Min

data preprocess

2

Do we need to normalize the training images into the range of (-1,1) before feed them into the network?

Pretraining RFBNet on source domain dataset COCO60, it shows loss nan

7

Hello, I really appreciate your work! When I pretrain RFBNet on source domain dataset COCO60, it shows loss nan. Is it correct and why?

Traceback (most recent call last): File "train.py", line 7, in from inpaint_model import InpaintCAModel File "/home/myang47/generative_inpainting/inpaint_model.py", line 13, in from neuralgym.ops.gan_ops import gan_hinge_loss File "/home/myang47/.pyenv/versions/tf/lib/python3.6/site-packages/neuralgym/ops/gan_ops.py", line 138, in class Conv2DSepctralNorm(tf.layers.Conv2D):...

Can you show me how to do tests after training WGAN

Does anyone know how to modify codes to fit any batch size?

Hello, I really appreciate your work! May I know what is the difference between the official Deformable DETR codes and your implementation?

Config file for using AdvSeg as uda

1

The given config file uses dacs as uda, does anyone know how to construct the config file for advseg? Thank you in advance.

Code

1

Can you share the code with me?

Hello, I am very interested in your work. However, I am still confused about how to build the universal prototype set C, and how to update it. I really appreciate...