search

ShapeNet / RenderForCNN

Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
Other
248 stars 82 forks source link

About "SOFTMAX_WITH_VIEW_LOSS" and "ACCURACY_VIEW" layer #3

Closed rockstone533 closed 8 years ago

rockstone533 commented 8 years ago

I try to train the network in the train folder with the "caffe-render-for-cnn", but I cannot find these two layers.

charlesq34 commented 8 years ago

you should switch branch by git checkout view_prediction and you will see those layers.