def testSingleConvMaskAdded(self): kernel_size = 3 input_depth, output_depth = 8, 32 input_tensor = array_ops.ones((8, self.height, self.width, input_depth)) layers.masked_conv2d(input_tensor, output_depth, kernel_size) masks = ops.get_collection(core_layers.MASK_COLLECTION) self.assertEqual(len(masks), 1) self.assertListEqual(masks[0].get_shape().as_list(), [kernel_size, kernel_size, input_depth, output_depth]) masked_weight = ops.get_collection(core_layers.MASKED_WEIGHT_COLLECTION) self.assertEqual(len(masked_weight), 1) self.assertListEqual(masked_weight[0].get_shape().as_list(), [kernel_size, kernel_size, input_depth, output_depth])
def testMultipleConvMaskAdded(self): number_of_layers = 5 kernel_size = 3 base_depth = 4 depth_step = 7 input_tensor = array_ops.ones((8, self.height, self.width, base_depth)) top_layer = input_tensor for ix in range(number_of_layers): top_layer = layers.masked_conv2d(top_layer, base_depth + (ix + 1) * depth_step, kernel_size) masks = ops.get_collection(core_layers.MASK_COLLECTION) self.assertEqual(len(masks), number_of_layers) for ix in range(number_of_layers): self.assertListEqual(masks[ix].get_shape().as_list(), [ kernel_size, kernel_size, base_depth + ix * depth_step, base_depth + (ix + 1) * depth_step ]) masked_weight = ops.get_collection(core_layers.MASKED_WEIGHT_COLLECTION) self.assertEqual(len(masked_weight), number_of_layers) for ix in range(number_of_layers): self.assertListEqual(masked_weight[ix].get_shape().as_list(), [ kernel_size, kernel_size, base_depth + ix * depth_step, base_depth + (ix + 1) * depth_step ])
def testMultipleConvMaskAdded(self): number_of_layers = 5 kernel_size = 3 base_depth = 4 depth_step = 7 input_tensor = array_ops.ones((8, self.height, self.width, base_depth)) top_layer = input_tensor for ix in range(number_of_layers): top_layer = layers.masked_conv2d( top_layer, base_depth + (ix + 1) * depth_step, kernel_size) masks = ops.get_collection(core_layers.MASK_COLLECTION) self.assertEqual(len(masks), number_of_layers) for ix in range(number_of_layers): self.assertListEqual(masks[ix].get_shape().as_list(), [ kernel_size, kernel_size, base_depth + ix * depth_step, base_depth + (ix + 1) * depth_step ]) masked_weight = ops.get_collection( core_layers.MASKED_WEIGHT_COLLECTION) self.assertEqual(len(masked_weight), number_of_layers) for ix in range(number_of_layers): self.assertListEqual(masked_weight[ix].get_shape().as_list(), [ kernel_size, kernel_size, base_depth + ix * depth_step, base_depth + (ix + 1) * depth_step ])
def testSingleConvMaskAdded(self): kernel_size = 3 input_depth, output_depth = 8, 32 input_tensor = array_ops.ones( (8, self.height, self.width, input_depth)) layers.masked_conv2d(input_tensor, output_depth, kernel_size) masks = ops.get_collection(core_layers.MASK_COLLECTION) self.assertEqual(len(masks), 1) self.assertListEqual( masks[0].get_shape().as_list(), [kernel_size, kernel_size, input_depth, output_depth]) masked_weight = ops.get_collection( core_layers.MASKED_WEIGHT_COLLECTION) self.assertEqual(len(masked_weight), 1) self.assertListEqual( masked_weight[0].get_shape().as_list(), [kernel_size, kernel_size, input_depth, output_depth])
def _build_convolutional_model(self, number_of_layers): # Create a graph with several conv2d layers kernel_size = 3 base_depth = 4 depth_step = 7 height, width = 7, 9 with variable_scope.variable_scope("conv_model"): input_tensor = array_ops.ones((8, height, width, base_depth)) top_layer = input_tensor for ix in range(number_of_layers): top_layer = layers.masked_conv2d(top_layer, base_depth + (ix + 1) * depth_step, kernel_size, scope="Conv_" + str(ix)) return top_layer
def _build_convolutional_model(self, number_of_layers): # Create a graph with several conv2d layers kernel_size = 3 base_depth = 4 depth_step = 7 height, width = 7, 9 with variable_scope.variable_scope("conv_model"): input_tensor = array_ops.ones((8, height, width, base_depth)) top_layer = input_tensor for ix in range(number_of_layers): top_layer = layers.masked_conv2d( top_layer, base_depth + (ix + 1) * depth_step, kernel_size, scope="Conv_" + str(ix)) return top_layer
