mayuri0192 / object-tracking-using-cnn-and-rnn Goto Github PK

I use 2 GPU with 12G memory and it is not enough memory.

i try to run the ObjectTracking-training.py file but at line 178, it seems that i need a function which should
defined in ObjectTracking_utils.py, but i can't find it,how to fix it?

This is a great repository and it's been very helpful! The videos I'm trying to track in work much better if the object is manually selected and we have some decent tracks using openCV; would it be possible to replace the yolo_out file with a variation of location outputs from the openCV tracker? Do you have any recommendations for how to convert the locations into data the program can manipulate?

Thanks!

where is /home/mdeshpa3/Tracker/model_step6_exp1.ckpt