search

fyu / drn

Dilated Residual Networks
https://www.vis.xyz/pub/drn
BSD 3-Clause "New" or "Revised" License
1.1k stars 219 forks source link

How do you train DRN-D-22? #28

Open acgtyrant opened 6 years ago

acgtyrant commented 6 years ago

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?

acgtyrant commented 6 years ago

OK, I forget to use --bn-sync.

acgtyrant commented 6 years ago

I add --bn-sync and it overflow in epoch 3, it comfirms that the implementation of synced bn is not correct.

jakubLangr commented 4 years ago

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! : 👏 😎