Possible reasons for different performance between DIM Re-implementation and original implementation

poppinace / indexnet_matting

(ICCV'19) Indices Matter: Learning to Index for Deep Image Matting

Other

389 stars 90 forks source link

Possible reasons for different performance between DIM Re-implementation and original implementation #29

Open VitoChien opened 3 years ago

VitoChien commented 3 years ago

Thanks for your great work! When I'm trying to reproduce the result of DIM(Deep Image Matting), I found that using vgg model without BN and setting batch-size to 1 will give the same or even better performance, comparing to the results reported by the original DIM paper.

So I think that fewer training data is not supposed to be the reason for different performance.

poppinace commented 3 years ago

Solved. See this response