [batch, height_out, width_out, channels] with the convolution output. """ if stride == 1: return slim.conv2d(inputs, num_outputs, kernel_size, stride=1, rate=rate, padding='SAME', scope=scope) else: kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1) pad_total = kernel_size_effective - 1 pad_beg = pad_total // 2 pad_end = pad_total - pad_beg inputs = tf.pad(inputs, [[0, 0], [pad_beg, pad_end], [pad_beg, pad_end], [0, 0]]) return slim.conv2d(inputs, num_outputs, kernel_size, stride=stride, rate=rate, padding='VALID', scope=scope)
def block35(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None): """Builds the 35x35 resnet block.""" with tf.compat.v1.variable_scope(scope, 'Block35', [net], reuse=reuse): with tf.compat.v1.variable_scope('Branch_0'): tower_conv = slim.conv2d(net, 32, 1, scope='Conv2d_1x1') with tf.compat.v1.variable_scope('Branch_1'): tower_conv1_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1') tower_conv1_1 = slim.conv2d(tower_conv1_0, 32, 3, scope='Conv2d_0b_3x3') with tf.compat.v1.variable_scope('Branch_2'): tower_conv2_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1') tower_conv2_1 = slim.conv2d(tower_conv2_0, 32, 3, scope='Conv2d_0b_3x3') tower_conv2_2 = slim.conv2d(tower_conv2_1, 32, 3, scope='Conv2d_0c_3x3') mixed = tf.concat([tower_conv, tower_conv1_1, tower_conv2_2], 3) up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None, activation_fn=None, scope='Conv2d_1x1') net += scale * up if activation_fn: net = activation_fn(net) return net
def reduction_b(net): with tf.compat.v1.variable_scope('Branch_0'): tower_conv = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1') tower_conv_1 = slim.conv2d(tower_conv, 384, 3, stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.compat.v1.variable_scope('Branch_1'): tower_conv1 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1') tower_conv1_1 = slim.conv2d(tower_conv1, 256, 3, stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.compat.v1.variable_scope('Branch_2'): tower_conv2 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1') tower_conv2_1 = slim.conv2d(tower_conv2, 256, 3, scope='Conv2d_0b_3x3') tower_conv2_2 = slim.conv2d(tower_conv2_1, 256, 3, stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.compat.v1.variable_scope('Branch_3'): tower_pool = slim.max_pool2d(net, 3, stride=2, padding='VALID', scope='MaxPool_1a_3x3') net = tf.concat([tower_conv_1, tower_conv1_1, tower_conv2_2, tower_pool], 3) return net
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
def _build_aux_head(net, end_points, num_classes, hparams, scope): """Auxiliary head used for all models across all datasets.""" with tf.variable_scope(scope): aux_logits = tf.identity(net) with tf.variable_scope('aux_logits'): aux_logits = slim.avg_pool2d(aux_logits, [5, 5], stride=3, padding='VALID') aux_logits = slim.conv2d(aux_logits, 128, [1, 1], scope='proj') aux_logits = slim.batch_norm(aux_logits, scope='aux_bn0') aux_logits = tf.nn.relu(aux_logits) # Shape of feature map before the final layer. shape = aux_logits.shape if hparams.data_format == 'NHWC': shape = shape[1:3] else: shape = shape[2:4] aux_logits = slim.conv2d(aux_logits, 768, shape, padding='VALID') aux_logits = slim.batch_norm(aux_logits, scope='aux_bn1') aux_logits = tf.nn.relu(aux_logits) aux_logits = tf.contrib.layers.flatten(aux_logits) aux_logits = slim.fully_connected(aux_logits, num_classes) end_points['AuxLogits'] = aux_logits
def block17(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None): """Builds the 17x17 resnet block.""" with tf.compat.v1.variable_scope(scope, 'Block17', [net], reuse=reuse): with tf.compat.v1.variable_scope('Branch_0'): tower_conv = slim.conv2d(net, 128, 1, scope='Conv2d_1x1') with tf.compat.v1.variable_scope('Branch_1'): tower_conv1_0 = slim.conv2d(net, 128, 1, scope='Conv2d_0a_1x1') tower_conv1_1 = slim.conv2d(tower_conv1_0, 128, [1, 7], scope='Conv2d_0b_1x7') tower_conv1_2 = slim.conv2d(tower_conv1_1, 128, [7, 1], scope='Conv2d_0c_7x1') mixed = tf.concat([tower_conv, tower_conv1_2], 3) up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None, activation_fn=None, scope='Conv2d_1x1') net += scale * up if activation_fn: net = activation_fn(net) return net
def resnet_v1(inputs, blocks, num_classes=None, is_training=True, global_pool=True, output_stride=None, include_root_block=True, spatial_squeeze=True, reuse=None, scope=None): """Generator for v1 ResNet models. This function generates a family of ResNet v1 models. See the resnet_v1_*() 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. 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 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_v1', [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 if include_root_block: if output_stride is not None: if output_stride % 4 != 0: raise ValueError('The output_stride needs to be a multiple of 4.') output_stride /= 4 net = resnet_utils.conv2d_same(net, 64, 7, stride=2, scope='conv1') net = slim.max_pool2d(net, [3, 3], stride=2, scope='pool1') net = resnet_utils.stack_blocks_dense(net, blocks, output_stride) # Convert end_points_collection into a dictionary of end_points. end_points = slim.utils.convert_collection_to_dict( end_points_collection) 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 osvos(inputs, scope='osvos'): """Defines the OSVOS network Args: inputs: Tensorflow placeholder that contains the input image scope: Scope name for the network Returns: net: Output Tensor of the network end_points: Dictionary with all Tensors of the network """ im_size = tf.shape(inputs) with tf.variable_scope(scope, 'osvos', [inputs]) as sc: end_points_collection = sc.name + '_end_points' # Collect outputs of all intermediate layers. with slim.arg_scope([slim.conv2d, slim.max_pool2d], padding='SAME', outputs_collections=end_points_collection): net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1') net = slim.max_pool2d(net, [2, 2], scope='pool1') net_2 = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2') net = slim.max_pool2d(net_2, [2, 2], scope='pool2') net_3 = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3') net = slim.max_pool2d(net_3, [2, 2], scope='pool3') net_4 = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4') net = slim.max_pool2d(net_4, [2, 2], scope='pool4') net_5 = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5') # Get side outputs of the network with slim.arg_scope([slim.conv2d], activation_fn=None): side_2 = slim.conv2d(net_2, 16, [3, 3], scope='conv2_2_16') side_3 = slim.conv2d(net_3, 16, [3, 3], scope='conv3_3_16') side_4 = slim.conv2d(net_4, 16, [3, 3], scope='conv4_3_16') side_5 = slim.conv2d(net_5, 16, [3, 3], scope='conv5_3_16') # Supervise side outputs side_2_s = slim.conv2d(side_2, 1, [1, 1], scope='score-dsn_2') side_3_s = slim.conv2d(side_3, 1, [1, 1], scope='score-dsn_3') side_4_s = slim.conv2d(side_4, 1, [1, 1], scope='score-dsn_4') side_5_s = slim.conv2d(side_5, 1, [1, 1], scope='score-dsn_5') with slim.arg_scope([slim.convolution2d_transpose], activation_fn=None, biases_initializer=None, padding='VALID', outputs_collections=end_points_collection, trainable=False): # Side outputs side_2_s = slim.convolution2d_transpose( side_2_s, 1, 4, 2, scope='score-dsn_2-up') side_2_s = crop_features(side_2_s, im_size) utils.collect_named_outputs(end_points_collection, 'osvos/score-dsn_2-cr', side_2_s) side_3_s = slim.convolution2d_transpose( side_3_s, 1, 8, 4, scope='score-dsn_3-up') side_3_s = crop_features(side_3_s, im_size) utils.collect_named_outputs(end_points_collection, 'osvos/score-dsn_3-cr', side_3_s) side_4_s = slim.convolution2d_transpose( side_4_s, 1, 16, 8, scope='score-dsn_4-up') side_4_s = crop_features(side_4_s, im_size) utils.collect_named_outputs(end_points_collection, 'osvos/score-dsn_4-cr', side_4_s) side_5_s = slim.convolution2d_transpose( side_5_s, 1, 32, 16, scope='score-dsn_5-up') side_5_s = crop_features(side_5_s, im_size) utils.collect_named_outputs(end_points_collection, 'osvos/score-dsn_5-cr', side_5_s) # Main output side_2_f = slim.convolution2d_transpose( side_2, 16, 4, 2, scope='score-multi2-up') side_2_f = crop_features(side_2_f, im_size) utils.collect_named_outputs(end_points_collection, 'osvos/side-multi2-cr', side_2_f) side_3_f = slim.convolution2d_transpose( side_3, 16, 8, 4, scope='score-multi3-up') side_3_f = crop_features(side_3_f, im_size) utils.collect_named_outputs(end_points_collection, 'osvos/side-multi3-cr', side_3_f) side_4_f = slim.convolution2d_transpose( side_4, 16, 16, 8, scope='score-multi4-up') side_4_f = crop_features(side_4_f, im_size) utils.collect_named_outputs(end_points_collection, 'osvos/side-multi4-cr', side_4_f) side_5_f = slim.convolution2d_transpose( side_5, 16, 32, 16, scope='score-multi5-up') side_5_f = crop_features(side_5_f, im_size) utils.collect_named_outputs(end_points_collection, 'osvos/side-multi5-cr', side_5_f) concat_side = tf.concat( [side_2_f, side_3_f, side_4_f, side_5_f], axis=3) net = slim.conv2d(concat_side, 1, [1, 1], scope='upscore-fuse') end_points = slim.utils.convert_collection_to_dict( end_points_collection) return net, end_points
