trikim
trikim
@nyanmn Hi, I have tried your solution, but it doesn't work. The error was changed from F1212 22:23:30.527931 21847 cudnn_relu_layer.cu:24] Check failed: status == CUDNN_STATUS_SUCCESS (3 vs. 0) CUDNN_STATUS_BAD_PARAM to...
By reference from http://blog.csdn.net/u012841667/article/details/53436615, I changed all the cudnn* files, with newest caffe project from https://github.com/BVLC/caffe. the cudnn* files are in /py-faster-rcnn/caffe-fast-rcnn/include/caffe/util/ , /py-faster-rcnn/caffe-fast-rcnn/include/caffe/layers/, /py-faster-rcnn/caffe-fast-rcnn/src/caffe/util/ and /py-faster-rcnn/caffe-fast-rcnn/src/caffe/layers/ my GPU is...
The goturn.caffemodel of OpenCV version can be found [here](https://github.com/opencv/opencv_extra/tree/c4219d5eb3105ed8e634278fad312a1a8d2c182d).
Is there someone know how to run GOTURN with gpu mode in opencv version? I succeed to run the multitracker.cpp demo in opencv_contrib-3.4.1. But the speed is only 6 FPS...
> 有試過 https://github.com/JunnYu/mish-cuda 嗎 GPU=2080s 在镜像pytorch:20.06-py3下使用[https://github.com/thomasbrandon/mish-cuda](https://github.com/thomasbrandon/mish-cuda)不能正常编译，[https://github.com/JunnYu/mish-cuda](https://github.com/JunnYu/mish-cuda)则可以。
@healthai I have also encountered the same problem. Have you solved the problem? I have tried the methods described above. But it doesn't work.
I think the problem is that your tensorflow version is too high. My cuda version is 8.0. My cudnn version is 6.0. At the first time, I used "pip install...
The same error, @kerolos , have you solved the problem?
借楼向知道的大佬请教个问题，训练的时候给模特图（gt）加噪，经过vton_unet预测噪声，MSE计算预测噪声与原噪声的loss，这个操作正确吗？因为在推理时vton_uent每次新的step，latents都是经过上次预测去噪后的latents、ori_img_latents和mask_latents这三个数据融合的，这块有点疑惑。
> I made an unofficial training code here. Still testing it. Please try if you like: https://github.com/nftblackmagic/IDM-VTON-training Thanks for sharing the training code of IDM-VTON. I have some questions. Around...