def pruning_inference(self, inputs): net = layers.masked_conv2d(inputs, 64, 3) net = layers.masked_conv2d(net, 64, 3) net = tf.layers.max_pooling2d(net, 2, 2) net = layers.masked_conv2d(net, 128, 3) net = layers.masked_conv2d(net, 128, 3) net = tf.layers.max_pooling2d(net, 2, 2) net = layers.masked_conv2d(net, 256, 3) net = layers.masked_conv2d(net, 256, 3) net = layers.masked_conv2d(net, 256, 3) net = tf.layers.max_pooling2d(net, 2, 2) net = tf.layers.flatten(net) net = layers.masked_fully_connected(net, 1024) net = layers.masked_fully_connected(net, 1024) logits = layers.masked_fully_connected(net, self.num_classes, activation_fn=None) return tf.identity(logits, name='logits')
def tf_fcn_model(image): _ = image _ = layers.masked_conv2d(_, 96, (3, 3), 1, 'SAME') _ = tf.layers.batch_normalization(_, name='norm1-1') _ = layers.masked_conv2d(_, 96, (3, 3), 1, 'SAME') _ = tf.layers.batch_normalization(_, name='norm1-2') _ = tf.layers.max_pooling2d(_, (3, 3), 2, 'SAME', name='pool1') _ = layers.masked_conv2d(_, 192, (3, 3), 1, 'SAME') _ = tf.layers.batch_normalization(_, name='norm2-1') _ = layers.masked_conv2d(_, 192, (3, 3), 1, 'SAME') _ = tf.layers.batch_normalization(_, name='norm2-2') _ = tf.layers.max_pooling2d(_, (3, 3), 2, 'SAME', name='pool2') _ = layers.masked_conv2d(_, 192, (3, 3), 1, 'VALID') _ = tf.layers.batch_normalization(_, name='norm3') _ = layers.masked_conv2d(_, 192, (1, 1), 1) _ = tf.layers.batch_normalization(_, name='norm4') _ = layers.masked_conv2d(_, 10, (1, 1), 1) _ = tf.layers.batch_normalization(_, name='norm5') _ = tf.layers.average_pooling2d(_, (6, 6), 1, name='avg_pool') y = _ logits = tf.reshape(y, [tf.shape(y)[0], 10]) return logits
def testInvalidRank5(self): input_tensor = array_ops.ones((8, 8, self.height, self.width, 3)) with self.assertRaisesRegexp(ValueError, 'rank'): layers.masked_conv2d(input_tensor, 32, 3)
def get_model(point_cloud, input_label, is_training, cat_num, part_num, \ batch_size, num_point, weight_decay=.00004, bn_decay=None): bn_decay = bn_decay if bn_decay is not None else 0.9 with tf.variable_scope("DGCNN"): batch_size = point_cloud.get_shape()[0].value num_point = point_cloud.get_shape()[1].value input_image = tf.expand_dims(point_cloud, -1) k = 20 bn_params = { "is_training": is_training, "decay": bn_decay, 'renorm': True } adj = tf_util.pairwise_distance(point_cloud) nn_idx = tf_util.knn(adj, k=k) edge_feature = tf_util.get_edge_feature(input_image, nn_idx=nn_idx, k=k) with tf.variable_scope('transform_net1') as sc: transform = input_transform_net(edge_feature, is_training, bn_decay, K=3) point_cloud_transformed = tf.matmul(point_cloud, transform) input_image = tf.expand_dims(point_cloud_transformed, -1) adj = tf_util.pairwise_distance(point_cloud_transformed) nn_idx = tf_util.knn(adj, k=k) edge_feature = tf_util.get_edge_feature(input_image, nn_idx=nn_idx, k=k) # out1 = tf_util.conv2d(edge_feature, 64, [1,1], # padding='VALID', stride=[1,1], # bn=True, is_training=is_training, weight_decay=weight_decay, # scope='adj_conv1', bn_decay=bn_decay, is_dist=True) out1 = layers.masked_conv2d( edge_feature, 64, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='adj_conv1') # out2 = tf_util.conv2d(out1, 64, [1,1], # padding='VALID', stride=[1,1], # bn=True, is_training=is_training, weight_decay=weight_decay, # scope='adj_conv2', bn_decay=bn_decay, is_dist=True) out2 = layers.masked_conv2d( out1, 64, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='adj_conv2') net_1 = tf.reduce_max(out2, axis=-2, keep_dims=True) adj = tf_util.pairwise_distance(net_1) nn_idx = tf_util.knn(adj, k=k) edge_feature = tf_util.get_edge_feature(net_1, nn_idx=nn_idx, k=k) # out3 = tf_util.conv2d(edge_feature, 64, [1,1], # padding='VALID', stride=[1,1], # bn=True, is_training=is_training, weight_decay=weight_decay, # scope='adj_conv3', bn_decay=bn_decay, is_dist=True) out3 = layers.masked_conv2d( edge_feature, 64, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='adj_conv3') # out4 = tf_util.conv2d(out3, 64, [1,1], # padding='VALID', stride=[1,1], # bn=True, is_training=is_training, weight_decay=weight_decay, # scope='adj_conv4', bn_decay=bn_decay, is_dist=True) out4 = layers.masked_conv2d( out3, 64, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='adj_conv4') net_2 = tf.reduce_max(out4, axis=-2, keep_dims=True) adj = tf_util.pairwise_distance(net_2) nn_idx = tf_util.knn(adj, k=k) edge_feature = tf_util.get_edge_feature(net_2, nn_idx=nn_idx, k=k) # out5 = tf_util.conv2d(edge_feature, 64, [1,1], # padding='VALID', stride=[1,1], # bn=True, is_training=is_training, weight_decay=weight_decay, # scope='adj_conv5', bn_decay=bn_decay, is_dist=True) out5 = layers.masked_conv2d( edge_feature, 64, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='adj_conv5') # out6 = tf_util.conv2d(out5, 64, [1,1], # padding='VALID', stride=[1,1], # bn=True, is_training=is_training, weight_decay=weight_decay, # scope='adj_conv6', bn_decay=bn_decay, is_dist=True) net_3 = tf.reduce_max(out5, axis=-2, keep_dims=True) # out7 = tf_util.conv2d(tf.concat([net_1, net_2, net_3], axis=-1), 1024, [1, 1], # padding='VALID', stride=[1,1], # bn=True, is_training=is_training, # scope='adj_conv7', bn_decay=bn_decay, is_dist=True) out7 = layers.masked_conv2d( tf.concat([net_1, net_2, net_3], axis=-1), 1024, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='adj_conv7') # out_max = tf_util.max_pool2d(out7, [num_point, 1], padding='VALID', scope='maxpool') out_max = slim.max_pool2d(out7, [num_point, 1], stride=1, padding='VALID', scope='maxpool') one_hot_label_expand = tf.reshape(input_label, [batch_size, 1, 1, cat_num]) # one_hot_label_expand = tf_util.conv2d(one_hot_label_expand, 64, [1, 1], # padding='VALID', stride=[1,1], # bn=True, is_training=is_training, # scope='one_hot_label_expand', bn_decay=bn_decay, is_dist=True) one_hot_label_expand = layers.masked_conv2d( one_hot_label_expand, 64, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='one_hot_label_expand') out_max = tf.concat(axis=3, values=[out_max, one_hot_label_expand]) expand = tf.tile(out_max, [1, num_point, 1, 1]) concat = tf.concat(axis=3, values=[expand, net_1, net_2, net_3]) # net2 = tf_util.conv2d(concat, 256, [1,1], padding='VALID', stride=[1,1], bn_decay=bn_decay, # bn=True, is_training=is_training, scope='seg/conv1', weight_decay=weight_decay, is_dist=True) net2 = layers.masked_conv2d( concat, 256, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='seg/conv1') # net2 = tf_util.dropout(net2, keep_prob=0.6, is_training=is_training, scope='seg/dp1') net2 = slim.dropout(net2, keep_prob=0.6, is_training=is_training, scope='seg/dp1') # net2 = tf_util.conv2d(net2, 256, [1,1], padding='VALID', stride=[1,1], bn_decay=bn_decay, # bn=True, is_training=is_training, scope='seg/conv2', weight_decay=weight_decay, is_dist=True) net2 = layers.masked_conv2d( net2, 256, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='seg/conv2') # net2 = tf_util.dropout(net2, keep_prob=0.6, is_training=is_training, scope='seg/dp2') net2 = slim.dropout(net2, keep_prob=0.6, is_training=is_training, scope='seg/dp2') # net2 = tf_util.conv2d(net2, 128, [1,1], padding='VALID', stride=[1,1], bn_decay=bn_decay, # bn=True, is_training=is_training, scope='seg/conv3', weight_decay=weight_decay, is_dist=True) net2 = layers.masked_conv2d( net2, 128, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='seg/conv3') # net2 = tf_util.conv2d(net2, part_num, [1,1], padding='VALID', stride=[1,1], activation_fn=None, # bn=False, scope='seg/conv4', weight_decay=weight_decay, is_dist=True) net2 = layers.masked_conv2d( net2, part_num, # max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=None, # normalizer_params=bn_params, biases_initializer=tf.contrib.layers.xavier_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=None, weights_initializer=tf.contrib.layers.xavier_initializer(), scope='seg/conv4') net2 = tf.reshape(net2, [batch_size, num_point, part_num]) return net2
def input_transform_net(edge_feature, is_training, bn_decay=None, K=3, scale=1., weight_decay=0.00004): """ Input (XYZ) Transform Net, input is BxNx3 gray image Return: Transformation matrix of size 3xK """ bn_params = {"is_training": is_training, "decay": bn_decay, } with tf.variable_scope(None, default_name="transform_net"): batch_size = edge_feature.get_shape()[0].value num_point = edge_feature.get_shape()[1].value neighbor = edge_feature.get_shape()[2].value # input_image = tf.expand_dims(point_cloud, -1) net = layers.masked_conv2d(edge_feature, # 64, max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, activation_fn=tf.nn.relu6, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tconv1') net = layers.masked_conv2d(net, # 128, max(int(round(128 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tconv2', activation_fn=tf.nn.relu6) net = tf.reduce_max(net, axis=-2, keepdims=True) # net = slim.max_pool2d(net, [1, neighbor], stride=1, padding='VALID') net = layers.masked_conv2d(net, # 1024, # max(int(round(1024 * scale)), 32), max(int(round(1024 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tconv3', activation_fn=tf.nn.relu6) # print(net) net = slim.max_pool2d(net, [num_point, 1], padding='VALID', scope='tmaxpool') # net = tf.reshape(net, [batch_size, 1, 1, -1]) # print(net) net = layers.masked_conv2d(net, # 512, max(int(round(512 * scale)), 32), [1, 1], padding='SAME', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tfc1', activation_fn=tf.nn.relu6) net = layers.masked_conv2d(net, # 256, max(int(round(256 * scale)), 32), [1, 1], padding='SAME', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tfc2', activation_fn=tf.nn.relu6) transform = layers.masked_conv2d(net, K * K, [1, 1], padding='SAME', stride=1, normalizer_fn=None, # normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='transform_XYZ', activation_fn=None, # activation_fn=tf.nn.relu6, ) transform = tf.reshape(transform, [batch_size, K, K]) return transform
def prunable_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 = prunable_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( [masked_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 = masked_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 = masked_conv2d( aux_logits, depth(768), kernel_size, weights_initializer=trunc_normal(0.01), padding='VALID', scope='Conv2d_2a_{}x{}'.format(*kernel_size)) aux_logits = masked_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 = masked_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 prunable_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([masked_conv2d, slim.max_pool2d, slim.avg_pool2d], stride=1, padding='VALID'): # 299 x 299 x 3 end_point = 'Conv2d_1a_3x3' net = masked_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 = masked_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 = masked_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 = masked_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 = masked_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([masked_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 = masked_conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(48), [1, 1], scope='Conv2d_0a_1x1') branch_1 = masked_conv2d(branch_1, depth(64), [5, 5], scope='Conv2d_0b_5x5') with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_2 = masked_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 = masked_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 = masked_conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(48), [1, 1], scope='Conv2d_0b_1x1') branch_1 = masked_conv2d(branch_1, depth(64), [5, 5], scope='Conv_1_0c_5x5') with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_2 = masked_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 = masked_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 = masked_conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(48), [1, 1], scope='Conv2d_0a_1x1') branch_1 = masked_conv2d(branch_1, depth(64), [5, 5], scope='Conv2d_0b_5x5') with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_2 = masked_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 = masked_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 = masked_conv2d(net, depth(384), [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(64), [1, 1], scope='Conv2d_0a_1x1') branch_1 = masked_conv2d(branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3') branch_1 = masked_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 = masked_conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(128), [1, 1], scope='Conv2d_0a_1x1') branch_1 = masked_conv2d(branch_1, depth(128), [1, 7], scope='Conv2d_0b_1x7') branch_1 = masked_conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(128), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(128), [7, 1], scope='Conv2d_0b_7x1') branch_2 = masked_conv2d(branch_2, depth(128), [1, 7], scope='Conv2d_0c_1x7') branch_2 = masked_conv2d(branch_2, depth(128), [7, 1], scope='Conv2d_0d_7x1') branch_2 = masked_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 = masked_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 = masked_conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') branch_1 = masked_conv2d(branch_1, depth(160), [1, 7], scope='Conv2d_0b_1x7') branch_1 = masked_conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(160), [7, 1], scope='Conv2d_0b_7x1') branch_2 = masked_conv2d(branch_2, depth(160), [1, 7], scope='Conv2d_0c_1x7') branch_2 = masked_conv2d(branch_2, depth(160), [7, 1], scope='Conv2d_0d_7x1') branch_2 = masked_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 = masked_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 = masked_conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') branch_1 = masked_conv2d(branch_1, depth(160), [1, 7], scope='Conv2d_0b_1x7') branch_1 = masked_conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(160), [7, 1], scope='Conv2d_0b_7x1') branch_2 = masked_conv2d(branch_2, depth(160), [1, 7], scope='Conv2d_0c_1x7') branch_2 = masked_conv2d(branch_2, depth(160), [7, 1], scope='Conv2d_0d_7x1') branch_2 = masked_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 = masked_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 = masked_conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') branch_1 = masked_conv2d(branch_1, depth(192), [1, 7], scope='Conv2d_0b_1x7') branch_1 = masked_conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(192), [7, 1], scope='Conv2d_0b_7x1') branch_2 = masked_conv2d(branch_2, depth(192), [1, 7], scope='Conv2d_0c_1x7') branch_2 = masked_conv2d(branch_2, depth(192), [7, 1], scope='Conv2d_0d_7x1') branch_2 = masked_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 = masked_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 = masked_conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') branch_0 = masked_conv2d(branch_0, depth(320), [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1') branch_1 = masked_conv2d(branch_1, depth(192), [1, 7], scope='Conv2d_0b_1x7') branch_1 = masked_conv2d(branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1') branch_1 = masked_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 = masked_conv2d(net, depth(320), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(384), [1, 1], scope='Conv2d_0a_1x1') branch_1 = tf.concat( axis=3, values=[ masked_conv2d(branch_1, depth(384), [1, 3], scope='Conv2d_0b_1x3'), masked_conv2d(branch_1, depth(384), [3, 1], scope='Conv2d_0b_3x1') ]) with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(448), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(384), [3, 3], scope='Conv2d_0b_3x3') branch_2 = tf.concat( axis=3, values=[ masked_conv2d(branch_2, depth(384), [1, 