leohsuofnthu / Tensorflow-YOLACT

Implementation of the paper "YOLACT Real-time Instance Segmentation" in Tensorflow 2
111 stars 36 forks source link

Missing conv layer in prediction layers/head.py #14

Open GPhilo opened 4 years ago

GPhilo commented 4 years ago

Hello,

I'm looking at your implementation and I noticed that the prediction heads only have one Conv layer before splitting in the three actual heads, while in the paper, in figure 4, they seem to have two Conv layers there. Is this on purpose or is it missing a layer?