about pretrain model
ygjwd12345 opened this issue · comments
Hi,
I want to reproduce your work.
but I get an error as follow
FileNotFoundError: [Errno 2] No such file or directory: 'pretrained/resnet101_iabn_sync.pth.tar'
can you tell me how to get it?
I find it
thanks
@ygjwd12345 Could you tell me how you resolved this issue?
I'm facing similar issue
Hi @deepakksingh.
I've seen only now your comment.
That's the link: https://github.com/mapillary/inplace_abn#training-on-imagenet-1k (click on md5 to get the download page).
If you open the link, there's a table. The last row is the pretrained model you need, but in case you want to try different architecture, you can just download the pretrained and specify the correct backbone.
@fcdl94 Thank you for your reply.
I did the same. I downloaded it from the Google drive and renamed it accordingly.
@fcdl94 Thank you for your reply.
I did the same. I downloaded it from the Google drive and renamed it accordingly.
Hi~ I download corresponding pth.tar file for this project from inpace_abn repository. But the parameters' name doesn't match. Do you encounter this problem?
thanks~
Hi!
Which parameters does not match? That's strange since I took their resent and deeplab implementation (have you specified the norm_act parameter maybe?)
I faced the issue where "module" word was not matching. That happens when the model was trained and saved as per multi-gpu setting. So you may have to rename some parameter names to remove the "module" word
Follow up : The renaming issue is mentioned here : #14 (comment)
I faced the issue where "module" word was not matching. That happens when the model was trained and saved as per multi-gpu setting. So you may have to rename some parameter names to remove the "module" word
yes, it is the reason why not matched. ~ I didn't read README carefully. Thank you~
Hi!
Which parameters does not match? That's strange since I took their resent and deeplab implementation (have you specified the norm_act parameter maybe?)
Thanks for your reply. It is the reason of "module." in pretrained model's state_dict's keys~