Skip to content
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

Re Train #34

Open
LIUHAO121 opened this issue Jul 27, 2020 · 2 comments
Open

Re Train #34

LIUHAO121 opened this issue Jul 27, 2020 · 2 comments

Comments

@LIUHAO121
Copy link

i use coco2017 and your pretrained model dla34.pth to train again,the loss is still growing from 3.1 to round 17.why the loss does keep unchanged or change smaller,

@gsx1378
Copy link

gsx1378 commented Mar 16, 2022

你好,请问你这个问题解决了吗?我也遇到了相同的问题,训练了30多轮loss基本不变,过程中的评估结果Map也非常低。

@yzbx
Copy link

yzbx commented Mar 30, 2022

你好,请问你这个问题解决了吗?我也遇到了相同的问题,训练了30多轮loss基本不变,过程中的评估结果Map也非常低。

我通过修改KeypointHead网络初始化得到缓解,原代码没有初始化self.hm 与 self.hm_hp
models/heads/keypoints.py

    def init_weights(self):                              
        self.fill_fc_weights(self.wh)
        self.fill_fc_weights(self.hps)
        self.fill_fc_weights(self.reg)
        self.fill_fc_weights(self.hp_offset)
        self.fill_fc_weights(self.hm)
        self.fill_fc_weights(self.hm_hp)
        # https://github.com/princeton-vl/CornerNet/issues/13
        self.hm[-1].bias.data.fill_(-2.19)
        self.hm_hp[-1].bias.data.fill_(-2.19)

我只训练了100个epoch, 没有像配置文件中训练1000个epoch, 相应的LR_STEP由[800,900] 改为[80,90],最后得到如下结果
(COCO上的官方结果为54.5)

Backbone dataset AP $AP^{50}$ $AP^{75}$ note
Resnet50 COCO 0.460 0.759 0.475 -
Resnet50 CrowdPose 0.395 0.738 0.370 max_objs=32
Resnet50 CrowdPose 0.398 0.741 0.374 max_objs=64

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants