search

msracver / FCIS

Fully Convolutional Instance-aware Semantic Segmentation
MIT License
1.57k stars 414 forks source link

This convolution is not supported by cudnn, MXNET convolution is applied #26

Open robotzheng opened 7 years ago

robotzheng commented 7 years ago

when I run the trainning of coco data, it reports "This convolution is not supported by cudnn, MXNET convolution is applied." but, when I run the demo, it does not reports this. it is very slow. Can you help me?

javierjsa commented 7 years ago

Hi,

I have the same problem with demo.py (haven't tried training yet). Which cuda/cudnn versions are you using? I have cudnn 5.1.10 and cuda 8.0.61.

Regards

lc8631058 commented 7 years ago

@javierjsa @robotzheng have you solved this problem??

javierjsa commented 7 years ago

@lc8631058 I'm afraid I haven't, but I think it's just a matter of using the right cudnn/cuda versions

realwecan commented 7 years ago

I can confirm that I had this issue before, and it could be resolved by installing the appropriate version of cudnn.

lc8631058 commented 7 years ago

@javierjsa so it's just something like Warning and has no influence to the result?

javierjsa commented 7 years ago

@lc8631058 The result might be the same, but I'd say it's probably slower. If I understand the error/warning message, it means it's using the CPU to perform the convolution instead of the GPU. However, I'm just a newbie.

lc8631058 commented 7 years ago

@javierjsa thanks a lot

dajiangxiaoyan commented 7 years ago

I have met this problem. Anyone fix it ?

betterhalfwzm commented 6 years ago

I have met this problem. Anyone fix it ? @javierjsa @robotzheng @javierjsa @dajiangxiaoyan @realwecan

javierjsa commented 6 years ago

@betterhalfwzm Sorry, I didn't. However, if you are into semantic segmentation, you should take a look at Mask R-CNN (https://github.com/matterport/Mask_RCNN). They claim to outperform both FCIS and MNC.

DuinoDu commented 6 years ago

I met this problem when using mxnet and I fix it by switch cuda and cudnn version from cuda-9.1 to cuda-9.0. BTW, I install mxnet from src.

light201212 commented 6 years ago

because dilation convolution is not support in cudnn5,using cuda8+cudnn7,install mxnet from src will be ok