CUDA_ERROR_OUT_OF_MEMORY on Tesla V100 while training

hunglc007 / tensorflow-yolov4-tflite

YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite

https://github.com/hunglc007/tensorflow-yolov4-tflite

MIT License

2.23k stars 1.24k forks source link

CUDA_ERROR_OUT_OF_MEMORY on Tesla V100 while training #333

Open AditTuf opened 3 years ago

AditTuf commented 3 years ago

Hi ,I was trying to check training of YOLOV4 on Tesla V100 16 Gb with batch size set to 2 .But consistently falling into out of memory error .I also tried batch size 1 which didn't work either . Can you suggest some fix