def inception_v2(inputs, num_classes=1000, is_training=True, dropout_keep_prob=0.8, min_depth=16, depth_multiplier=1.0, prediction_fn=slim.softmax, spatial_squeeze=True, reuse=None, scope='InceptionV2', global_pool=False): """Inception v2 model for classification. Constructs an Inception v2 network for classification as described in http://arxiv.org/abs/1502.03167. The default image size used to train this network is 224x224. Args: inputs: a tensor of shape [batch_size, height, width, channels]. num_classes: number of predicted classes. If 0 or None, the logits layer is omitted and the input features to the logits layer (before dropout) are returned instead. is_training: whether is training or not. dropout_keep_prob: the percentage of activation values that are retained. min_depth: Minimum depth value (number of channels) for all convolution ops. Enforced when depth_multiplier < 1, and not an active constraint when depth_multiplier >= 1. depth_multiplier: Float multiplier for the depth (number of channels) for all convolution ops. The value must be greater than zero. Typical usage will be to set this value in (0, 1) to reduce the number of parameters or computation cost of the model. prediction_fn: a function to get predictions out of logits. 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. 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. global_pool: Optional boolean flag to control the avgpooling before the logits layer. If false or unset, pooling is done with a fixed window that reduces default-sized inputs to 1x1, while larger inputs lead to larger outputs. If true, any input size is pooled down to 1x1. Returns: net: a Tensor with the logits (pre-softmax activations) if num_classes is a non-zero integer, or the non-dropped-out input to the logits layer if num_classes is 0 or None. end_points: 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, or depth_multiplier <= 0 """ if depth_multiplier <= 0: raise ValueError('depth_multiplier is not greater than zero.') # Final pooling and prediction with tf.variable_scope(scope, 'InceptionV2', [inputs], reuse=reuse) as scope: with slim.arg_scope([slim.batch_norm, slim.dropout], is_training=is_training): net, end_points = inception_v2_base( inputs, scope=scope, min_depth=min_depth, depth_multiplier=depth_multiplier) with tf.variable_scope('Logits'): if global_pool: # Global average pooling. net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool') end_points['global_pool'] = net else: # Pooling with a fixed kernel size. kernel_size = _reduced_kernel_size_for_small_input(net, [7, 7]) net = slim.avg_pool2d(net, kernel_size, padding='VALID', scope='AvgPool_1a_{}x{}'.format(*kernel_size)) end_points['AvgPool_1a'] = net if not num_classes: return net, end_points # 1 x 1 x 1024 net = slim.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_1b') logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, normalizer_fn=None, scope='Conv2d_1c_1x1') if spatial_squeeze: logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze') end_points['Logits'] = logits end_points['Predictions'] = prediction_fn(logits, scope='Predictions') return logits, end_points
def inception_v2_base(inputs, final_endpoint='Mixed_5c', min_depth=16, depth_multiplier=1.0, use_separable_conv=True, data_format='NHWC', scope=None): """Inception v2 (6a2). Constructs an Inception v2 network from inputs to the given final endpoint. This method can construct the network up to the layer inception(5b) as described in http://arxiv.org/abs/1502.03167. Args: inputs: a tensor of shape [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', 'Mixed_4a', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_5a', 'Mixed_5b', 'Mixed_5c']. min_depth: Minimum depth value (number of channels) for all convolution ops. Enforced when depth_multiplier < 1, and not an active constraint when depth_multiplier >= 1. depth_multiplier: Float multiplier for the depth (number of channels) for all convolution ops. The value must be greater than zero. Typical usage will be to set this value in (0, 1) to reduce the number of parameters or computation cost of the model. use_separable_conv: Use a separable convolution for the first layer Conv2d_1a_7x7. If this is False, use a normal convolution instead. data_format: Data format of the activations ('NHWC' or 'NCHW'). scope: Optional variable_scope. Returns: tensor_out: output tensor corresponding to the final_endpoint. end_points: a set of activations for external use, for example summaries or losses. Raises: ValueError: if final_endpoint is not set to one of the predefined values, or depth_multiplier <= 0 """ # end_points will collect relevant activations for external use, for example # summaries or losses. end_points = {} # Used to find thinned depths for each layer. if depth_multiplier <= 0: raise ValueError('depth_multiplier is not greater than zero.') depth = lambda d: max(int(d * depth_multiplier), min_depth) if data_format != 'NHWC' and data_format != 'NCHW': raise ValueError('data_format must be either NHWC or NCHW.') if data_format == 'NCHW' and use_separable_conv: raise ValueError( 'separable convolution only supports NHWC layout. NCHW data format can' ' only be used when use_separable_conv is False.' ) concat_dim = 3 if data_format == 'NHWC' else 1 with tf.variable_scope(scope, 'InceptionV2', [inputs]): with slim.arg_scope( [slim.conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='SAME', data_format=data_format): # Note that sizes in the comments below assume an input spatial size of # 224x224, however, the inputs can be of any size greater 32x32. # 224 x 224 x 3 end_point = 'Conv2d_1a_7x7' if use_separable_conv: # depthwise_multiplier here is different from depth_multiplier. # depthwise_multiplier determines the output channels of the initial # depthwise conv (see docs for tf.nn.separable_conv2d), while # depth_multiplier controls the # channels of the subsequent 1x1 # convolution. Must have # in_channels * depthwise_multipler <= out_channels # so that the separable convolution is not overparameterized. depthwise_multiplier = min(int(depth(64) / 3), 8) net = slim.separable_conv2d( inputs, depth(64), [7, 7], depth_multiplier=depthwise_multiplier, stride=2, padding='SAME', weights_initializer=trunc_normal(1.0), scope=end_point) else: # Use a normal convolution instead of a separable convolution. net = slim.conv2d( inputs, depth(64), [7, 7], stride=2, weights_initializer=trunc_normal(1.0), scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 112 x 112 x 64 end_point = 'MaxPool_2a_3x3' net = slim.max_pool2d(net, [3, 3], scope=end_point, stride=2) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 56 x 56 x 64 end_point = 'Conv2d_2b_1x1' net = slim.conv2d(net, depth(64), [1, 1], scope=end_point, weights_initializer=trunc_normal(0.1)) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 56 x 56 x 64 end_point = 'Conv2d_2c_3x3' net = slim.conv2d(net, depth(192), [3, 3], scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 56 x 56 x 192 end_point = 'MaxPool_3a_3x3' net = slim.max_pool2d(net, [3, 3], scope=end_point, stride=2) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 28 x 28 x 192 # Inception module. end_point = 'Mixed_3b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(64), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(64), [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d( net, depth(64), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(32), [1, 1], weights_initializer=trunc_normal(0.1), scope='Conv2d_0b_1x1') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 28 x 28 x 256 end_point = 'Mixed_3c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(64), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d( net, depth(64), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(64), [1, 1], weights_initializer=trunc_normal(0.1), scope='Conv2d_0b_1x1') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 28 x 28 x 320 end_point = 'Mixed_4a' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d( net, depth(128), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_0 = slim.conv2d(branch_0, depth(160), [3, 3], stride=2, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(64), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d( branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_1 = slim.conv2d( branch_1, depth(96), [3, 3], stride=2, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.max_pool2d( net, [3, 3], stride=2, scope='MaxPool_1a_3x3') net = tf.concat(axis=concat_dim, values=[branch_0, branch_1, branch_2]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 14 x 14 x 576 end_point = 'Mixed_4b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(224), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(64), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d( branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d( net, depth(96), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(128), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(128), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(128), [1, 1], weights_initializer=trunc_normal(0.1), scope='Conv2d_0b_1x1') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 14 x 14 x 576 end_point = 'Mixed_4c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(96), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(128), [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d( net, depth(96), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(128), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(128), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(128), [1, 1], weights_initializer=trunc_normal(0.1), scope='Conv2d_0b_1x1') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 