epiphqny/yolact_fcos

YOLACT: Real-time Instance Segmentation on the FCOS detector (without bbox cropping), achives 35.2mAP on coco val

• 👋 Hi, I’m Yuqing Wang, a PhD student in the University of Hong Kong.
• 👀 I’m interested in computer vision and generative models.
• 📫 How to reach me : [email protected].

yolact_fcos's Issues

about proto_tower

proto_tower is stacked by 32 convolutions according to your code (fcos/modeling/fcos/fcos.py Line 166). Did you try less number convolutions? I have also recently combined yolact and fcos, but my accuracy is only 10

Predicting bbox

Input image size

@Epiphqny what is the default input size which your using for the model ? what is the shape of the FPN final layer in ur implementation

Inference speed

@Epiphqny thanks for opensourcing your work just had few queries

1. This repo is for yolact/ yolact++
2. what is the inference time obtained from your end

FCOS branch

@Epiphqny hi thanks for the source code , i am trying to understand how you have integrated the FCOS into the yolact can you provide pointers on where the changes have been made since u build detectron i am not able to figure out . I am more interested in lincomb_mask_loss function which takes anchors into the consideration. Thanks in advance