Results
13
comments of
Larry
可以看LoRA的参数，这个repo对只对"q_proj", "v_proj"这两个类型的layer进行了finetune所以会小。增加的可训练的layer越多最后生成的模型就越大。
> > > The inference only has output for the 1st batch. why is it like that? Is there a way to do dynamic batching for a list of images...
I have the same problem，RT-DETR-R18 FP16 have correct result on V100 and weird result on A10 （TensorRT 8.6.1）.