-
Notifications
You must be signed in to change notification settings - Fork 6
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
为啥 #8
Comments
抱歉,不清楚这个的原因。 |
我用全部的train和val数据训练,然后在test上测试,得到的moderate Car的精度为14.01,比官方论文中报道的12.26高不少,真奇怪,官方的repository里面报道的是13.6、13.7左右,我觉得这才是应该是正常的精度,看了下您跑的原始monodle精度是13.7197,和官方的epository里面报道的差不多。但是我试了下用您的monodleX(加入了对截断obj的处理),主干网络我用的是DLA34,精度居然掉到了13.28,不能理解,照理说对截断物体的处理不会影响模型对正常物体的检测呀😭 |
你直接clone下来跑通就是单卡运行的,不需要做什么改动 |
@shanqiu24 可以尝试把截断率调整下,降低截断目标的样本数看下指标是否有提升。再把结果和这个效果差的可视化观察下。 |
为什么的运行官方的monodle:
(monodle) G:\WWProject\monodle\experiments\example>python ../../tools/train_val.py --config kitti_example.yaml
2022-10-11 10:46:15,326 INFO ################### Training ##################
2022-10-11 10:46:15,326 INFO Batch Size: 16
2022-10-11 10:46:15,326 INFO Learning Rate: 0.001250
然后居然需要过半个小时才出现的训练的epoch进度条,我将原monodle改为单卡运行了,我的是单卡3090
epochs: 0%| | 0/140 [00:00<?, ?it/s]
iters: 0%| | 0/232 [00:00<?, ?it/s]
The text was updated successfully, but these errors were encountered: