total_loss_layer.py File Reference

Classes
class	total_loss_layer.TotalLossLayer

Namespaces
namespace	total_loss_layer

Functions
def	total_loss_layer.forward (self, bottom, top)
def	total_loss_layer.backward (self, bottom, top)

Variables
	total_loss_layer.res = absolute_difference(labels, predictions)
int	total_loss_layer.variance_loss = 0
	total_loss_layer.temp1 = tf.reduce_mean(y_GT[:,:,:,(i*8):(i*8)+8], axis=-1)
	total_loss_layer.temp2 = tf.reduce_mean(pred_LF_loss[:,:,:,(i*8):(i*8)+8], axis=-1)
	total_loss_layer.temp3 = tf.reduce_mean(y_GT_H[:,:,:,(i*8):(i*8)+8], axis=-1)
	total_loss_layer.temp4 = tf.reduce_mean(pred_LF_loss_H[:,:,:,(i*8):(i*8)+8], axis=-1)
	total_loss_layer.mean = tf.where(tf.is_nan(mean), tf.zeros_like(mean), mean)
	total_loss_layer.variance = tf.where(tf.is_nan(variance), tf.zeros_like(variance), variance)
	total_loss_layer.mean2 = tf.where(tf.is_nan(mean2), tf.zeros_like(mean2), mean2)
	total_loss_layer.variance2 = tf.where(tf.is_nan(variance2), tf.zeros_like(variance2), variance2)
	total_loss_layer.mean_loss = tf.losses.absolute_difference(mean, mean2)
tuple	total_loss_layer.tv_loss_x = (total_variation_self(flow_LF[:,:,:,0::2]))
tuple	total_loss_layer.tv_loss_y = (total_variation_self(flow_LF[:,:,:,1::2]))
	total_loss_layer.tv_loss = tf.reduce_mean(tv_loss_x) + tf.reduce_mean(tv_loss_y)
tuple	total_loss_layer.Total_Loss = (LAMBDA_L1 * pixel_loss_V) + (LAMBDA_L1 * pixel_loss_H) \
	total_loss_layer.src_h
	L_Loss ###. More...
	total_loss_layer.gt_h