juliusshufan edited a comment on issue #12591: USE_MKLDNN=1 is default in make 
build (mkldnn must be explicitly turned off)
URL: https://github.com/apache/incubator-mxnet/pull/12591#issuecomment-423890706
 
 
   Apart from ImageNet-1k traning test, training test also been executed on 
small dataset, that includes:
   
     | Training set | Validation set | Classes | Source
   -- | -- | -- | -- | --
   CiFAR-10 | 50,000 | 10,000 | 10 | Released by MxNET official   
http://data.mxnet.io/data/cifar10/
   CiFAR-100 | 50,000 | 10,000 | 100 | Released by MxNET official   
http://data.mxnet.io/data/cifar100.zip
   sampled ImageNet | 100,200 | 10,000 | 200 | Sampled from ImageNet-1k and 
converted following the structure   and classes retrieved from tinyImageNet   
(https://www.kaggle.com/c/tiny-imagenet/)
   
   Due to the lackness of the SOTA accuracy data on these small dataset,  the 
comparisons between MXNET-MKLDNN and MXNET-GPU on convergence trends and 
inference accuracy will be "indirectly" used as the correctness check of MXNET 
with MKLDNN backend.
   Below tables lists the validation accuracy on CIFAR10, CIFAR100 and the 
sampled-Imagenet and comparisons achieved on GPU, models including ResNet-50, 
VGG16 and Inception-v3.
   
   On Resnet-50:
   
     | HW Platform | Dataset | Validation Accuracy
   -- | -- | -- | --
   CPU | SKX-8180 | sampled ImageNet | top1=0.629879    top5=0.842132
   GPU | GTX-1080T | sampled ImageNet | top1=0.630609    top5=0.840345
   CPU | SKX-8180 | CiFAR-10 | top1=0.917067    top5=0.997796
   GPU | GTX-1080T | CiFAR-10 | top1=0.921474    top5=0.998397
   CPU | SKX-8180 | CiFAR-100 | top1=0.734475    top5=0.915865
   GPU | GTX-1080T | CiFAR-100 | top1= 0.723257   top5= 0.913161
   
   On Inception-v3, (as inception-v3 only accepts input size 229, CIFAR is not 
applicable)
   
     | HW Platform | Dataset | Validation Accuracy
   -- | -- | -- | --
   CPU | SKX-8180 | sampled ImageNet | top1= 0.684964   top5=0.866470
   GPU | GTX-1080T | sampled ImageNet | top1= 0.684095   top5= 0.868890
   
   On VGG-16:
   
     | HW Platform | Dataset | Validation Accuracy
   -- | -- | -- | --
   CPU | SKX-8180 | sampled ImageNet | top1=0.528029    top5=0.759809
   GPU | GTX-1080T | sampled ImageNet | top1=0.526834    top5= 0.761318
   CPU | SKX-8180 | CiFAR-10 | top1=0.884615    top5=0.994391
   GPU | GTX-1080T | CiFAR-10 | top1=0.888622    top5=0.995092
   CPU | SKX-8180 | CiFAR-100 | top1=0.634415    top5=0.855569
   GPU | GTX-1080T | CiFAR-100 | top1= 0.634916   top5= 0.855669
   
   The below two figures are the top-5 validation accuracy trends collected on 
CPU and GPU respectively,
   On CPU:
   
![image](https://user-images.githubusercontent.com/33112206/45941205-a203ca80-c00f-11e8-87f5-752b776ad037.png)
   On GPU:
   
![image](https://user-images.githubusercontent.com/33112206/45941220-b5169a80-c00f-11e8-9753-2294c68f78b7.png)
   
    
   

----------------------------------------------------------------
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:
[email protected]


With regards,
Apache Git Services

Reply via email to