V-Sense / DeepNormals

Code and Dataset from Deep Normal Estimation for Automatic Shading of Hand-Drawn Characters

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Training an Image

JuHyung-Son opened this issue · comments

When training, did you train every tile of an image among 420 images or just a random tile among 84000 tiles?

If I understand your question correctly: Random tile among 84000, we generated a tfrecord file containing all tiles (20 tiles per image), then used the shuffle batch during training.
Contact me by email if you need more info or the tfrecord file directly. (hudonm@scss.tcd.ie)