-
Notifications
You must be signed in to change notification settings - Fork 61
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
Train Parameters #43
Comments
我想问一下这样的结果正常么,精度上的差距主要是因为缺失第三步骤么?还有这里的border可以带来多少的精度提升呢 :)
|
请问,您是否有修改过作者的代码,主要指的是数据增强那块,为什么我按着作者代码的训练调参方式,训练出来的结果精度只有70呢 |
去年的实验,我不太记得了。建议把训练的bbox值打出来看一下,此外可以看一下这个函数。 |
设置max_obj=314, k=600能有提升 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
你好,我想请问一下具体是在多少个epoch后做finetune的呢,finetune的学习率和步长具体是多少呢?
我在640 * 640的输入上做训练,使用lr_step为90、120,lr为5e-4,batch_size为8。之后将140的epoch取出,送入第二步做finetune,输入尺寸为800 * 800,使用lr_step为30、60,lr为5e-4,batch_size为8。
训练结果为
![image](https://user-images.githubusercontent.com/32426369/97564758-06c85500-1a20-11eb-8546-89d1535284ad.png)
1.First train with the size of 640×640/514×514
2.Then fine tune with the size of 800×800
3.For the easy and hard part, s = s * np.random. Choice (np.arange(0.3, 1.2, 0.1)). The larger the value, the more small samples will be generated
The text was updated successfully, but these errors were encountered: