Why weights event.out.tfevents are getting generated in each run in Tracking-with-darkflow\darkflow\summary\train2

obendidi / Tracking-with-darkflow

Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow

GNU General Public License v3.0

524 stars 174 forks source link

Why weights event.out.tfevents are getting generated in each run in Tracking-with-darkflow\darkflow\summary\train2 #31

Closed Jumabek closed 6 years ago

Jumabek commented 6 years ago

So I have YOLO detector weights in outside directory which is like FLAGS.load = "E:\\darknet\\backup\\head/head_10000.weights"

When I execute the tracker by python run.py i am getting new file of size 263MB in E:\code\tensorflow\Tracking-with-darkflow\darkflow\summary\train2

So quickly it occupies a lot of disk memory: untitled

Please feel free to give any suggestions. Thx, Jumabek

obendidi commented 6 years ago

thanks for the info , I just noticed that I had tf events saved too , I'm planning a major cleaning of all the unused code in this repo in the next days and this should be removed by then

Jumabek commented 6 years ago

Okay, looking forward to it!