14 x 14 x 576 end_point = 'Mixed_4d' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(128), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(160), [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d( net, depth(128), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(160), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(160), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(96), [1, 1], weights_initializer=trunc_normal(0.1), scope='Conv2d_0b_1x1') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 14 x 14 x 576 end_point = 'Mixed_4e' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(96), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(128), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(192), [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d( net, depth(160), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(192), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(192), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(96), [1, 1], weights_initializer=trunc_normal(0.1), scope='Conv2d_0b_1x1') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 14 x 14 x 576 end_point = 'Mixed_5a' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d( net, depth(128), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_0 = slim.conv2d(branch_0, depth(192), [3, 3], stride=2, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(192), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(256), [3, 3], scope='Conv2d_0b_3x3') branch_1 = slim.conv2d(branch_1, depth(256), [3, 3], stride=2, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.max_pool2d(net, [3, 3], stride=2, scope='MaxPool_1a_3x3') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 7 x 7 x 1024 end_point = 'Mixed_5b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(352), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(192), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(320), [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d( net, depth(160), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(224), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(224), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(128), [1, 1], weights_initializer=trunc_normal(0.1), scope='Conv2d_0b_1x1') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 7 x 7 x 1024 end_point = 'Mixed_5c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(352), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d( net, depth(192), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(320), [3, 3], scope='Conv2d_0b_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d( net, depth(192), [1, 1], weights_initializer=trunc_normal(0.09), scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(224), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(224), [3, 3], scope='Conv2d_0c_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, depth(128), [1, 1], weights_initializer=trunc_normal(0.1), scope='Conv2d_0b_1x1') net = tf.concat( axis=concat_dim, values=[branch_0, branch_1, branch_2, branch_3]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points raise ValueError('Unknown final endpoint %s' % final_endpoint)
def vgg_a(inputs, num_classes=1000, is_training=True, dropout_keep_prob=0.5, spatial_squeeze=True, scope='vgg_a', fc_conv_padding='VALID', global_pool=False): """Oxford Net VGG 11-Layers version A Example. Note: All the fully_connected layers have been transformed to conv2d layers. To use in classification mode, resize input to 224x224. Args: inputs: a tensor of size [batch_size, height, width, channels]. num_classes: number of predicted classes. If 0 or None, the logits layer is omitted and the input features to the logits layer are returned instead. is_training: whether or not the model is being trained. dropout_keep_prob: the probability that activations are kept in the dropout layers during training. spatial_squeeze: whether or not should squeeze the spatial dimensions of the outputs. Useful to remove unnecessary dimensions for classification. scope: Optional scope for the variables. fc_conv_padding: the type of padding to use for the fully connected layer that is implemented as a convolutional layer. Use 'SAME' padding if you are applying the network in a fully convolutional manner and want to get a prediction map downsampled by a factor of 32 as an output. Otherwise, the output prediction map will be (input / 32) - 6 in case of 'VALID' padding. global_pool: Optional boolean flag. If True, the input to the classification layer is avgpooled to size 1x1, for any input size. (This is not part of the original VGG architecture.) Returns: net: the output of the logits layer (if num_classes is a non-zero integer), or the input to the logits layer (if num_classes is 0 or None). end_points: a dict of tensors with intermediate activations. """ with tf.variable_scope(scope, 'vgg_a', [inputs]) as sc: end_points_collection = sc.original_name_scope + '_end_points' # Collect outputs for conv2d, fully_connected and max_pool2d. with slim.arg_scope([slim.conv2d, slim.max_pool2d], outputs_collections=end_points_collection): net = slim.repeat(inputs, 1, slim.conv2d, 64, [3, 3], scope='conv1') net = slim.max_pool2d(net, [2, 2], scope='pool1') net = slim.repeat(net, 1, slim.conv2d, 128, [3, 3], scope='conv2') net = slim.max_pool2d(net, [2, 2], scope='pool2') net = slim.repeat(net, 2, slim.conv2d, 256, [3, 3], scope='conv3') net = slim.max_pool2d(net, [2, 2], scope='pool3') net = slim.repeat(net, 2, slim.conv2d, 512, [3, 3], scope='conv4') net = slim.max_pool2d(net, [2, 2], scope='pool4') net = slim.repeat(net, 2, slim.conv2d, 512, [3, 3], scope='conv5') net = slim.max_pool2d(net, [2, 2], scope='pool5') # Use conv2d instead of fully_connected layers. net = slim.conv2d(net, 4096, [7, 7], padding=fc_conv_padding, scope='fc6') net = slim.dropout(net, dropout_keep_prob, is_training=is_training, scope='dropout6') net = slim.conv2d(net, 4096, [1, 1], scope='fc7') # Convert end_points_collection into a end_point dict. end_points = slim.utils.convert_collection_to_dict( end_points_collection) if global_pool: net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool') end_points['global_pool'] = net if num_classes: net = slim.dropout(net, dropout_keep_prob, is_training=is_training, scope='dropout7') net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, normalizer_fn=None, scope='fc8') if spatial_squeeze: net = tf.squeeze(net, [1, 2], name='fc8/squeezed') end_points[sc.name + '/fc8'] = net return net, end_points
def bottleneck(inputs, depth, depth_bottleneck, stride, rate=1, outputs_collections=None, scope=None): """Bottleneck residual unit variant with BN before convolutions. This is the full preactivation residual unit variant proposed in [2]. See Fig. 1(b) of [2] for its definition. Note that we use here the bottleneck variant which has an extra bottleneck layer. When putting together two consecutive ResNet blocks that use this unit, one should use stride = 2 in the last unit of the first block. Args: inputs: A tensor of size [batch, height, width, channels]. depth: The depth of the ResNet unit output. depth_bottleneck: The depth of the bottleneck layers. stride: The ResNet unit's stride. Determines the amount of downsampling of the units output compared to its input. rate: An integer, rate for atrous convolution. outputs_collections: Collection to add the ResNet unit output. scope: Optional variable_scope. Returns: The ResNet unit's output. """ with tf.variable_scope(scope, 'bottleneck_v2', [inputs]) as sc: depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4) preact = slim.batch_norm(inputs, activation_fn=tf.nn.relu, scope='preact') if depth == depth_in: shortcut = resnet_utils.subsample(inputs, stride, 'shortcut') else: shortcut = slim.conv2d(preact, depth, [1, 1], stride=stride, normalizer_fn=None, activation_fn=None, scope='shortcut') residual = slim.conv2d(preact, depth_bottleneck, [1, 1], stride=1, scope='conv1') residual = resnet_utils.conv2d_same(residual, depth_bottleneck, 3, stride, rate=rate, scope='conv2') residual = slim.conv2d(residual, depth, [1, 1], stride=1, normalizer_fn=None, activation_fn=None, scope='conv3') output = shortcut + residual return slim.utils.collect_named_outputs(outputs_collections, sc.name, output)
