Scaled-YOLOv4-TensorRT icon indicating copy to clipboard operation
Scaled-YOLOv4-TensorRT copied to clipboard

Got 100fps on TX2. Got 500fps on GeForce GTX 1660 Ti. If the project is useful to you, please Star it.

Results 22 Scaled-YOLOv4-TensorRT issues
Sort by recently updated
recently updated
newest added

when I run gen_wts code I get ```NameError: name 'Darknet' is not defined``` .

In the README.md, it is mentioned that the inference speed on TX2 is around 10-11ms. Is this speed measured around the function doInference here: https://github.com/tjuskyzhang/yolov4-tiny-tensorrt/blob/bc49483e49e4de698fd88b878799b8b0a979e88f/yolov4-tiny.cpp#L496. Or around context.enqueue line here:...

Dear sir, Thanks for good work! just a question: "yolov4-tiny.pt" can use torch.load("yolov4-tiny.pt") directly? what is the input_shape? Thanks!

I tried it, and if the width and height don't match, I get an error. ![image](https://user-images.githubusercontent.com/28076332/102332123-a8066d00-3fc6-11eb-8d58-81457b403e9d.png)

Hi, Firstly, thanks for this great piece of work! I would like to train YOLOv4-Tiny on my custom dataset and the use-case is to run the model on Jetson TX2....

Is there any different between yolov4 ,can i use it for yolov4 directly?or i should change some code in there

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

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

用darknet框架训练的模型能支持吗?

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 torch.Size([32, 32, 3,...