Shujian Deng

(1.2.17) Rational.java

1

在判断是否overflow时，int值好像本身就不会超过max和min，所以判断a + b < MAX这种是不是并不能得到想要的效果？ 其次，min应该是2^31，所以是-2147483648，不是-2147483647; 我的想法就是，比如ab>0且a > 0，根据a + b

will the inference memory reduced too?

1

As described in the title

As described in the title. Thank you!

As described in the title. Thank you

How to combine scores of stage1 and stage2

1

What if their prediction class is different? Like stage1 predict the box as cat, while stage2 predict the box as dog. Thank you

Have u tried to generate heatmaps around gt, then train the network with focal loss?

These pre-trained models are really helpful. But is the pretraining code available？I am kind of confused about how to combine 8 decoders into one unified network. Thx!

code to load 2D parameters (pretrained on imagenet) to 3D model

3

Could you please provide the code which loads 2D parameters (pretrained on imagenet) to I3D model？ (especially the processing of BN/GN). Thank you very much!

testing pretrained model - depth

8

 I'm using the pretrained model in folder "rgb2depth". I want to reproduce "loss = 0.35". Which data should I use? I've tried the "depth_zbuffer" test data, but "l1_loss, loss_g,...

could you please offer an example of x, c, A, B~The description in the paper is a little bit abstract. Thank you very much!