123

合肥

Results 17 comments of

[E] [TRT] Network must have at least one output

./mmpose_trt ../../../configs/mmpose/config.yaml ../../../samples/pedestrian ---------------------------------------------------------------- Input filename: ../hrnet_w48_coco_256x192.onnx ONNX IR version: 0.0.6 Opset version: 11 Producer name: pytorch Producer version: 1.7 Domain: Model version: 0 Doc string: ---------------------------------------------------------------- While parsing node...

请问现在paddle2onnx支持fastscnn了吗？转出的时候报如下错误

@chen0928622 大佬，我也遇到这个问题了，怎么手动修改AdaptivePool呢，感谢！

为什么训练10类得到的precession很低呢

> > > 哦哦，原来是这样，嗯嗯懂了我去试一下 > > 你用0.4 0.5试试改了之后，P提高了么

Cpp Implementation

https://github.com/pcb9382/FaceAlgorithm

TensorRT Implementation

https://github.com/pcb9382/FaceAlgorithm

请问有yolov7face openvino c++推理代码吗

根据我的之前写openvino的经验，不难的，自己把onnx转下，写个demo应该很简单的

您好！请问yolov8-face-n的yamal是怎么样配置的？

你可以去看看yolov8faced的github:https://github.com/derronqi/yolov8-face

人脸角度计算关键点数量的问题

我觉的得关键点位置准，计算的角度才是比较正确的当然关键点数量多的话可以计算出多个角度，对角度进行过滤，排除一些错误的角度

百度网盘链接失效

加群单独发吧，链接老是这样，也是无语

Onnx2Trt Conversion Problem

Please use TRT8, trt7 may need to be changed by yourself due to some operator unsupport and interface problems

1
2
›