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

[ ERROR ] Dims and format are inconsistent. when running YOLO model with FPGA

Yatish_M_Intel
Employee
354 Views

Hello

I converted YOLO model from caffe to IR. This works fine with CPU only device, but when i use FPGA, i get "[ ERROR ] Dims and format are inconsistent." error. I am using 0-8-1_a10dk_fp16_8x24_arch13.aocx as the binary for FPGA. What else do i need to do ?

I downloaded YOLO caffe model from https://github.com/cinastanbean/caffe-yolo-1

Thanks

Yatish

0 Kudos
1 Reply
Cary_P_Intel1
Employee
354 Views

Hi, Yatish,

The YOLO model is only supported by CPU/GPU, for FPGA it won't recognize the layer of YOLO region, so that's why it has error. Please refer to the online documents.

https://software.intel.com/en-us/articles/OpenVINO-InferEngine. Navigate to

1. "Running the samples/Object Detection YOLO* V3 Demo, Async API Performance Showcase"

2. "Advanced Topics/Supported Devices"

 

Reply