def _activation_summary(x): """Helper to create summaries for activations. Creates a summary that provides a histogram of activations. Creates a summary that measure the sparsity of activations. Args: x: Tensor Returns: nothing """ # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training # session. This helps the clarity of presentation on tensorboard. tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name) tf.histogram_summary(tensor_name + '/activations', x) tf.scalar_summary(tensor_name + '/sparsity', tf.nn.zero_fraction(x))
def _activation_summary(x): """Helper to create summaries for activations. Creates a summary that provides a histogram of activations. Creates a summary that measure the sparsity of activations. Args: x: Tensor Returns: nothing """ # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training # session. This helps the clarity of presentation on tensorboard. tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name) tf.histogram_summary(tensor_name + '/activations', x) tf.scalar_summary(tensor_name + '/sparsity', tf.nn.zero_fraction(x))
def train_setup(total_loss, global_step): """Optimize CIFAR-10 model. """ # Variables that affect learning rate. num_batches_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY) # Decay the learning rate exponentially based on the number of steps. lr = tf.train.exponential_decay(INITIAL_LEARNING_RATE, global_step, decay_steps, LEARNING_RATE_DECAY_FACTOR, staircase=True) tf.scalar_summary('learning_rate', lr) # Generate moving averages of all losses and associated summaries. loss_averages_op = _add_loss_summaries(total_loss) # Compute gradients. with tf.control_dependencies([loss_averages_op]): opt = tf.train.GradientDescentOptimizer(lr) grads = opt.compute_gradients(total_loss) # Apply gradients. apply_gradient_op = opt.apply_gradients(grads, global_step=global_step) # Add histograms for trainable variables. for var in tf.trainable_variables(): tf.histogram_summary(var.op.name, var) # Add histograms for gradients. for grad, var in grads: if grad is not None: tf.histogram_summary(var.op.name + '/gradients', grad) # Track the moving averages of all trainable variables. variable_averages = tf.train.ExponentialMovingAverage( MOVING_AVERAGE_DECAY, global_step) variables_averages_op = variable_averages.apply(tf.trainable_variables()) with tf.control_dependencies([apply_gradient_op, variables_averages_op]): train_op = tf.no_op(name='train') return train_op
def train_setup(total_loss, global_step): """Optimize CIFAR-10 model. """ # Variables that affect learning rate. num_batches_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY) # Decay the learning rate exponentially based on the number of steps. lr = tf.train.exponential_decay(INITIAL_LEARNING_RATE, global_step, decay_steps, LEARNING_RATE_DECAY_FACTOR, staircase=True) tf.scalar_summary('learning_rate', lr) # Generate moving averages of all losses and associated summaries. loss_averages_op = _add_loss_summaries(total_loss) # Compute gradients. with tf.control_dependencies([loss_averages_op]): opt = tf.train.GradientDescentOptimizer(lr) grads = opt.compute_gradients(total_loss) # Apply gradients. apply_gradient_op = opt.apply_gradients(grads, global_step=global_step) # Add histograms for trainable variables. for var in tf.trainable_variables(): tf.histogram_summary(var.op.name, var) # Add histograms for gradients. for grad, var in grads: if grad is not None: tf.histogram_summary(var.op.name + '/gradients', grad) # Track the moving averages of all trainable variables. variable_averages = tf.train.ExponentialMovingAverage( MOVING_AVERAGE_DECAY, global_step) variables_averages_op = variable_averages.apply(tf.trainable_variables()) with tf.control_dependencies([apply_gradient_op, variables_averages_op]): train_op = tf.no_op(name='train') return train_op