3], scope='Conv2d_0c_1x3'), masked_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 = masked_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 = masked_conv2d(net, depth(320), [1, 1], scope='Conv2d_0a_1x1') with tf.variable_scope('Branch_1'): branch_1 = masked_conv2d(net, depth(384), [1, 1], scope='Conv2d_0a_1x1') branch_1 = tf.concat( axis=3, values=[ masked_conv2d(branch_1, depth(384), [1, 3], scope='Conv2d_0b_1x3'), masked_conv2d(branch_1, depth(384), [3, 1], scope='Conv2d_0c_3x1') ]) with tf.variable_scope('Branch_2'): branch_2 = masked_conv2d(net, depth(448), [1, 1], scope='Conv2d_0a_1x1') branch_2 = masked_conv2d(branch_2, depth(384), [3, 3], scope='Conv2d_0b_3x3') branch_2 = tf.concat( axis=3, values=[ masked_conv2d(branch_2, depth(384), [1, 3], scope='Conv2d_0c_1x3'), masked_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 = masked_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 feature_transform_net(inputs, is_training, bn_decay=None, K=64, scale=1., weight_decay=0.00004): """ Feature Transform Net, input is BxNx1xK Return: Transformation matrix of size KxK """ bn_params = {"is_training": is_training, "decay": bn_decay, 'epsilon': 1e-3 } with tf.variable_scope(None, default_name="feature_transform_net"): batch_size = inputs.get_shape()[0].value num_point = inputs.get_shape()[1].value net = layers.masked_conv2d(inputs, # 64, max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, activation_fn=tf.nn.relu6, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tconv1') net = layers.masked_conv2d(net, # 128, max(int(round(128 * scale)), 32), [1, 1], padding='VALID', stride=1, activation_fn=tf.nn.relu6, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tconv2') net = layers.masked_conv2d(net, # 128, max(int(round(1024 * scale)), 32), [1, 1], padding='VALID', stride=1, activation_fn=tf.nn.relu6, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tconv3') net = slim.max_pool2d(net, [num_point, 1], padding='VALID', scope='tmaxpool') # net = tf.reshape(net, [batch_size, -1]) net = layers.masked_conv2d(net, # 128, max(int(round(512 * scale)), 32), [1, 1], padding='VALID', stride=1, activation_fn=tf.nn.relu6, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tfc1') net = layers.masked_conv2d(net, # 128, max(int(round(256 * scale)), 32), [1, 1], padding='VALID', stride=1, activation_fn=tf.nn.relu6, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='tfc2') transform = layers.masked_conv2d(net, K * K, [1, 1], padding='SAME', stride=1, normalizer_fn=None, # normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='transform_XYZ', activation_fn=None, # activation_fn=tf.nn.relu6, ) transform = tf.reshape(transform, [batch_size, K, K]) return transform
def testInvalidRank5(self): input_tensor = array_ops.ones((8, 8, self.height, self.width, 3)) with self.assertRaisesRegexp(ValueError, 'rank'): layers.masked_conv2d(input_tensor, 32, 3)
def sparse_conv2d(x, units, kernel_size, activation=None, use_bias=False, kernel_initializer=None, kernel_regularizer=None, bias_initializer=None, biases_regularizer=None, sparsity_technique='baseline', log_sigma2_initializer=None, log_alpha_initializer=None, normalizer_fn=None, strides=(1, 1), padding='SAME', threshold=3.0, clip_alpha=None, data_format='channels_last', is_training=False, name=None): """Function that constructs conv2d with any desired pruning method. Args: x: Input, float32 tensor. units: Int representing size of output tensor. kernel_size: The size of the convolutional window, int of list of ints. activation: If None, a linear activation is used. use_bias: Boolean specifying whether bias vector should be used. kernel_initializer: Initializer for the convolution weights. kernel_regularizer: Regularization method for the convolution weights. bias_initializer: Initalizer of the bias vector. biases_regularizer: Optional regularizer for the bias vector. sparsity_technique: Method used to introduce sparsity. ['threshold', 'variational_dropout', 'l0_regularization'] log_sigma2_initializer: Specified initializer of the log_sigma2 term used in variational dropout. log_alpha_initializer: Specified initializer of the log_alpha term used in l0 regularization. normalizer_fn: function used to transform the output activations. strides: stride length of convolution, a single int is expected. padding: May be populated as 'VALID' or 'SAME'. threshold: Theshold for masking variational dropout log alpha at test time. clip_alpha: Int that specifies range for clippling variational dropout log alpha values. data_format: Either 'channels_last', 'channels_first'. is_training: Boolean specifying whether it is training or eval. name: String speciying name scope of layer in network. Returns: Output: activations. Raises: ValueError: If the rank of the input is not greater than 2. """ if data_format == 'channels_last': data_format_channels = 'NHWC' elif data_format == 'channels_first': data_format_channels = 'NCHW' else: raise ValueError('Not a valid channel string:', data_format) layer_variable_getter = variable_getter({ 'bias': 'biases', 'kernel': 'weights', }) input_rank = x.get_shape().ndims if input_rank != 4: raise ValueError('Rank not supported {}'.format(input_rank)) with tf.variable_scope(name, 'Conv', [x], custom_getter=layer_variable_getter) as sc: input_shape = x.get_shape().as_list() if input_shape[-1] is None: raise ValueError( 'The last dimension of the inputs to `Convolution` ' 'should be defined. Found `None`.') pruning_methods = ['threshold'] if sparsity_technique in pruning_methods: return layers.masked_conv2d(inputs=x, num_outputs=units, kernel_size=kernel_size[0], stride=strides[0], padding=padding, data_format=data_format_channels, rate=1, activation_fn=activation, weights_initializer=kernel_initializer, weights_regularizer=kernel_regularizer, normalizer_fn=normalizer_fn, normalizer_params=None, biases_initializer=bias_initializer, biases_regularizer=biases_regularizer, outputs_collections=None, trainable=True, scope=sc) elif sparsity_technique == 'variational_dropout': vd_conv = vd.layers.Conv2D( num_outputs=units, kernel_size=kernel_size, strides=strides, activation=activation, kernel_initializer=kernel_initializer, kernel_regularizer=kernel_regularizer, bias_initializer=bias_initializer, bias_regularizer=biases_regularizer, log_sigma2_initializer=log_sigma2_initializer, is_training=is_training, use_bias=use_bias, padding=padding, data_format=data_format_channels, clip_alpha=clip_alpha, threshold=threshold, trainable=True, name=sc) return vd_conv.apply(x) elif sparsity_technique == 'l0_regularization': l0_conv = l0.layers.Conv2D( num_outputs=units, kernel_size=kernel_size, strides=strides, activation=activation, kernel_initializer=kernel_initializer, kernel_regularizer=kernel_regularizer, bias_initializer=bias_initializer, bias_regularizer=biases_regularizer, log_alpha_initializer=log_alpha_initializer, is_training=is_training, use_bias=use_bias, padding=padding, data_format=data_format_channels, trainable=True, name=sc) return l0_conv.apply(x) elif sparsity_technique == 'baseline': return tf.layers.conv2d(inputs=x, filters=units, kernel_size=kernel_size, strides=strides, padding=padding, use_bias=use_bias, kernel_initializer=kernel_initializer, kernel_regularizer=kernel_regularizer, data_format=data_format, name=name) else: raise ValueError( 'Unsupported sparsity technique {}'.format(sparsity_technique))
