Repository navigation
How do you train DRN-D-22? #28
Description
I trained it with python3 segment.py train -d <data_folder> -c <category_number> -s 896 --arch drn_d_22 --batch-size 14 --epochs 250 --lr 0.001 --momentum 0.99 --step 100, and multi-scale test only get 66.49.
It seems that you have many GPUs, you may use a huge batch-size or big crop size, right?
Activity
acgtyrant commentedon May 10, 2018
OK, I forget to use
--bn-sync.acgtyrant commentedon May 10, 2018
I add
--bn-syncand it overflow in epoch 3, it comfirms that the implementation of synced bn is not correct.jakubLangr commentedon Dec 24, 2019
Hi @acgtyrant would you be able to upload the models to e.g. dropbox as they don't seem to be accessible on the Princeton site? That'd be awesome! : 👏 😎