stiansel comments

Repositories
Issues
Comments

Results 3 comments of


                                            stiansel

In superGAN for contest, training loss LG = Lpercep + λLRa G + ηL1,What is the value of λ and η?

The values for ESRGAN appear to be in the training options file at https://github.com/xinntao/BasicSR/blob/master/codes/options/train/train_ESRGAN.yml (see near the bottom of the file)

parser error(?) in flickr crawler

If anyone else gets this error, it appears to be caused by the output queue of the FlickrFeeder being sized at 5*num_threads, which means you'll get at most 5 pages...

NCNN - Bounding box is slightly off for NanoDet-m but is correct for NanoDet-Plus-m

The non-plus model has a 0.5 offset in the output grid. This may not be accounted for in that inference script's output decoding. See this part of the code in...