alicera

Thanks for your document. I have some question. I input two number. It will search the num1.csv to response to result value. And add it. `case1`: Input: 1 , 2...

INT8

5

Do you try the INT8 for yolov5? I try to do onnx ->trt I cant detect any object for yolov5 INT8. But the yolov5 FP16 can detect the object. Do...

docker

1

command : docker build -t tensorrt_inference:0.1.0_rc . Error: Unpacking libsasl2-2:amd64 (2.1.27~101-g0780600+dfsg-3ubuntu2.3) over (2.1.27~101-g0780600+dfsg-3ubuntu2.1) ... Preparing to unpack .../linux-libc-dev_4.15.0-135.139_amd64.deb ... Unpacking linux-libc-dev:amd64 (4.15.0-135.139) over (4.15.0-130.134) ... Setting up libsasl2-modules-db:amd64 (2.1.27~101-g0780600+dfsg-3ubuntu2.3) ......

Does the mmpose support botton-up?

map

6

If running the main.py, the mAP IOU is 0.5 or 0.5:0.75 ?

bottom up

5

Is the bottom - up network similar to openpose ? Because I get the onnx model output is [1,34,128,128] for (512,512,3) image. Is the 34 compose of 17 keypoints and...

Meaning of the last two elements of `preds` in bottom up result

5

I try to print the array {'preds': [array([[9.70417969e+02, 4.94542969e+02, 1.00000000e+00, 1.00000000e+00, 1.00000000e+00] I only know the first x,y, keypoint_score . The other doesnt know. https://user-images.githubusercontent.com/59388989/117801610-1b1ac380-b287-11eb-990c-e37de7c3f39d.png

我使用 train-version-slim.sh 去訓練並將得到的*.pth轉成*.MNN。 再python 上測試*.MNN 沒有報錯，但用C++ 就出現 error """ Resize error for ConvertTensor36, code=3 Processing ../imgs/1.jpg inference time:0.00404521 s Segmentation fault (core dumped) """ 无法解决 https://github.com/alibaba/MNN/issues/295

the project have face landmark?

"a"->{ "b" "c" } "b"->{linux windows macos} "c"->{linux1 windows1 macos1}  I want to let the linux1 be linux, but it will be the common. How to set the two...