Alex Lau

Thanks for the greatwork! It is creative and the shown results are promising. I saw from paper you have several baselines to be compared against your proposed CSMN (e.g. 1-nearest...

What is the traing v.s. validation loss on your trained model

1

Thanks for the tutorial and code implementation! I am trying to train the model on my custom dataset and I encountered high loss on both training dataset and validation dataset...

Thanks for making such a great collection of tutorials open source, Ritchie! I am not raising a bug but instead have a genuine question on how you managed to render...

From Generation to Translation

5

This is a very interesting work! Do you think this model can be easily adapted to tackle SVG translation problem? (ie translating a SVG from one type to another) Do...

Thanks for the great work! I have 2 questions: 1. I wanna do custom training on images of different dimensions, could your training pipeline handle that? or I needa write...

First of all, thanks for open-sourcing such an amazing lib! I am trying to find out a chance to apply this lib (or other libs that you created) on a...

I would like to deploy this interactive annotations on images with overlapping chromosomes. Does the model supports annotation of overlapping masks?

Hi! I am looking for a way to implement callbacks in PyTorch, so as to mimic the way I write training pipeline in Keras. I find your repo very comprehensive...

Great work! From the softmax setting, it seems the trick is typically applied on multi-class classification. Do you think the trick can be extended to multi-label classification? If so, what...

How Long does It Take to Train Your Model

2

I saw from ur readme doc that you take ~100k images for training. I would like to know more abt the training details, such as: 1. What is the resolution...