search

mystic123 / tensorflow-yolo-v3

Implementation of YOLO v3 object detector in Tensorflow (TF-Slim)
https://medium.com/@pawekapica_31302/implementing-yolo-v3-in-tensorflow-tf-slim-c3c55ff59dbe
Apache License 2.0
893 stars 353 forks source link

get this error #29

Open borre47 opened 5 years ago

borre47 commented 5 years ago

python ./demo.py --input_img autos.jpg --output_img autos2.jpg --weightsfile yolov3.weights Dimension size,given by scalr input 2, must be non negative but is -1 for 'detector/yolo-v3/split' <op 'SplitV'> with input shapes: [?,507,85],[4],[].

mystic123 commented 5 years ago

Did you change "size" flag?

borre47 commented 5 years ago

Did you change "size" flag?

No, i did not change anything

mystic123 commented 5 years ago

Could you please share the images, and write more details about your setup (OS, python version, tensorflow version, running on CPU/GPU)?