def get_network(point_cloud, is_training, neighbor=None, bn_decay=None, dynamic=True, STN=True, scale=1., concat_fea=True, weight_decay=0.00004): """ Classification PointNet, input is BxNx3, output Bx40 """ bn_decay = bn_decay if bn_decay is not None else 0.9 with tf.variable_scope("DGCNN"): batch_size = point_cloud.get_shape()[0].value num_point = point_cloud.get_shape()[1].value # point_cloud = tf.squeeze(point_cloud) # if batch_size == 1: # point_cloud = tf.expand_dims(point_cloud, 0) end_points = {} k = 20 bn_params = { "is_training": is_training, "decay": bn_decay, 'epsilon': 1e-3 } if STN: if neighbor is None: adj_matrix = tf_util.pairwise_distance(point_cloud) nn_idx = tf_util.knn(adj_matrix, k=k) else: nn_idx = neighbor edge_feature = tf_util.get_edge_feature(point_cloud, nn_idx=nn_idx, k=k) transform = input_transform_net(edge_feature, is_training, bn_decay, K=3, weight_decay=weight_decay, scale=scale) with tf.variable_scope("Transform"): point_cloud_transformed = tf.matmul(point_cloud, transform) if dynamic: adj_matrix = tf_util.pairwise_distance(point_cloud_transformed) nn_idx = tf_util.knn(adj_matrix, k=k) else: point_cloud_transformed = point_cloud if neighbor is None: adj_matrix = tf_util.pairwise_distance(point_cloud_transformed) nn_idx = tf_util.knn(adj_matrix, k=k) else: nn_idx = neighbor edge_feature = tf_util.get_edge_feature(point_cloud_transformed, nn_idx=nn_idx, k=k) with tf.variable_scope("dgcnn1"): net = layers.masked_conv2d( edge_feature, # 64, max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6) net = tf.reduce_max(net, axis=-2, keepdims=True) # net = slim.max_pool2d(net, [1, k], stride=1, padding='VALID') net1 = net if dynamic: adj_matrix = tf_util.pairwise_distance(net) nn_idx = tf_util.knn(adj_matrix, k=k) edge_feature = tf_util.get_edge_feature(net, nn_idx=nn_idx, k=k, concat_feature=concat_fea) with tf.variable_scope("dgcnn2"): net = layers.masked_conv2d( edge_feature, # 64, max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6) net = tf.reduce_max(net, axis=-2, keepdims=True) # net = slim.max_pool2d(net, [1, k], stride=1, padding='VALID') net2 = net if dynamic: adj_matrix = tf_util.pairwise_distance(net) nn_idx = tf_util.knn(adj_matrix, k=k) edge_feature = tf_util.get_edge_feature(net, nn_idx=nn_idx, k=k, concat_feature=concat_fea) with tf.variable_scope("dgcnn3"): net = layers.masked_conv2d( edge_feature, # 64, max(int(round(64 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6) net = tf.reduce_max(net, axis=-2, keepdims=True) # net = slim.max_pool2d(net, [1, k], stride=1, padding='VALID') net3 = net if dynamic: adj_matrix = tf_util.pairwise_distance(net) nn_idx = tf_util.knn(adj_matrix, k=k) edge_feature = tf_util.get_edge_feature(net, nn_idx=nn_idx, k=k, concat_feature=concat_fea) with tf.variable_scope("dgcnn4"): net = layers.masked_conv2d( edge_feature, # 128, max(int(round(128 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6) net = tf.reduce_max(net, axis=-2, keepdims=True) # net = slim.max_pool2d(net, [1, k], stride=1, padding='VALID') net4 = net with tf.variable_scope("agg"): net = layers.masked_conv2d( tf.concat([net1, net2, net3, net4], axis=-1), # 1024, # max(int(round(1024 * scale)), 32), max(int(round(1024 * scale)), 32), [1, 1], padding='VALID', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), activation_fn=tf.nn.relu6) net = tf.reduce_max(net, axis=1, keepdims=True) # net = slim.max_pool2d(net, [num_point, 1], stride=1, padding='VALID') # MLP on global point cloud vector # net = tf.reshape(net, [batch_size, 1, 1, -1]) net = layers.masked_conv2d( net, # 512, max(int(round(512 * scale)), 32), [1, 1], padding='SAME', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='fc1', activation_fn=tf.nn.relu6) net = slim.dropout(net, keep_prob=0.5, is_training=is_training, scope='dp1') net = layers.masked_conv2d( net, # 256, max(int(round(256 * scale)), 32), [1, 1], padding='SAME', stride=1, normalizer_fn=slim.batch_norm, normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='fc2', activation_fn=tf.nn.relu6) net = slim.dropout(net, keep_prob=0.5, is_training=is_training, scope='dp2') net = layers.masked_conv2d( net, 40, [1, 1], padding='SAME', stride=1, # normalizer_fn=slim.batch_norm, # normalizer_params=bn_params, biases_initializer=tf.zeros_initializer(), weights_regularizer=slim.l2_regularizer(weight_decay), scope='fc3', # activation_fn=tf.nn.relu6, activation_fn=None, ) net = tf.reshape(net, [batch_size, -1]) return net, end_points