Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.

Post training quantization Custom Network

V_Marco
Beginner
172 Views

Hi,

Please could you give me some indication on which file i have to modify to generate a custom accuracy checking for post training quantization?  it's not a topology supported by accuracy checker ( is an auto-encoder  monodepth estimation) , i have custom dataset  and for groundtruth i have image disparity(.npy) for depth estimation (that are contained in a folder) for accuracy checking i don't need labels.  Without documentation is very difficult to extend the classes (representation,annotation converter, metrics, adapter ...) so a workflow or a documentation will be awesome

0 Kudos
1 Reply
Max_L_Intel
Moderator
172 Views

Hi Marco.

Please check my replies for this question here - https://software.intel.com/en-us/forums/intel-distribution-of-openvino-toolkit/topic/836994

Thanks.
Best regards, Max.

Reply