-
Notifications
You must be signed in to change notification settings - Fork 2.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
yolov8_x训练速度太慢 #8832
Comments
PaddlePaddle/PaddleYOLO#43 训自定义数据集可参照这个教程的3. Fintune 微调训练。训练命令后加上: 训练速度方面,可以注释mosaic即不使用它,可以加速很多, |
请问下,加入微调是否会导致训练速度变慢?我们尝试了v3,v5和v8,都有发现这个 情况。训练一个epoch的时间明显增加 |
1 similar comment
请问下,加入微调是否会导致训练速度变慢?我们尝试了v3,v5和v8,都有发现这个 情况。训练一个epoch的时间明显增加 |
加入微调只是提前加载了一个coco训完的权重的参数做初始化,是为了更快收敛,并不会导致训练变慢,建议再检查一下。加速建议如上就是不使用mosaic,微调加mosaic可能不一定有涨点的,视数据集而定。 |
问题确认 Search before asking
请提出你的问题 Please ask your question
训练图片840张(1330×720),训练一轮超过一个小时,
版本号/Version:Paddle: paddlepaddle-gpu==2.6.0
Gpu compute capability:8.6 , priver ApI version:12.2 ,Runtime API Version:12.0
PaddleDetection: release/2.7
运行指令/Command Code:
python tools/train.py -c configs/yolov8/yolov8_x_500e_coco.yml --use_vdl=true --vdl_log_dir=vdl_dir/scalar
数据集类型:coco数据集
配置文件:
硬件配置
GPU:RTX 3080 GPU显存10GB
CPU:10 核 Xeon Gold 6142
内存:64GB
硬盘:952GB
请大佬指点,谢谢
The text was updated successfully, but these errors were encountered: