我们从Python开源项目中，提取了以下17个代码示例，用于说明如何使用tensorflow.contrib.slim.variance_scaling_initializer()。
def resnet_arg_scope(is_training=True, batch_norm_decay=0.997, batch_norm_epsilon=1e-5, batch_norm_scale=True): batch_norm_params = { 'is_training': False, 'decay': batch_norm_decay, 'epsilon': batch_norm_epsilon, 'scale': batch_norm_scale, 'trainable': False, 'updates_collections': tf.GraphKeys.UPDATE_OPS } with arg_scope( [slim.conv2d], weights_regularizer=slim.l2_regularizer(cfg.TRAIN.WEIGHT_DECAY), weights_initializer=slim.variance_scaling_initializer(), trainable=is_training, activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): with arg_scope([slim.batch_norm], **batch_norm_params) as arg_sc: return arg_sc
def _extra_conv_arg_scope_with_bn(weight_decay=0.00001, activation_fn=None, batch_norm_decay=0.997, batch_norm_epsilon=1e-5, batch_norm_scale=True): batch_norm_params = { 'decay': batch_norm_decay, 'epsilon': batch_norm_epsilon, 'scale': batch_norm_scale, 'updates_collections': tf.GraphKeys.UPDATE_OPS, } with slim.arg_scope( [slim.conv2d], weights_regularizer=slim.l2_regularizer(weight_decay), weights_initializer=slim.variance_scaling_initializer(), activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): with slim.arg_scope([slim.batch_norm], **batch_norm_params): with slim.arg_scope([slim.max_pool2d], padding='SAME') as arg_sc: return arg_sc
def _extra_conv_arg_scope_with_bn(weight_decay=0.00001, activation_fn=None, batch_norm_decay=0.997, batch_norm_epsilon=1e-5, batch_norm_scale=True): batch_norm_params = { 'decay': batch_norm_decay, 'epsilon': batch_norm_epsilon, 'scale': batch_norm_scale, 'updates_collections': tf.GraphKeys.UPDATE_OPS_EXTRA, } with slim.arg_scope( [slim.conv2d], weights_regularizer=slim.l2_regularizer(weight_decay), weights_initializer=slim.variance_scaling_initializer(), activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): with slim.arg_scope([slim.batch_norm], **batch_norm_params): with slim.arg_scope([slim.max_pool2d], padding='SAME') as arg_sc: return arg_sc
def resnet_arg_scope(is_training=True): """Sets up the default arguments for the CIFAR-10 resnet model.""" batch_norm_params = { 'is_training': is_training, 'decay': 0.9, 'epsilon': 0.001, 'scale': True, # This forces batch_norm to compute the moving averages in-place # instead of using a global collection which does not work with tf.cond. # 'updates_collections': None, } with slim.arg_scope([slim.conv2d, slim.batch_norm], activation_fn=lrelu): with slim.arg_scope( [slim.conv2d], weights_regularizer=slim.l2_regularizer(0.0002), weights_initializer=slim.variance_scaling_initializer(), normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): with slim.arg_scope([slim.batch_norm], **batch_norm_params) as arg_sc: return arg_sc
def _create_baseline(self, n_output=1, n_hidden=100, is_zero_init=False, collection='BASELINE'): # center input h = self._x if self.mean_xs is not None: h -= self.mean_xs if is_zero_init: initializer = init_ops.zeros_initializer() else: initializer = slim.variance_scaling_initializer() with slim.arg_scope([slim.fully_connected], variables_collections=[collection, Q_COLLECTION], trainable=False, weights_initializer=initializer): h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh) baseline = slim.fully_connected(h, n_output, activation_fn=None) if n_output == 1: baseline = tf.reshape(baseline, [-1]) # very important to reshape return baseline
def inference(images, num_classes, is_traiing=True, scope='inception_v3'): """Build Inception v3 model architecture. See here for reference: http://arxiv.org/abs/1512.00567 Args: images: Images returned from inputs() or distorted_inputs(). num_classes: number of classes for_training: If set to `True`, build the inference model for training. Kernels that operate differently for inference during training e.g. dropout, are appropriately configured. restore_logits: whether or not the logits layers should be restored. Useful for fine-tuning a model with different num_classes. scope: optional prefix string identifying the ImageNet tower. Returns: Logits. 2-D float Tensor. Auxiliary Logits. 2-D float Tensor of side-head. Used for training only. """ # Parameters for BatchNorm. batch_norm_params = { # Decay for the moving averages. 'decay': BATCHNORM_MOVING_AVERAGE_DECAY, # epsilon to prevent 0s in variance. 'epsilon': 0.001, # calculate moving average or using exist one 'is_training': is_traiing } # Set weight_decay for weights in Conv and FC layers. with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_regularizer=slim.l2_regularizer(FLAGS.weight_decay)): with slim.arg_scope([slim.conv2d], weights_initializer=slim.variance_scaling_initializer(), activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): logits, endpoints = inception_v3( images, num_classes=num_classes, dropout_keep_prob=0.8, is_training=is_traiing, scope=scope ) # Add summaries for viewing model statistics on TensorBoard. _activation_summaries(endpoints) # Grab the logits associated with the side head. Employed during training. auxiliary_logits = endpoints['aux_logits'] return logits, auxiliary_logits
def inference(images, num_classes, is_training=True, scope='squeeze'): """ Args: images: Images returned from inputs() or distorted_inputs(). num_classes: number of classes for_training: If set to `True`, build the inference model for training. Kernels that operate differently for inference during training e.g. dropout, are appropriately configured. restore_logits: whether or not the logits layers should be restored. Useful for fine-tuning a model with different num_classes. scope: optional prefix string identifying the ImageNet tower. Returns: Logits. 2-D float Tensor. Auxiliary Logits. 2-D float Tensor of side-head. Used for training only. """ # Parameters for BatchNorm. batch_norm_params = { # Decay for the moving averages. 'decay': BATCHNORM_MOVING_AVERAGE_DECAY, # epsilon to prevent 0s in variance. 'epsilon': 0.001, # calculate moving average or using exist one 'is_training': is_training } # Set weight_decay for weights in Conv and FC layers. with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_regularizer=slim.l2_regularizer(FLAGS.weight_decay)): with slim.arg_scope([slim.conv2d], weights_initializer=slim.variance_scaling_initializer(), activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): logits, endpoints = squeezenet( images, num_classes=num_classes, keep_prob=0.5, is_training=is_training, scope=scope ) # Add summaries for viewing model statistics on TensorBoard. _activation_summaries(endpoints) return logits
def inference(images, num_classes, is_training=True,scope='densenet_121'): """ Args: images: Images returned from inputs() or distorted_inputs(). num_classes: number of classes for_training: If set to `True`, build the inference model for training. Kernels that operate differently for inference during training e.g. dropout, are appropriately configured. restore_logits: whether or not the logits layers should be restored. Useful for fine-tuning a model with different num_classes. scope: optional prefix string identifying the ImageNet tower. Returns: Logits. 2-D float Tensor. Auxiliary Logits. 2-D float Tensor of side-head. Used for training only. """ # Parameters for BatchNorm. batch_norm_params = { # Decay for the moving averages. 'decay': BATCHNORM_MOVING_AVERAGE_DECAY, # epsilon to prevent 0s in variance. 'epsilon': 0.001, # calculate moving average or using exist one 'is_training': is_training } # Set weight_decay for weights in Conv and FC layers. with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_regularizer=slim.l2_regularizer(FLAGS.weight_decay)): with slim.arg_scope([slim.conv2d], weights_initializer=slim.variance_scaling_initializer(), activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): logits, endpoints = densenet_a( images, num_classes=num_classes, keep_prob=0.2, is_training=is_training, scope=scope ) # Add summaries for viewing model statistics on TensorBoard. _activation_summaries(endpoints) return logits
def inference(images, num_classes, is_training=True, scope='vgg_16'): """Build Inception v3 model architecture. See here for reference: http://arxiv.org/abs/1512.00567 Args: images: Images returned from inputs() or distorted_inputs(). num_classes: number of classes for_training: If set to `True`, build the inference model for training. Kernels that operate differently for inference during training e.g. dropout, are appropriately configured. restore_logits: whether or not the logits layers should be restored. Useful for fine-tuning a model with different num_classes. scope: optional prefix string identifying the ImageNet tower. Returns: Logits. 