Running out of memory error when running demo

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

Running out of memory error when running demo #67

Open monwen opened 5 years ago

monwen commented 5 years ago

Anyway to reduce the memory usage when running the demo? the error shows it requires 5.93 GB to run the demo with gpu version of tensorflow. My system only has 5.5 GB. Is this requirement normal? or I did something wrong there?

If anyone could help, please. Thanks

NickShargan commented 5 years ago

Quick fix is to reduce default value of gpu_memory_fraction in line 42 (demo.py). Set something like 0.8 and it should work.

computervisionlearner commented 5 years ago

Quick fix is to reduce default value of gpu_memory_fraction in line 42 (demo.py). Set something like 0.8 and it should work.

Thank you !!