Giters

scaelles / OSVOS-TensorFlow

One-Shot Video Object Segmentation

Home Page:http://vision.ee.ethz.ch/~cvlsegmentation/osvos/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why should make the deconvolutional part untrainable

Beanocean opened this issue · comments

commented

OSVOS-TensorFlow/osvos.py

Line 97 in f1eef49

outputs_collections=end_points_collection, trainable=False):

The code above shows the deconvolution layers are set to be untrainable, would you please help to explain this?

commented

We tried training the deconvolutional layers using the bilinear interpolation weights as initialization or directly training from scratch. The best result was obtained using the biliniear interpolation weights, but the performance was almost the same if we trained those layers or not, so we decided not train them.