def inception_v3(inputs, num_classes=1000, is_training=True, dropout_keep_prob=0.8, min_depth=16, depth_multiplier=1.0, prediction_fn=slim.softmax, spatial_squeeze=True, reuse=None, create_aux_logits=True, scope='InceptionV3', global_pool=False): """Inception model from http://arxiv.org/abs/1512.00567. "Rethinking the Inception Architecture for Computer Vision" Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna. With the default arguments this method constructs the exact model defined in the paper. However, one can experiment with variations of the inception_v3 network by changing arguments dropout_keep_prob, min_depth and depth_multiplier. The default image size used to train this network is 299x299. Args: inputs: a tensor of size [batch_size, height, width, channels]. num_classes: number of predicted classes. If 0 or None, the logits layer is omitted and the input features to the logits layer (before dropout) are returned instead. is_training: whether is training or not. dropout_keep_prob: the percentage of activation values that are retained. min_depth: Minimum depth value (number of channels) for all convolution ops. Enforced when depth_multiplier < 1, and not an active constraint when depth_multiplier >= 1. depth_multiplier: Float multiplier for the depth (number of channels) for all convolution ops. The value must be greater than zero. Typical usage will be to set this value in (0, 1) to reduce the number of parameters or computation cost of the model. prediction_fn: a function to get predictions out of logits. 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. reuse: whether or not the network and its variables should be reused. To be able to reuse 'scope' must be given. create_aux_logits: Whether to create the auxiliary logits. scope: Optional variable_scope. global_pool: Optional boolean flag to control the avgpooling before the logits layer. If false or unset, pooling is done with a fixed window that reduces default-sized inputs to 1x1, while larger inputs lead to larger outputs. If true, any input size is pooled down to 1x1. Returns: net: a Tensor with the logits (pre-softmax activations) if num_classes is a non-zero integer, or the non-dropped-out input to the logits layer if num_classes is 0 or None. end_points: a dictionary from components of the network to the corresponding activation. Raises: ValueError: if 'depth_multiplier' is less than or equal to zero. """ if depth_multiplier <= 0: raise ValueError('depth_multiplier is not greater than zero.') depth = lambda d: max(int(d * depth_multiplier), min_depth) with tf.variable_scope(scope, 'InceptionV3', [inputs], reuse=reuse) as scope: with slim.arg_scope([slim.batch_norm, slim.dropout], is_training=is_training): net, end_points = inception_v3_base( inputs, scope=scope, min_depth=min_depth, depth_multiplier=depth_multiplier) # Auxiliary Head logits if create_aux_logits and num_classes: with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='SAME'): aux_logits = end_points['Mixed_6e'] with tf.variable_scope('AuxLogits'): aux_logits = slim.avg_pool2d( aux_logits, [5, 5], stride=3, padding='VALID', scope='AvgPool_1a_5x5') aux_logits = slim.conv2d(aux_logits, depth(128), [1, 1], scope='Conv2d_1b_1x1') # Shape of feature map before the final layer. kernel_size = _reduced_kernel_size_for_small_input( aux_logits, [5, 5]) aux_logits = slim.conv2d( aux_logits, depth(768), kernel_size, weights_initializer=trunc_normal(0.01), padding='VALID', scope='Conv2d_2a_{}x{}'.format(*kernel_size)) aux_logits = slim.conv2d( aux_logits, num_classes, [1, 1], activation_fn=None, normalizer_fn=None, weights_initializer=trunc_normal(0.001), scope='Conv2d_2b_1x1') if spatial_squeeze: aux_logits = tf.squeeze(aux_logits, [1, 2], name='SpatialSqueeze') end_points['AuxLogits'] = aux_logits # Final pooling and prediction with tf.variable_scope('Logits'): if global_pool: # Global average pooling. net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='GlobalPool') end_points['global_pool'] = net else: # Pooling with a fixed kernel size. kernel_size = _reduced_kernel_size_for_small_input(net, [8, 8]) net = slim.avg_pool2d(net, kernel_size, padding='VALID', scope='AvgPool_1a_{}x{}'.format(*kernel_size)) end_points['AvgPool_1a'] = net if not num_classes: return net, end_points # 1 x 1 x 2048 net = slim.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_1b') end_points['PreLogits'] = net # 2048 logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, normalizer_fn=None, scope='Conv2d_1c_1x1') if spatial_squeeze: logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze') # 1000 end_points['Logits'] = logits end_points['Predictions'] = prediction_fn(logits, scope='Predictions') return logits, end_points
def inception_v3_base(inputs, final_endpoint='Mixed_7c', min_depth=16, depth_multiplier=1.0, scope=None): """Inception model from http://arxiv.org/abs/1512.00567. Constructs an Inception v3 network from inputs to the given final endpoint. This method can construct the network up to the final inception block Mixed_7c. Note that the names of the layers in the paper do not correspond to the names of the endpoints registered by this function although they build the same network. Here is a mapping from the old_names to the new names: Old name | New name ======================================= conv0 | Conv2d_1a_3x3 conv1 | Conv2d_2a_3x3 conv2 | Conv2d_2b_3x3 pool1 | MaxPool_3a_3x3 conv3 | Conv2d_3b_1x1 conv4 | Conv2d_4a_3x3 pool2 | MaxPool_5a_3x3 mixed_35x35x256a | Mixed_5b mixed_35x35x288a | Mixed_5c mixed_35x35x288b | Mixed_5d mixed_17x17x768a | Mixed_6a mixed_17x17x768b | Mixed_6b mixed_17x17x768c | Mixed_6c mixed_17x17x768d | Mixed_6d mixed_17x17x768e | Mixed_6e mixed_8x8x1280a | Mixed_7a mixed_8x8x2048a | Mixed_7b mixed_8x8x2048b | Mixed_7c 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_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3', 'MaxPool_3a_3x3', 'Conv2d_3b_1x1', 'Conv2d_4a_3x3', 'MaxPool_5a_3x3', 'Mixed_5b', 'Mixed_5c', 'Mixed_5d', 'Mixed_6a', 'Mixed_6b', 'Mixed_6c', 'Mixed_6d', 'Mixed_6e', 'Mixed_7a', 'Mixed_7b', 'Mixed_7c']. min_depth: Minimum depth value (number of channels) for all convolution ops. Enforced when depth_multiplier < 1, and not an active constraint when depth_multiplier >= 1. depth_multiplier: Float multiplier for the depth (number of channels) for all convolution ops. The value must be greater than zero. Typical usage will be to set this value in (0, 1) to reduce the number of parameters or computation cost of the model. scope: Optional variable_scope. Returns: tensor_out: output tensor corresponding to the final_endpoint. end_points: a set of activations for external use, for example summaries or losses. Raises: ValueError: if final_endpoint is not set to one of the predefined values, or depth_multiplier <= 0 """ # end_points will collect relevant activations for external use, for example # summaries or losses. end_points = {} if depth_multiplier <= 0: raise ValueError('depth_multiplier is not greater than zero.') depth = lambda d: max(int(d * depth_multiplier), min_depth) with tf.variable_scope(scope, 'InceptionV3', [inputs]): with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='VALID'): # 299 x 299 x 3 end_point = 'Conv2d_1a_3x3' net = slim.conv2d(inputs, depth(32), [3, 3], stride=2, scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 149 x 149 x 32 end_point = 'Conv2d_2a_3x3' net = slim.conv2d(net, depth(32), [3, 3], scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 147 x 147 x 32 end_point = 'Conv2d_2b_3x3' net = slim.conv2d(net, depth(64), [3, 3], padding='SAME', scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 147 x 147 x 64 end_point = 'MaxPool_3a_3x3' net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 73 x 73 x 64 end_point = 'Conv2d_3b_1x1' net = slim.conv2d(net, depth(80), [1, 1], scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 73 x 73 x 80. end_point = 'Conv2d_4a_3x3' net = slim.conv2d(net, depth(192), [3, 3], scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 71 x 71 x 192. end_point = 'MaxPool_5a_3x3' net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # 35 x 35 x 192. # Inception blocks with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='SAME'): # mixed: 35 x 35 x 256. end_point = 'Mixed_5b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(48), [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(64), [5, 5], scope='Conv2d_0b_5x5') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d(branch_3, depth(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 end_point == final_endpoint: return net, end_points # mixed_1: 35 x 35 x 288. end_point = 'Mixed_5c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(48), [1, 1], scope='Conv2d_0b_1x1') branch_1 = slim.conv2d(branch_1, depth(64), [5, 5], scope='Conv_1_0c_5x5') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d(branch_3, depth(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 end_point == final_endpoint: return net, end_points # mixed_2: 35 x 35 x 288. end_point = 'Mixed_5d' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(48), [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(64), [5, 5], scope='Conv2d_0b_5x5') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_2 = slim.conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d(branch_3, depth(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 end_point == final_endpoint: return net, end_points # mixed_3: 17 x 17 x 768. end_point = 'Mixed_6a' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(384), [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_1 = slim.conv2d(branch_1, depth(96), [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_1x1') with tf.variable_scope('Branch_2'): branch_2 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='MaxPool_1a_3x3') net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # mixed4: 17 x 17 x 768. end_point = 'Mixed_6b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(128), [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(128), [1, 7], scope='Conv2d_0b_1x7') branch_1 = slim.conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(128), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(128), [7, 1], scope='Conv2d_0b_7x1') branch_2 = slim.conv2d(branch_2, depth(128), [1, 7], scope='Conv2d_0c_1x7') branch_2 = slim.conv2d(branch_2, depth(128), [7, 1], scope='Conv2d_0d_7x1') branch_2 = slim.conv2d(branch_2, depth(192), [1, 