DDRNet icon indicating copy to clipboard operation
DDRNet copied to clipboard

Saved model without pretraining

Open hojunson opened this issue 2 years ago • 2 comments

Hello Yuanduo,

I think your achievement is really awesome. I am looking into your code and your model to develop more on it.

I was wondering whether the "best.pth" model is the trained model without Imagenet pre-training.

I remember I got the file from the google drive and it shows about 75.xx in validation set of Cityscapes.

Could you confirm it?

hojunson avatar May 27 '22 05:05 hojunson

Hello Yuanduo,

I think your achievement is really awesome. I am looking into your code and your model to develop more on it.

I was wondering whether the "best.pth" model is the trained model without Imagenet pre-training.

I remember I got the file from the google drive and it shows about 75.xx in validation set of Cityscapes.

Could you confirm it?

All the models utilize the imagenet pre-training. 75.xx is abnormal. There are some third-party repos or papers reproducing my method and it is easy to achieve above 77% mIoU for ddrnet_23_slim. The model I provided should be 77.8.

ydhongHIT avatar May 27 '22 06:05 ydhongHIT

Hello Yuanduo,

I think your achievement is really awesome. I am looking into your code and your model to develop more on it.

I was wondering whether the "best.pth" model is the trained model without Imagenet pre-training.

I remember I got the file from the google drive and it shows about 75.xx in validation set of Cityscapes.

Could you confirm it?

If you have some problems, you can refer to this repo which provides the eval script.

ydhongHIT avatar May 27 '22 07:05 ydhongHIT