search

GeorgeSeif / Semantic-Segmentation-Suite

Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!
2.51k stars 880 forks source link

What is the output modified using one-hot code if I want to train model by 3D images? Such as video frames #223

Open che006 opened 5 years ago

che006 commented 5 years ago

I stacked three frames as a training sample. The semantic labels of every frames were included in my dataset. But I dont know how to modify the output layer with one-hot code. The 2D labels is different from 3D.