7], scope='Conv2d_0e_1x7') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d(branch_3, depth(192), [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 end_point == final_endpoint: return net, end_points # mixed_5: 17 x 17 x 768. end_point = 'Mixed_6c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(160), [1, 7], scope='Conv2d_0b_1x7') branch_1 = slim.conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(160), [7, 1], scope='Conv2d_0b_7x1') branch_2 = slim.conv2d(branch_2, depth(160), [1, 7], scope='Conv2d_0c_1x7') branch_2 = slim.conv2d(branch_2, depth(160), [7, 1], scope='Conv2d_0d_7x1') branch_2 = slim.conv2d(branch_2, depth(192), [1, 7], scope='Conv2d_0e_1x7') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d(branch_3, depth(192), [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 end_point == final_endpoint: return net, end_points # mixed_6: 17 x 17 x 768. end_point = 'Mixed_6d' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(160), [1, 7], scope='Conv2d_0b_1x7') branch_1 = slim.conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(160), [7, 1], scope='Conv2d_0b_7x1') branch_2 = slim.conv2d(branch_2, depth(160), [1, 7], scope='Conv2d_0c_1x7') branch_2 = slim.conv2d(branch_2, depth(160), [7, 1], scope='Conv2d_0d_7x1') branch_2 = slim.conv2d(branch_2, depth(192), [1, 7], scope='Conv2d_0e_1x7') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d(branch_3, depth(192), [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 end_point == final_endpoint: return net, end_points # mixed_7: 17 x 17 x 768. end_point = 'Mixed_6e' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(192), [1, 7], scope='Conv2d_0b_1x7') branch_1 = slim.conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d(branch_2, depth(192), [7, 1], scope='Conv2d_0b_7x1') branch_2 = slim.conv2d(branch_2, depth(192), [1, 7], scope='Conv2d_0c_1x7') branch_2 = slim.conv2d(branch_2, depth(192), [7, 1], scope='Conv2d_0d_7x1') branch_2 = slim.conv2d(branch_2, depth(192), [1, 7], scope='Conv2d_0e_1x7') with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d(branch_3, depth(192), [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 end_point == final_endpoint: return net, end_points # mixed_8: 8 x 8 x 1280. end_point = 'Mixed_7a' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') branch_0 = slim.conv2d(branch_0, depth(320), [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, depth(192), [1, 7], scope='Conv2d_0b_1x7') branch_1 = slim.conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') branch_1 = slim.conv2d(branch_1, depth(192), [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_2'): branch_2 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='MaxPool_1a_3x3') net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2]) end_points[end_point] = net if end_point == final_endpoint: return net, end_points # mixed_9: 8 x 8 x 2048. end_point = 'Mixed_7b' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(320), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(384), [1, 1], scope='Conv2d_0a_1x1') branch_1 = tf.concat(axis=3, values=[ slim.conv2d(branch_1, depth(384), [1, 3], scope='Conv2d_0b_1x3'), slim.conv2d(branch_1, depth(384), [3, 1], scope='Conv2d_0b_3x1')]) with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(448), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d( branch_2, depth(384), [3, 3], scope='Conv2d_0b_3x3') branch_2 = tf.concat(axis=3, values=[ slim.conv2d(branch_2, depth(384), [1, 3], scope='Conv2d_0c_1x3'), slim.conv2d(branch_2, depth(384), [3, 1], scope='Conv2d_0d_3x1')]) with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(192), [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 end_point == final_endpoint: return net, end_points # mixed_10: 8 x 8 x 2048. end_point = 'Mixed_7c' with tf.variable_scope(end_point): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, depth(320), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, depth(384), [1, 1], scope='Conv2d_0a_1x1') branch_1 = tf.concat(axis=3, values=[ slim.conv2d(branch_1, depth(384), [1, 3], scope='Conv2d_0b_1x3'), slim.conv2d(branch_1, depth(384), [3, 1], scope='Conv2d_0c_3x1')]) with tf.variable_scope('Branch_2'): branch_2 = slim.conv2d(net, depth(448), [1, 1], scope='Conv2d_0a_1x1') branch_2 = slim.conv2d( branch_2, depth(384), [3, 3], scope='Conv2d_0b_3x3') branch_2 = tf.concat(axis=3, values=[ slim.conv2d(branch_2, depth(384), [1, 3], scope='Conv2d_0c_1x3'), slim.conv2d(branch_2, depth(384), [3, 1], scope='Conv2d_0d_3x1')]) with tf.variable_scope('Branch_3'): branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3') branch_3 = slim.conv2d( branch_3, depth(192), [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 end_point == final_endpoint: return net, end_points raise ValueError('Unknown final endpoint %s' % final_endpoint)
def overfeat(inputs, num_classes=1000, is_training=True, dropout_keep_prob=0.5, spatial_squeeze=True, scope='overfeat', global_pool=False): """Contains the model definition for the OverFeat network. The definition for the network was obtained from: OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus and Yann LeCun, 2014 http://arxiv.org/abs/1312.6229 Note: All the fully_connected layers have been transformed to conv2d layers. To use in classification mode, resize input to 231x231. To use in fully convolutional mode, set spatial_squeeze to false. Args: inputs: a tensor of size [batch_size, height, width, channels]. num_classes: number of predicted classes. If 0 or None, the logits layer is omitted and the input features to the logits layer are returned instead. is_training: whether or not the model is being trained. dropout_keep_prob: the probability that activations are kept in the dropout layers during training. spatial_squeeze: whether or not should squeeze the spatial dimensions of the outputs. Useful to remove unnecessary dimensions for classification. scope: Optional scope for the variables. global_pool: Optional boolean flag. If True, the input to the classification layer is avgpooled to size 1x1, for any input size. (This is not part of the original OverFeat.) Returns: net: the output of the logits layer (if num_classes is a non-zero integer), or the non-dropped-out input to the logits layer (if num_classes is 0 or None). end_points: a dict of tensors with intermediate activations. """ with tf.variable_scope(scope, 'overfeat', [inputs]) as sc: end_points_collection = sc.original_name_scope + '_end_points' # Collect outputs for conv2d, fully_connected and max_pool2d with slim.arg_scope( [slim.conv2d, slim.fully_connected, slim.max_pool2d], outputs_collections=end_points_collection): net = slim.conv2d(inputs, 64, [11, 11], 4, padding='VALID', scope='conv1') net = slim.max_pool2d(net, [2, 2], scope='pool1') net = slim.conv2d(net, 256, [5, 5], padding='VALID', scope='conv2') net = slim.max_pool2d(net, [2, 2], scope='pool2') net = slim.conv2d(net, 512, [3, 3], scope='conv3') net = slim.conv2d(net, 1024, [3, 3], scope='conv4') net = slim.conv2d(net, 1024, [3, 3], scope='conv5') net = slim.max_pool2d(net, [2, 2], scope='pool5') # Use conv2d instead of fully_connected layers. with slim.arg_scope( [slim.conv2d], weights_initializer=trunc_normal(0.005), biases_initializer=tf.constant_initializer(0.1)): net = slim.conv2d(net, 3072, [6, 6], padding='VALID', scope='fc6') net = slim.dropout(net, dropout_keep_prob, is_training=is_training, scope='dropout6') net = slim.conv2d(net, 4096, [1, 1], scope='fc7') # Convert end_points_collection into a end_point dict. end_points = slim.utils.convert_collection_to_dict( end_points_collection) if global_pool: net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool') end_points['global_pool'] = net if num_classes: net = slim.dropout(net, dropout_keep_prob, is_training=is_training, scope='dropout7') net = slim.conv2d( net, num_classes, [1, 1], activation_fn=None, normalizer_fn=None, biases_initializer=tf.zeros_initializer(), scope='fc8') if spatial_squeeze: net = tf.squeeze(net, [1, 2], name='fc8/squeezed') end_points[sc.name + '/fc8'] = net return net, end_points
