You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2019/03/21 06:26:22 UTC

[GitHub] [incubator-mxnet] Ian8888 opened a new issue #14486: Predict of mx.mod.Module api problem 2

Ian8888 opened a new issue #14486: Predict of mx.mod.Module api problem 2
URL: https://github.com/apache/incubator-mxnet/issues/14486
 
 
   Note: Providing complete information in the most concise form is the best way to get help. This issue template serves as the checklist for essential information to most of the technical issues and bug reports. For non-technical issues and feature requests, feel free to present the information in what you believe is the best form.
   
   For Q & A and discussion, please start a discussion thread at https://discuss.mxnet.io 
   
   ## Description
   
   I have the question about the predict result.
   When I make the inference program, I must be know the model accuracy result about image classification.
   In my job, I have the two classification(0 or 1 labels).
   
   So, I use the im2rec tool to make the .rec and .lst file.
   
   > 39	1.000000	1/CenterOrg1_000_2_B_b04dfe80-d9f5-4928-9ac0-550fc5d7688a_ScanImgORG.jpg
   > 24	1.000000	1/CenterOrg1_000_2_A_16e83b7c-9daf-4393-9a62-41a2a65125ce_ScanImgORG.jpg
   > 28	1.000000	1/CenterOrg1_000_2_A_88d71f72-9858-41f3-bd70-8b12a40f009d_ScanImgORG.jpg
   > 30	1.000000	1/CenterOrg1_000_2_A_ec1ed52c-c8ea-4cae-967c-25de87720416_ScanImgORG.jpg
   > 21	1.000000	1/CenterOrg1_000_1_B_020e5e40-2611-4548-ae57-78da77ddcbca_ScanImgORG.jpg
   > 10	0.000000	0/CenterOrg0_0_155_B_ebea1c1c-560f-4512-8ce2-58c9c8fbd7fa_ScanImgORG.jpg
   > 34	1.000000	1/CenterOrg1_000_2_B_6cb8cdd4-4345-488b-a195-1c1b3692acb0_ScanImgORG.jpg 
   
   and, use mx.image.ImageIter api to catch the data.
   Then, I compare the data.label and predict result label to calculate acc.
   And I run the same code in every times, but the acc is not same.
   
   > Infernce Accuracy: 0.45
   > Infernce Accuracy: 0.5
   > Infernce Accuracy: 0.475
   
   So, I gusset the predict api catch the image data that wasn't the same order with the ImageIter.
   
   How can I solve the problem to calculate the Infernce Accuracy?
   
   
   

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services