Xiaoyang Chen comments

Results 8 comments of


                                            Xiaoyang Chen

not-edge loss value is too small, edge loss is nan/inf

Have you guys obtained improved results using affinity field loss? I tried many times, but I can hardly get improved results over my baseline. I also have the same issue...

questions of function "ignores_from_label" in layers.py

Do not understand why you think the results are unexpected. What is your expectation of the outputs?

We downloaded the data set and model parameters in your steps, but get the value of loss is Nan at run time.

Have you solved the problem and how? Same problem here Thanks

WGAN-GP producing bad result with CIFAR10

Have you solved your problem? If you do, could you share your experience for training GAN? I am a newbie for GAN. Thanks

How to apply the boundary loss to 3D images both efficiently and correctly?

> The solution is to pre-compute offline the distance map in 3D, save them into a `.npy` in the with the axises `kxyz`, with `k` being the class axis. Pay...

How to apply the boundary loss to 3D images both efficiently and correctly?

Thanks for your response. I tried your loss function on our dataset, however, I have not seen improved performance till now. I want to know if the simplification from the...

How to apply the boundary loss to 3D images both efficiently and correctly?

Also, what does ‘rebalance’ mean and how to implement it? Thanks Get Outlook for iOS ________________________________ From: Chen, Xiaoyang Sent: Sunday, November 29, 2020 2:28:53 PM To: LIVIAETS/boundary-loss ; LIVIAETS/boundary-loss...

How to apply the boundary loss to 3D images both efficiently and correctly?

I tried to understand the the mathematics in your paper. It is interesting to see the beautiful connection between Eq 2 and 3. However, I found it difficult to understand...