Fanteng Meng

icon company Railroad UAV Research Group icon location Beijing Jiaotong University, Beijing, China icon location @BJTU-Railroad-UAV-Research-Group

Results 2 comments of Fanteng Meng

Potential BUG

I think you are right! When I use log probability I get Nan loss, but when I use probability (p = F.softmax(logits)), my loss looks normal!

tensorrt inference?

> I handled it. You can reference at link: [GitHub] (https://github.com/ChuRuaNh0/FastSam_Awsome_TensorRT). If it helpful with you, give me a star, thanks. Great Work! I want to know the inference speed...