def mobilenet_v1_base(inputs, final_endpoint='Conv2d_13_pointwise', min_depth=8, depth_multiplier=1.0, conv_defs=None, output_stride=None, scope=None): """Mobilenet v1. Constructs a Mobilenet v1 network from inputs to the given final endpoint. Args: inputs: a tensor of shape [batch_size, height, width, channels]. final_endpoint: specifies the endpoint to construct the network up to. It can be one of ['Conv2d_0', 'Conv2d_1_pointwise', 'Conv2d_2_pointwise', 'Conv2d_3_pointwise', 'Conv2d_4_pointwise', 'Conv2d_5'_pointwise, 'Conv2d_6_pointwise', 'Conv2d_7_pointwise', 'Conv2d_8_pointwise', 'Conv2d_9_pointwise', 'Conv2d_10_pointwise', 'Conv2d_11_pointwise', 'Conv2d_12_pointwise', 'Conv2d_13_pointwise']. min_depth: Minimum depth value (number of channels) for all convolution ops. Enforced when depth_multiplier < 1, and not an active constraint when depth_multiplier >= 1. depth_multiplier: Float multiplier for the depth (number of channels) for all convolution ops. The value must be greater than zero. Typical usage will be to set this value in (0, 1) to reduce the number of parameters or computation cost of the model. conv_defs: A list of ConvDef namedtuples specifying the net architecture. output_stride: An integer that specifies the requested ratio of input to output spatial resolution. If not None, then we invoke atrous convolution if necessary to prevent the network from reducing the spatial resolution of the activation maps. Allowed values are 8 (accurate fully convolutional mode), 16 (fast fully convolutional mode), 32 (classification mode). scope: Optional variable_scope. Returns: tensor_out: output tensor corresponding to the final_endpoint. end_points: a set of activations for external use, for example summaries or losses. Raises: ValueError: if final_endpoint is not set to one of the predefined values, or depth_multiplier <= 0, or the target output_stride is not allowed. """ depth = lambda d: max(int(d * depth_multiplier), min_depth) end_points = {} # Used to find thinned depths for each layer. if depth_multiplier <= 0: raise ValueError('depth_multiplier is not greater than zero.') if conv_defs is None: conv_defs = _CONV_DEFS if output_stride is not None and output_stride not in [8, 16, 32]: raise ValueError('Only allowed output_stride values are 8, 16, 32.') with tf.variable_scope(scope, 'MobilenetV1', [inputs]): with slim.arg_scope([slim.conv2d, slim.separable_conv2d], padding='SAME'): # The current_stride variable keeps track of the output stride of the # activations, i.e., the running product of convolution strides up to the # current network layer. This allows us to invoke atrous convolution # whenever applying the next convolution would result in the activations # having output stride larger than the target output_stride. current_stride = 1 # The atrous convolution rate parameter. rate = 1 net = inputs for i, conv_def in enumerate(conv_defs): end_point_base = 'Conv2d_%d' % i if output_stride is not None and current_stride == output_stride: # If we have reached the target output_stride, then we need to employ # atrous convolution with stride=1 and multiply the atrous rate by the # current unit's stride for use in subsequent layers. layer_stride = 1 layer_rate = rate rate *= conv_def.stride else: layer_stride = conv_def.stride layer_rate = 1 current_stride *= conv_def.stride if isinstance(conv_def, Conv): end_point = end_point_base net = slim.conv2d(net, depth(conv_def.depth), conv_def.kernel, stride=conv_def.stride, normalizer_fn=slim.batch_norm, scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points elif isinstance(conv_def, DepthSepConv): end_point = end_point_base + '_depthwise' # By passing filters=None # separable_conv2d produces only a depthwise convolution layer net = slim.separable_conv2d(net, None, conv_def.kernel, depth_multiplier=1, stride=layer_stride, rate=layer_rate, normalizer_fn=slim.batch_norm, scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points end_point = end_point_base + '_pointwise' net = slim.conv2d(net, depth(conv_def.depth), [1, 1], stride=1, normalizer_fn=slim.batch_norm, scope=end_point) end_points[end_point] = net if end_point == final_endpoint: return net, end_points else: raise ValueError( 'Unknown convolution type %s for layer %d' % (conv_def.ltype, i)) raise ValueError('Unknown final endpoint %s' % final_endpoint)
def bottleneck(inputs, depth, depth_bottleneck, stride, rate=1, outputs_collections=None, scope=None, use_bounded_activations=False): """Bottleneck residual unit variant with BN after convolutions. This is the original residual unit proposed in [1]. See Fig. 1(a) of [2] for its definition. Note that we use here the bottleneck variant which has an extra bottleneck layer. When putting together two consecutive ResNet blocks that use this unit, one should use stride = 2 in the last unit of the first block. Args: inputs: A tensor of size [batch, height, width, channels]. depth: The depth of the ResNet unit output. depth_bottleneck: The depth of the bottleneck layers. stride: The ResNet unit's stride. Determines the amount of downsampling of the units output compared to its input. rate: An integer, rate for atrous convolution. outputs_collections: Collection to add the ResNet unit output. scope: Optional variable_scope. use_bounded_activations: Whether or not to use bounded activations. Bounded activations better lend themselves to quantized inference. Returns: The ResNet unit's output. """ with tf.variable_scope(scope, 'bottleneck_v1', [inputs]) as sc: depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4) if depth == depth_in: shortcut = resnet_utils.subsample(inputs, stride, 'shortcut') else: shortcut = slim.conv2d( inputs, depth, [1, 1], stride=stride, activation_fn=tf.nn.relu6 if use_bounded_activations else None, scope='shortcut') residual = slim.conv2d(inputs, depth_bottleneck, [1, 1], stride=1, scope='conv1') residual = resnet_utils.conv2d_same(residual, depth_bottleneck, 3, stride, rate=rate, scope='conv2') residual = slim.conv2d(residual, depth, [1, 1], stride=1, activation_fn=None, scope='conv3') if use_bounded_activations: # Use clip_by_value to simulate bandpass activation. residual = tf.clip_by_value(residual, -6.0, 6.0) output = tf.nn.relu6(shortcut + residual) else: output = tf.nn.relu(shortcut + residual) return slim.utils.collect_named_outputs(outputs_collections, sc.name, output)
def inception_v4_base(inputs, final_endpoint='Mixed_7d', scope=None): """Creates the Inception V4 network up to the given final endpoint. Args: inputs: a 4-D tensor of size [batch_size, height, width, 3]. final_endpoint: specifies the endpoint to construct the network up to. It can be one of [ 'Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3', 'Mixed_3a', 'Mixed_4a', 'Mixed_5a', 'Mixed_5b', 'Mixed_5c', 'Mixed_5d', 'Mixed_5e', 'Mixed_6a', 'Mixed_6b', 'Mixed_6c', 'Mixed_6d', 'Mixed_6e', 'Mixed_6f', 'Mixed_6g', 'Mixed_6h', 'Mixed_7a', 'Mixed_7b', 'Mixed_7c', 'Mixed_7d'] scope: Optional variable_scope. Returns: logits: the logits outputs of the model. end_points: the set of end_points from the inception model. Raises: ValueError: if final_endpoint is not set to one of the predefined values, """ end_points = {} def add_and_check_final(name, net): end_points[name] = net return name == final_endpoint with tf.variable_scope(scope, 'InceptionV4', [inputs]): with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='SAME'): # 299 x 299 x 3 net = slim.conv2d(inputs, 32, [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3') if add_and_check_final('Conv2d_1a_3x3', net): return net, end_points # 149 x 149 x 32 net = slim.conv2d(net, 32, [3, 3], padding='VALID', scope='Conv2d_2a_3x3') if add_and_check_final('Conv2d_2a_3x3', net): return net, end_points # 147 x 147 x 32 net = slim.conv2d(net, 64, [3, 3], scope='Conv2d_2b_3x3') if add_and_check_final('Conv2d_2b_3x3', net): return net, end_points # 147 x 147 x 64 with tf.variable_scope('Mixed_3a'): with tf.variable_scope('Branch_0'): branch_0 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='MaxPool_0a_3x3') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 96, [3, 3], stride=2, padding='VALID', scope='Conv2d_0a_3x3') net = tf.concat(axis=3, values=[branch_0, branch_1]) if add_and_check_final('Mixed_3a', net): return net, end_points # 73 x 73 x 160 with tf.variable_scope('Mixed_4a'): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1') branch_0 = slim.conv2d(branch_0, 96, [3, 3], padding='VALID', scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): branch_1 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1') branch_1 = slim.conv2d(branch_1, 64, [1, 7], scope='Conv2d_0b_1x7') branch_1 = slim.conv2d(branch_1, 64, [7, 1], scope='Conv2d_0c_7x1') branch_1 = slim.conv2d(branch_1, 96, [3, 3], padding='VALID', scope='Conv2d_1a_3x3') net = tf.concat(axis=3, values=[branch_0, branch_1]) if add_and_check_final('Mixed_4a', net): return net, end_points # 71 x 71 x 192 with tf.variable_scope('Mixed_5a'): with tf.variable_scope('Branch_0'): branch_0 = slim.conv2d(net, 192, [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): branch_1 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='MaxPool_1a_3x3') net = tf.concat(axis=3, values=[branch_0, branch_1]) if add_and_check_final('Mixed_5a', net): return net, end_points # 35 x 35 x 384 # 4 x Inception-A blocks for idx in range(4): block_scope = 'Mixed_5' + chr(ord('b') + idx) net = block_inception_a(net, block_scope) if add_and_check_final(block_scope, net): return net, end_points # 35 x 35 x 384 # Reduction-A block net = block_reduction_a(net, 'Mixed_6a') if add_and_check_final('Mixed_6a', net): return net, end_points # 17 x 17 x 1024 # 7 x Inception-B blocks for idx in range(7): block_scope = 'Mixed_6' + chr(ord('b') + idx) net = block_inception_b(net, block_scope) if add_and_check_final(block_scope, net): return net, end_points # 17 x 17 x 1024 # Reduction-B block net = block_reduction_b(net, 'Mixed_7a') if add_and_check_final('Mixed_7a', net): return net, end_points # 8 x 8 x 1536 # 3 x Inception-C blocks for idx in range(3): block_scope = 'Mixed_7' + chr(ord('b') + idx) net = block_inception_c(net, block_scope) if add_and_check_final(block_scope, net): return net, end_points raise ValueError('Unknown final endpoint %s' % final_endpoint)
variables_to_restore = variable_averages.variables_to_restore() saver = tf.train.Saver(variables_to_restore) while True: with tf.Session() as sess: ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH) if ckpt and ckpt.model_checkpoint_path: saver.restore(sess, ckpt.model_checkpoint_path) accuracy_score = sess.run(accuracy, feed_dict=validate_feed) print( "after training steps,valid acc using average model is %g" % (accuracy_score)) time.sleep(EVAL_INTERVAL_SEC) evaluate(mnist) import slim with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='SAME'): with tf.variable_scope('Mixes_7c'): branch_0 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = tf.concat(3, [ slim.conv2d(branch_1, 384, [1, 3], scope='Conv2d_0b_1x3'), slim.conv2d(branch_1, 384, [3, 1], scope='Conv2d_0b_3x1') ])