2-D float Tensor. Auxiliary Logits. 2-D float Tensor of side-head. Used for training only. """ # Parameters for BatchNorm. batch_norm_params = { # Decay for the moving averages. 'decay': BATCHNORM_MOVING_AVERAGE_DECAY, # epsilon to prevent 0s in variance. 'epsilon': 0.001, # calculate moving average or using exist one 'is_training': is_training } # Set weight_decay for weights in Conv and FC layers. with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_regularizer=slim.l2_regularizer(FLAGS.weight_decay)): with slim.arg_scope([slim.conv2d], weights_initializer=slim.variance_scaling_initializer(), activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): logits, endpoints = vgg_16( images, num_classes=num_classes, dropout_keep_prob=0.8, is_training=is_training, scope=scope ) # Add summaries for viewing model statistics on TensorBoard. _activation_summaries(endpoints) return logits
def resnet_arg_scope(weight_decay=0.0001, batch_norm_decay=0.997, batch_norm_epsilon=1e-5, batch_norm_scale=True): """Defines the default ResNet arg scope. TODO(gpapan): The batch-normalization related default values above are appropriate for use in conjunction with the reference ResNet models released at https://github.com/KaimingHe/deep-residual-networks. When training ResNets from scratch, they might need to be tuned. Args: weight_decay: The weight decay to use for regularizing the model. batch_norm_decay: The moving average decay when estimating layer activation statistics in batch normalization. batch_norm_epsilon: Small constant to prevent division by zero when normalizing activations by their variance in batch normalization. batch_norm_scale: If True, uses an explicit `gamma` multiplier to scale the activations in the batch normalization layer. Returns: An `arg_scope` to use for the resnet models. """ batch_norm_params = { 'decay': batch_norm_decay, 'epsilon': batch_norm_epsilon, 'scale': batch_norm_scale, 'updates_collections': tf.GraphKeys.UPDATE_OPS, } with slim.arg_scope( [slim.conv2d], weights_regularizer=slim.l2_regularizer(weight_decay), weights_initializer=slim.variance_scaling_initializer(), activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params): with slim.arg_scope([slim.batch_norm], **batch_norm_params): # The following implies padding='SAME' for pool1, which makes feature # alignment easier for dense prediction tasks. This is also used in # https://github.com/facebook/fb.resnet.torch. However the accompanying # code of 'Deep Residual Learning for Image Recognition' uses # padding='VALID' for pool1. You can switch to that choice by setting # slim.arg_scope([slim.max_pool2d], padding='VALID'). with slim.arg_scope([slim.max_pool2d], padding='SAME') as arg_sc: return arg_sc
def _q_func(self, samples, collection='Q_FUNC'): '''Returns learning signal and function. This is the implementation for SBNs for the ELBO. Args: samples: dictionary of sampled latent variables logQ: list of log q(h_i) terms log_likelihood_func: function used to compute log probs for the latent variables Returns: learning_signal: the "reward" function function_term: part of the function that depends on the parameters and needs to have the gradient taken through ''' reuse=None if not self.run_q_func else True if self.hparams.task in ['sbn', 'omni']: with slim.arg_scope([slim.fully_connected], weights_initializer=slim.variance_scaling_initializer(), variables_collections=[collection, tf.GraphKeys.GLOBAL_VARIABLES, Q_COLLECTION]): # for i in reversed(xrange(self.hparams.n_layer)): # if i == 0: # n_output = self.hparams.n_input # else: # n_output = self.hparams.n_hidden n_output = self.hparams.n_input i = self.hparams.n_layer - 1 # use the last layer input = 2.0*samples[i]['activation']-1.0 h = self._create_transformation(input, n_output, reuse=reuse, scope_prefix='q_func_%d' % i) h = tf.reduce_sum(h) self.run_q_func = True return h, h elif self.hparams.task == 'sp': with slim.arg_scope([slim.fully_connected], weights_initializer=slim.variance_scaling_initializer(), variables_collections=[collection, tf.GraphKeys.GLOBAL_VARIABLES, Q_COLLECTION]): n_output = int(self.hparams.n_input/2) i = self.hparams.n_layer - 1 # use the last layer input = 2.0*samples[i]['activation']-1.0 h = self._create_transformation(input, n_output, reuse=reuse, scope_prefix='q_func_%d' % i) self.run_q_func = True return h, h
