Closed jianwu585218 closed 4 years ago
It is also float32 in caffe.
Thanks Why the second line improved a lot, it is also float32 which as same as caffe? Due to the framework ,or other way(such as Layer & Tensor Fusion)?
It benefits to TensorRT. See here https://developer.nvidia.com/tensorrt
Thanks for your repley~ Have you test the yolo3-416 's inference time under float16(by TensorRT)?
My graphics cards did not support fast fp16, just take a try on your card.
Thanks for your work~ I have a question,that is :
Is the data type of the yolo3 model under the darknet or caffe framework is double precision(FP64)?