Sean Xuefeng Du

cannot reproduce the results in the paper

2

Hi, @cuishuhao , thanks for your code implementations, but when I tried to reproduce the results in the paper using the office-31 dataset, specifically from the dslr dataset to the...

Hi, @ashafahi , thanks for your implementation, when evaluating your model during training, it seems like you did not switch off the batch norm, will that cause some difference in...

why not use the torchvision dataset for SVHN?

1

Hi, @gmh14 , thanks for our implementation, I notice that you re-implement the SVHN dataset in the dataset.py, kindly want to know what is the point of rewriting the dataset...

architectures compared to neural ode

3

Hi, @EmilienDupont , thanks for the code implementation! I am concerned about the structure implemented in this repo, actually, the architecture in the orginal Neural ODE (chen et al. )...

How to generate the json from the MCG proposals

2

Hi, thanks for your simplified implementation, If I want to use this code on COCO, for the input data, how do you obtain the json segmentation files from the coarse...

Questions with respect to the code.

3

Hi, @liyiying , Thanks for your implementation. I am a little confused with the method in the paper. Actually, your aim in the paper is the domain generalization. However, in...

why reverse the order of decoder output?

2

Hi, @huaxiuyao , thanks for your implementation, I notice that when you generate the decoder output in the task_embedding.py, you reverse the order of the prototypes, what is the meaning...

Questions with respect to the code implementation

2

Hi, @xujinfan , thank you for your implemenation first. After checking the code, I find there are some questions in the implementation of the policy generator. Such as in the...

questions with respect to the no_grad()

1

Hi, @dragen1860 , thanks for your implementation, I have a problem running the code, When I set the number of inner updates to 1, then an exception occurs, " RuntimeError:...

About training code

4

@lukas-schott , thank you for your implementation, can you also show the training code in order to me to evaluate it on other datasets? Thanks