bardiadoosti

icon indicating a website link https://bardiadoosti.github.io/

icon company Google icon location PhD in Computer Science, Research in Computer Vision, AI/ML Software Engineer at Google

Results 4 comments of bardiadoosti

Test error is bigger than reported

Hi, today I checked the weights and found out unfortunately something is wrong with the provided weights specially regarding to the GraphUNet's performance. I try to solve this problem by...

Some weights and baises are missing in the graphunet pre-trained model

Oh it seems that I mistakenly trained a wrong model. Please give me a couple of days and I will publish the correct weights.

Some weights and baises are missing in the graphunet pre-trained model

Yes it is correct. To quickly share the weights I just trained for 2K iterations. The full training cycle is 10K.

Intrinsic/Extrinsic parameters between different datasets

Hi Mohamed, Yes GraphUNet's performance is conditioned on the camera parameters of a particular dataset and a model trained with one dataset will not work on another dataset with different...