[GitHub] wsokolow commented on issue #11040: Big acc difference when fine-tune using vgg16 and resnet-50
wsokolow commented on issue #11040: Big acc difference when fine-tune using vgg16 and resnet-50 URL: https://github.com/apache/incubator-mxnet/issues/11040#issuecomment-392440814 I've also reproduced my problem while running with GPU. Thus "MKL" label should be removed. This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] wsokolow commented on issue #11040: Big acc difference when fine-tune using vgg16 and resnet-50
wsokolow commented on issue #11040: Big acc difference when fine-tune using vgg16 and resnet-50 URL: https://github.com/apache/incubator-mxnet/issues/11040#issuecomment-392440814 I've also reproduced my problem while running with GPU. This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] wsokolow commented on issue #11040: Big acc difference when fine-tune using vgg16 and resnet-50
wsokolow commented on issue #11040: Big acc difference when fine-tune using vgg16 and resnet-50 URL: https://github.com/apache/incubator-mxnet/issues/11040#issuecomment-392440814 I've also reproduced my problem with GPU. This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] wsokolow commented on issue #11040: Big acc difference when fine-tune using vgg16 and resnet-50
wsokolow commented on issue #11040: Big acc difference when fine-tune using vgg16 and resnet-50 URL: https://github.com/apache/incubator-mxnet/issues/11040#issuecomment-392050897 Which engine did you use for execution? GPU or CPU (with MKLDNN)? I'm observing issues with ~10% accuracy while running AlexNet with MKLDNN engine. This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
