d88e9d3f12
Since dense-depth will use half labels by default, the nyu train/eval datasets can be loaded from here at half resolutions for labels
23 lines
689 B
Python
23 lines
689 B
Python
import tensorflow as tf
|
|
import tensorflow.keras.backend as K
|
|
|
|
|
|
def dense_depth_loss_function(y_true, y_pred, theta=0.1, maxDepthVal=1000.0 / 10.0):
|
|
# Point-wise depth
|
|
l_depth = K.mean(K.abs(y_pred - y_true), axis=-1)
|
|
|
|
# Edges
|
|
dy_true, dx_true = tf.image.image_gradients(y_true)
|
|
dy_pred, dx_pred = tf.image.image_gradients(y_pred)
|
|
l_edges = K.mean(K.abs(dy_pred - dy_true) + K.abs(dx_pred - dx_true), axis=-1)
|
|
|
|
# Structural similarity (SSIM) index
|
|
l_ssim = K.clip((1 - tf.image.ssim(y_true, y_pred, maxDepthVal)) * 0.5, 0, 1)
|
|
|
|
# Weights
|
|
w1 = 1.0
|
|
w2 = 1.0
|
|
w3 = theta
|
|
|
|
return (w1 * l_ssim) + (w2 * K.mean(l_edges)) + (w3 * K.mean(l_depth))
|