-
已经成功转换了 engine 文件，在执行 yolov5_trt.py 时为啥还要依赖 torch 和 torchvision，仅利用 tensorrt 不能实现推理吗
-
Hi. I am trying to finetune a ShuffleNetv2 SSD model, ShuffleNetv2 pre-trained on ImageNet dataset, on COCO2017 dataset, no frozen layers. But I am getting pretty poor performance of the model. I get …
-
您好，感谢您带来这么好的工作。我在您的代码上进行yolov5s的训练，并将其结果与yolov5s u版 5.0版本进行对比。
**u版5.0的yolov5s的mAP@0.5为56.4**（u版5.0github中报告为55.4，此处56.4是我自己重新训练得到），**mAP@0.5:0.95为36.7**（与u版5.0github中报告一致）
在hpy.scratch.yaml相同的超参数设置…
-
For Part I of this week's lab, you have to practice using markdown with github issues. This will ensure that you know all of the syntax that you'll have to implement in your homework assignment. You…
-
Before #2537
SD
HD
 to onnx , meet the error below:
```
Traceback (most recent call last):
File "export2onnx.py", line 30, in
opset_version=args.opset, e…
-
- If no tournament start date is defined, default to today's date
- Don't allow tournaments to start/end in the past.
-
## Instructions To Reproduce the Issue:
1. Full runnable code or full changes you made:
No changes; simply install detectron2 and execute example scripts.
a. Install detectron2 on both machin…
-
And I found another thing that 'Hong Kong' and 'Macao' are as same as China's map data, the tool downloaded 3 exactly same size file with diff filenames.
from: #10
-
I've implemented the idea suggested in #732 to play table tennis in virtual reality and use imitation learning to create an AI that also can play table tennis.
This works by using the transform…