Open saikrishnadas opened 3 years ago
Could you provide your cfg, command, and gpu for training on pytorch and darknet? And why you guess scaled yolov4 is claimed to be 6 times faster than darknet-yolov4?
yolo-csp cfg : yolov4-csp.zip
command :
python train.py --img 512 --batch16 --epochs 5000 --data '../data.yaml' --cfg ./models/yolov4-csp.yaml --weights'' --name yolov4-csp-results --cache
GPU for training: Nvidia Tesla T4
And why you guess scaled yolov4 is claimed to be 6 times faster than darknet-yolov4? https://blog.roboflow.com/scaled-yolov4-tops-efficientdet/ speeding up training time 10x relative to Darknet
@WongKinYiu
@WongKinYiu Any solution?
check the memory usage, try to increase batch size if it could.
the reason why they said 10x is due to at the time:
2x2x2.25 = 9 9 + new cudnn speed up, ~10
But When I try increasing the batch size or switching to multi-GPU. My GPUs run out of memory.
@WongKinYiu ??
@WongKinYiu
If your gpu do not has tensor core, darknet is faster.
I used yolo-CSP with 512 input and 16 batch size and found that is slower than darknet-yolov4 with the same 512 and 16 batches. I guess scaled yolov4 is claimed to be 6 times faster than darknet-yolov4. Why? @WongKinYiu