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
Do you have a trained model (checkpoint) for this? #62
Comments
Do you mean search or retrain? |
yes, I am so appriciate if you can support |
But Now the search result is not very good. if you want, maybe I can offer a baiduyun drive |
Never mind, thanks :-) |
I am so interesting about this paper and your work implement to Pytorch. |
miou is lower than paper reports |
Oh,too strange, |
No, now we dont solve this issue. |
what a pity! |
in search V100 *1 |
Hey, boy, we have know get a better result for search, it has 0.34miou baiduyun drive:https://pan.baidu.com/s/1ASRyzK_0m9CvhfN3yHZZ5Q |
thanks :-) |
hi ! thanks for doing such amazing work ! |
I trained for about 1M iters on autodeeplab-M I remembered, not used SDP, and got 79.8miou without MS |
total train time is about 20 days |
thanks for your quick reply! |
|
thank you very much!
…------------------ 原始邮件 ------------------
发件人: "zhizhangxian"<notifications@github.com>;
发送时间: 2020年1月11日(星期六) 晚上11:48
收件人: "NoamRosenberg/AutoML"<AutoML@noreply.github.com>;
抄送: "0.0"<1639998780@qq.com>;"Comment"<comment@noreply.github.com>;
主题: Re: [NoamRosenberg/AutoML] Do you have a trained model (checkpoint) for this? (#62)
yes, not under ms I remember, I adapt the retrain code from chenxi's deeplab v3 reproduce, he didnot use MS
if you mean retrain, you should use CUDA_VISIBLE_DEVICES=0,1,2,···,n python -m torch.distributed.launch --nproc_per_node=n train_distributed.py to use distributed training
It is just because too much iterations(more than 1M in paper) and only 30K in deeplab v3plus, you can not get a good result if train only several thousands iters without imageNet pretrain, the retrain configurations are same as deeplab v3/v3+
I retrained it with another code(adapted from chenxi's code), I should have fixed the bugs in our project, but these days I am busy in some other things, but maybe I can pay some attention on it after March...
Thanks, good luck!
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
hi ! this is an amazing work !
I just wanna use this project to do some researches but my PC too slow.
Can you support a trained model for this ?
thanks.
The text was updated successfully, but these errors were encountered: