tjuskyzhang

Results 22 comments of tjuskyzhang

You can try this branch: git clone -b u3_preview https://github.com/WongKinYiu/PyTorch_YOLOv4.git

> when I modify code in yololayer.h i met such error > > ``` > static constexpr int INPUT_H = 1024; > static constexpr int INPUT_W = 1024; > ```...

> Hi, > > when following your tutorial I run into the following problem: > > name 'Darknet' is not defined > > Did I miss something ? > >...

> Is there a way to make this loop more faster? > > for (int i = 0; i < INPUT_H * INPUT_W; i++) { > data[b * 3 *...

for yolov4: https://github.com/wang-xinyu/tensorrtx/tree/master/yolov4

> Is there any different between yolov4 ,can i use it for yolov4 directly?or i should change some code in there Project for yolov4 : https://github.com/wang-xinyu/tensorrtx/tree/master/yolov4 By the way, yolov4-tiny-tensorrt...

> I tried to use yolov3-tiny.pt weight downloaded from the provided [link](https://github.com/WongKinYiu/PyTorch_YOLOv4) but unfortunately, I got the following error: > > `size mismatch for module_list.4.Conv2d.weight: copying a param with shape...

try https://github.com/WongKinYiu/PyTorch_YOLOv4/tree/u3_preview with [yolov4-tiny.pt](https://drive.google.com/file/d/1aQKcCvTAl1uOWzzHVE9Z8Ixgikc3AuYQ/view?usp=sharing)

Your GCC version may higher than the maximum supported GCC version for your CUDA version