def inception_v4(inputs, num_classes=1001, is_training=True, dropout_keep_prob=0.8, reuse=None, scope='InceptionV4', create_aux_logits=True): """Creates the Inception V4 model. Args: inputs: a 4-D tensor of size [batch_size, height, width, 3]. num_classes: number of predicted classes. If 0 or None, the logits layer is omitted and the input features to the logits layer (before dropout) are returned instead. is_training: whether is training or not. dropout_keep_prob: float, the fraction to keep before final layer. 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. create_aux_logits: Whether to include the auxiliary logits. Returns: net: a Tensor with the logits (pre-softmax activations) if num_classes is a non-zero integer, or the non-dropped input to the logits layer if num_classes is 0 or None. end_points: the set of end_points from the inception model. """ end_points = {} with tf.variable_scope(scope, 'InceptionV4', [inputs], reuse=reuse) as scope: with slim.arg_scope([slim.batch_norm, slim.dropout], is_training=is_training): net, end_points = inception_v4_base(inputs, scope=scope) with slim.arg_scope( [slim.conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='SAME'): # Auxiliary Head logits if create_aux_logits and num_classes: with tf.variable_scope('AuxLogits'): # 17 x 17 x 1024 aux_logits = end_points['Mixed_6h'] aux_logits = slim.avg_pool2d(aux_logits, [5, 5], stride=3, padding='VALID', scope='AvgPool_1a_5x5') aux_logits = slim.conv2d(aux_logits, 128, [1, 1], scope='Conv2d_1b_1x1') aux_logits = slim.conv2d(aux_logits, 768, aux_logits.get_shape()[1:3], padding='VALID', scope='Conv2d_2a') aux_logits = slim.flatten(aux_logits) aux_logits = slim.fully_connected(aux_logits, num_classes, activation_fn=None, scope='Aux_logits') end_points['AuxLogits'] = aux_logits # Final pooling and prediction # TODO(sguada,arnoegw): Consider adding a parameter global_pool which # can be set to False to disable pooling here (as in resnet_*()). with tf.variable_scope('Logits'): # 8 x 8 x 1536 kernel_size = net.get_shape()[1:3] if kernel_size.is_fully_defined(): net = slim.avg_pool2d(net, kernel_size, padding='VALID', scope='AvgPool_1a') else: net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool') end_points['global_pool'] = net if not num_classes: return net, end_points # 1 x 1 x 1536 net = slim.dropout(net, dropout_keep_prob, scope='Dropout_1b') net = slim.flatten(net, scope='PreLogitsFlatten') end_points['PreLogitsFlatten'] = net # 1536 logits = slim.fully_connected(net, num_classes, activation_fn=None, scope='Logits') end_points['Logits'] = logits end_points['Predictions'] = tf.nn.softmax( logits, name='Predictions') return logits, end_points
def alexnet_v2(inputs, num_classes=1000, is_training=True, dropout_keep_prob=0.5, spatial_squeeze=True, scope='alexnet_v2', global_pool=False): """AlexNet version 2. Described in: http://arxiv.org/pdf/1404.5997v2.pdf Parameters from: github.com/akrizhevsky/cuda-convnet2/blob/master/layers/ layers-imagenet-1gpu.cfg Note: All the fully_connected layers have been transformed to conv2d layers. To use in classification mode, resize input to 224x224 or set global_pool=True. To use in fully convolutional mode, set spatial_squeeze to false. The LRN layers have been removed and change the initializers from random_normal_initializer to xavier_initializer. Args: inputs: a tensor of size [batch_size, height, width, channels]. num_classes: the number of predicted classes. If 0 or None, the logits layer is omitted and the input features to the logits layer are returned instead. is_training: whether or not the model is being trained. dropout_keep_prob: the probability that activations are kept in the dropout layers during training. spatial_squeeze: whether or not should squeeze the spatial dimensions of the logits. Useful to remove unnecessary dimensions for classification. scope: Optional scope for the variables. global_pool: Optional boolean flag. If True, the input to the classification layer is avgpooled to size 1x1, for any input size. (This is not part of the original AlexNet.) Returns: net: the output of the logits layer (if num_classes is a non-zero integer), or the non-dropped-out input to the logits layer (if num_classes is 0 or None). end_points: a dict of tensors with intermediate activations. """ with tf.variable_scope(scope, 'alexnet_v2', [inputs]) as sc: end_points_collection = sc.original_name_scope + '_end_points' # Collect outputs for conv2d, fully_connected and max_pool2d. with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.max_pool2d], outputs_collections=[end_points_collection]): net = slim.conv2d(inputs, 64, [11, 11], 4, padding='VALID', scope='conv1') net = slim.max_pool2d(net, [3, 3], 2, scope='pool1') net = slim.conv2d(net, 192, [5, 5], scope='conv2') net = slim.max_pool2d(net, [3, 3], 2, scope='pool2') net = slim.conv2d(net, 384, [3, 3], scope='conv3') net = slim.conv2d(net, 384, [3, 3], scope='conv4') net = slim.conv2d(net, 256, [3, 3], scope='conv5') net = slim.max_pool2d(net, [3, 3], 2, scope='pool5') # Use conv2d instead of fully_connected layers. with slim.arg_scope([slim.conv2d], weights_initializer=trunc_normal(0.005), biases_initializer=tf.constant_initializer(0.1)): net = slim.conv2d(net, 4096, [5, 5], padding='VALID', scope='fc6') net = slim.dropout(net, dropout_keep_prob, is_training=is_training, scope='dropout6') net = slim.conv2d(net, 4096, [1, 1], scope='fc7') # Convert end_points_collection into a end_point dict. end_points = slim.utils.convert_collection_to_dict( end_points_collection) if global_pool: net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool') end_points['global_pool'] = net if num_classes: net = slim.dropout(net, dropout_keep_prob, is_training=is_training, scope='dropout7') net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, normalizer_fn=None, biases_initializer=tf.zeros_initializer(), scope='fc8') if spatial_squeeze: net = tf.squeeze(net, [1, 2], name='fc8/squeezed') end_points[sc.name + '/fc8'] = net return net, end_points
def inception_resnet_v2_base(inputs, final_endpoint='Conv2d_7b_1x1', output_stride=16, align_feature_maps=False, scope=None, activation_fn=tf.nn.relu): """Inception model from http://arxiv.org/abs/1602.07261. Constructs an Inception Resnet v2 network from inputs to the given final endpoint. This method can construct the network up to the final inception block Conv2d_7b_1x1. 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_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3', 'MaxPool_3a_3x3', 'Conv2d_3b_1x1', 'Conv2d_4a_3x3', 'MaxPool_5a_3x3', 'Mixed_5b', 'Mixed_6a', 'PreAuxLogits', 'Mixed_7a', 'Conv2d_7b_1x1'] output_stride: A scalar that specifies the requested ratio of input to output spatial resolution. Only supports 8 and 16. align_feature_maps: When true, changes all the VALID paddings in the network to SAME padding so that the feature maps are aligned. scope: Optional variable_scope. activation_fn: Activation function for block scopes. Returns: tensor_out: output tensor corresponding to the final_endpoint. end_points: a set of activations for external use, for example summaries or losses. Raises: ValueError: if final_endpoint is not set to one of the predefined values, or if the output_stride is not 8 or 16, or if the output_stride is 8 and we request an end point after 'PreAuxLogits'. """ if output_stride != 8 and output_stride != 16: raise ValueError('output_stride must be 8 or 16.') padding = 'SAME' if align_feature_maps else 'VALID' end_points = {} def add_and_check_final(name, net): end_points[name] = net return name == final_endpoint with tf.variable_scope(scope, 'InceptionResnetV2', [inputs]): with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='SAME'): # 149 x 149 x 32 net = slim.conv2d(inputs, 32, 3, stride=2, padding=padding, scope='Conv2d_1a_3x3') if add_and_check_final('Conv2d_1a_3x3', net): return net, end_points # 147 x 147 x 32 net = slim.conv2d(net, 32, 3, padding=padding, scope='Conv2d_2a_3x3') if add_and_check_final('Conv2d_2a_3x3', net): return net, end_points # 147 x 147 x 64 net = slim.conv2d(net, 64, 3, scope='Conv2d_2b_3x3') if add_and_check_final('Conv2d_2b_3x3', net): return net, end_points # 73 x 73 x 64 net = slim.max_pool2d(net, 3, stride=2, padding=padding, scope='MaxPool_3a_3x3') if add_and_check_final('MaxPool_3a_3x3', net): return net, end_points # 73 x 73 x 80 net = slim.conv2d(net, 80, 1, padding=padding, scope='Conv2d_3b_1x1') if add_and_check_final('Conv2d_3b_1x1', net): return net, end_points # 71 x 71 x 192 net = slim.conv2d(net, 192, 3, padding=padding, scope='Conv2d_4a_3x3') if add_and_check_final('Conv2d_4a_3x3', net): return net, end_points # 35 x 35 x 192 net = slim.max_pool2d(net, 3, stride=2, padding=padding, scope='MaxPool_5a_3x3') if add_and_check_final('MaxPool_5a_3x3', net): return net, end_points # 35 x 35 x 320 with tf.variable_scope('Mixed_5b'): with tf.variable_scope('Branch_0'): tower_conv = slim.conv2d(net, 96, 1, scope='Conv2d_1x1') with tf.variable_scope('Branch_1'): tower_conv1_0 = slim.conv2d(net, 48, 1, scope='Conv2d_0a_1x1') tower_conv1_1 = slim.conv2d(tower_conv1_0, 64, 5, scope='Conv2d_0b_5x5') with tf.variable_scope('Branch_2'): tower_conv2_0 = slim.conv2d(net, 64, 1, scope='Conv2d_0a_1x1') tower_conv2_1 = slim.conv2d(tower_conv2_0, 96, 3, scope='Conv2d_0b_3x3') tower_conv2_2 = slim.conv2d(tower_conv2_1, 96, 3, scope='Conv2d_0c_3x3') with tf.variable_scope('Branch_3'): tower_pool = slim.avg_pool2d(net, 3, stride=1, padding='SAME', scope='AvgPool_0a_3x3') tower_pool_1 = slim.conv2d(tower_pool, 64, 1, scope='Conv2d_0b_1x1') net = tf.concat( [tower_conv, tower_conv1_1, tower_conv2_2, tower_pool_1], 3) if add_and_check_final('Mixed_5b', net): return net, end_points # TODO(alemi): Register intermediate endpoints net = slim.repeat(net, 10, block35, scale=0.17, activation_fn=activation_fn) # 17 x 17 x 1088 if output_stride == 8, # 33 x 33 x 1088 if output_stride == 16 use_atrous = output_stride == 8 with tf.variable_scope('Mixed_6a'): with tf.variable_scope('Branch_0'): tower_conv = slim.conv2d(net, 384, 3, stride=1 if use_atrous else 2, padding=padding, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): tower_conv1_0 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1') tower_conv1_1 = slim.conv2d(tower_conv1_0, 256, 3, scope='Conv2d_0b_3x3') tower_conv1_2 = slim.conv2d(tower_conv1_1, 384, 3, stride=1 if use_atrous else 2, padding=padding, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_2'): tower_pool = slim.max_pool2d(net, 3, stride=1 if use_atrous else 2, padding=padding, scope='MaxPool_1a_3x3') net = tf.concat([tower_conv, tower_conv1_2, tower_pool], 3) if add_and_check_final('Mixed_6a', net): return net, end_points # TODO(alemi): register intermediate endpoints with slim.arg_scope([slim.conv2d], rate=2 if use_atrous else 1): net = slim.repeat(net, 20, block17, scale=0.10, activation_fn=activation_fn) if add_and_check_final('PreAuxLogits', net): return net, end_points if output_stride == 8: # TODO(gpapan): Properly support output_stride for the rest of the net. raise ValueError( 'output_stride==8 is only supported up to the ' 'PreAuxlogits end_point for now.') # 8 x 8 x 2080 with tf.variable_scope('Mixed_7a'): with tf.variable_scope('Branch_0'): tower_conv = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1') tower_conv_1 = slim.conv2d(tower_conv, 384, 3, stride=2, padding=padding, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): tower_conv1 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1') tower_conv1_1 = slim.conv2d(tower_conv1, 288, 3, stride=2, padding=padding, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_2'): tower_conv2 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1') tower_conv2_1 = slim.conv2d(tower_conv2, 288, 3, scope='Conv2d_0b_3x3') tower_conv2_2 = slim.conv2d(tower_conv2_1, 320, 3, stride=2, padding=padding, scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_3'): tower_pool = slim.max_pool2d(net, 3, stride=2, padding=padding, scope='MaxPool_1a_3x3') net = tf.concat( [tower_conv_1, tower_conv1_1, tower_conv2_2, tower_pool], 3) if add_and_check_final('Mixed_7a', net): return net, end_points # TODO(alemi): register intermediate endpoints net = slim.repeat(net, 9, block8, scale=0.20, activation_fn=activation_fn) net = block8(net, activation_fn=None) # 8 x 8 x 1536 net = slim.conv2d(net, 1536, 1, scope='Conv2d_7b_1x1') if add_and_check_final('Conv2d_7b_1x1', net): return net, end_points raise ValueError('final_endpoint (%s) not recognized', final_endpoint)
def mobilenet_v1(inputs, num_classes=1000, dropout_keep_prob=0.999, is_training=True, min_depth=8, depth_multiplier=1.0, conv_defs=None, prediction_fn=tf.contrib.layers.softmax, spatial_squeeze=True, reuse=None, scope='MobilenetV1', global_pool=False): """Mobilenet v1 model for classification. Args: inputs: a tensor of shape [batch_size, height, width, channels]. num_classes: number of predicted classes. If 0 or None, the logits layer is omitted and the input features to the logits layer (before dropout) are returned instead. dropout_keep_prob: the percentage of activation values that are retained. is_training: whether is training or not. min_depth: Minimum depth value (number of channels) for all convolution ops. Enforced when depth_multiplier < 1, and not an active constraint when depth_multiplier >= 1. depth_multiplier: Float multiplier for the depth (number of channels) for all convolution ops. The value must be greater than zero. Typical usage will be to set this value in (0, 1) to reduce the number of parameters or computation cost of the model. conv_defs: A list of ConvDef namedtuples specifying the net architecture. prediction_fn: a function to get predictions out of logits. spatial_squeeze: if True, logits is of shape is [B, C], if false logits is of shape [B, 1, 1, C], where B is batch_size and C is number of classes. 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. global_pool: Optional boolean flag to control the avgpooling before the logits layer. If false or unset, pooling is done with a fixed window that reduces default-sized inputs to 1x1, while larger inputs lead to larger outputs. If true, any input size is pooled down to 1x1. Returns: net: a 2D Tensor with the logits (pre-softmax activations) if num_classes is a non-zero integer, or the non-dropped-out input to the logits layer if num_classes is 0 or None. end_points: a dictionary from components of the network to the corresponding activation. Raises: ValueError: Input rank is invalid. """ input_shape = inputs.get_shape().as_list() if len(input_shape) != 4: raise ValueError('Invalid input tensor rank, expected 4, was: %d' % len(input_shape)) with tf.variable_scope(scope, 'MobilenetV1', [inputs], reuse=reuse) as scope: with slim.arg_scope([slim.batch_norm, slim.dropout], is_training=is_training): net, end_points = mobilenet_v1_base( inputs, scope=scope, min_depth=min_depth, depth_multiplier=depth_multiplier, conv_defs=conv_defs) with tf.variable_scope('Logits'): if global_pool: # Global average pooling. net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool') end_points['global_pool'] = net else: # Pooling with a fixed kernel size. kernel_size = _reduced_kernel_size_for_small_input( net, [7, 7]) net = slim.avg_pool2d(net, kernel_size, padding='VALID', scope='AvgPool_1a') end_points['AvgPool_1a'] = net if not num_classes: return net, end_points # 1 x 1 x 1024 net = slim.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_1b') logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None, normalizer_fn=None, scope='Conv2d_1c_1x1') if spatial_squeeze: logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze') end_points['Logits'] = logits if prediction_fn: end_points['Predictions'] = prediction_fn(logits, scope='Predictions') return logits, end_points
def inception_resnet_v2(inputs, num_classes=1001, is_training=True, dropout_keep_prob=0.8, reuse=None, scope='InceptionResnetV2', create_aux_logits=True, activation_fn=tf.nn.relu): """Creates the Inception Resnet V2 model. Args: inputs: a 4-D tensor of size [batch_size, height, width, 3]. Dimension batch_size may be undefined. If create_aux_logits is false, also height and width may be undefined. num_classes: number of predicted classes. If 0 or None, the logits layer is omitted and the input features to the logits layer (before dropout) are returned instead. is_training: whether is training or not. dropout_keep_prob: float, the fraction to keep before final layer. 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. create_aux_logits: Whether to include the auxilliary logits. activation_fn: Activation function for conv2d. Returns: net: the output of the logits layer (if num_classes is a non-zero integer), or the non-dropped-out input to the logits layer (if num_classes is 0 or None). end_points: the set of end_points from the inception model. """ end_points = {} with tf.variable_scope(scope, 'InceptionResnetV2', [inputs], reuse=reuse) as scope: with slim.arg_scope([slim.batch_norm, slim.dropout], is_training=is_training): net, end_points = inception_resnet_v2_base( inputs, scope=scope, activation_fn=activation_fn) if create_aux_logits and num_classes: with tf.variable_scope('AuxLogits'): aux = end_points['PreAuxLogits'] aux = slim.avg_pool2d(aux, 5, stride=3, padding='VALID', scope='Conv2d_1a_3x3') aux = slim.conv2d(aux, 128, 1, scope='Conv2d_1b_1x1') aux = slim.conv2d(aux, 768, aux.get_shape()[1:3], padding='VALID', scope='Conv2d_2a_5x5') aux = slim.flatten(aux) aux = slim.fully_connected(aux, num_classes, activation_fn=None, scope='Logits') end_points['AuxLogits'] = aux with tf.variable_scope('Logits'): # TODO(sguada,arnoegw): Consider adding a parameter global_pool which # can be set to False to disable pooling here (as in resnet_*()). kernel_size = net.get_shape()[1:3] if kernel_size.is_fully_defined(): net = slim.avg_pool2d(net, kernel_size, padding='VALID', scope='AvgPool_1a_8x8') else: net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool') end_points['global_pool'] = net if not num_classes: return net, end_points net = slim.flatten(net) net = slim.dropout(net, dropout_keep_prob, is_training=is_training, scope='Dropout') end_points['PreLogitsFlatten'] = net logits = slim.fully_connected(net, num_classes, activation_fn=None, scope='Logits') end_points['Logits'] = logits end_points['Predictions'] = tf.nn.softmax(logits, name='Predictions') return logits, end_points