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.
5924 Discussions

Model trained using darkflow( tiny_yolo_voc ), when converted to graph, no objects are detected.

Community Manager

I trained a model with tiny-yolo-voc.weights to detect number plates. The training was done using Darkflow. The detection work's fine with .pb and .meta files, for which i used return_predict function( . Then I compiled, the .pb file to generate the graph file(My ncsdk is installed in an aws ec2 instance). After obtaining Inference using the graph.queue_inference_with_fifo_elem( ) method , I referred this work (, ) for generating bbox from graph's output. Which is in fact an adaptation of return_predict method in darkflow. But no boxes were detected. Can anyone point out why this is happening?

0 Kudos
1 Reply
Community Manager



There was some steps missing in my image pre-processing. After correction the detection is as expected.