Peidong Liu

icon indicating a website link perdonliu.github.io icon indicating an email [email protected]

icon company Tsinghua University icon location Beijing icon location Algorithm Engineer in DJI Automotive. Master Student in CS @ Tsinghua University. My research interest lies in Visual-Language Model and Autonomous Driving.

Results 3 comments of Peidong Liu
trafficstars

Can I train with patches?

Thanks for your reply! The following is what I did in detail: I first preprocessed the large images(224\*224) as usual and then generated small patches and fed all individual patches...

Can I train with patches?

Thanks to your reply! In the `generate_heatmap_pytorch` method, I use patchsize=33 and stride=8 with padding just as what you did. Now the situation is : In the testing process, the...

Reproduce the results of the paper

I can not reproduce the result, either. On CIFAR-10, I used exactly the same setting as paper did(batch-size 256, epoch 350, target rate 0.7) but got 6.68% top-1 error.