Medical-Transformer

Medical-Transformer copied to clipboard

what is the augmentation configuration that you used to achieve the best results?

tomeramit

MoNuSeg dataset

7

Hello! I resized the monuseg dataset to 512 × After 512, it still can't reach the effect of the original text. What method do you use to resized it? Thanks!

TangdoudouAN

About the GLAS Dataset

1

Hi, I have downloaded the GLAS Dataset, but I find the label has 10 classes, which are 0, 1, 2, 3, ..., 9. So, which class should be saved for...

QiaoSiBo

Brain US dataset??

1

Can you send me a copy of the Brain US dataset, my email is [email protected] Thank you very much!!!

hxp2396

Hi, I have downloaded the GLAS Dataset, but I find the label has 10 classes, which are 0, 1, 2, 3, ..., 9. So, which class should be saved for...

QiaoSiBo

There is an attempt to save images in `train.py` and `test.py`, and main step towards making such an image is separation output of the model by threshold 0.5 . Such...

rtyasdf

Question about the training speed

3

Hello, author. Thank you for your code. CUDA has been used and the batch size has been adjusted to 4, but the training speed of the model is still very...

JackHeroFly

Update utils.py

4

'labelcol' is not the folder name as in your readme.md, thus, code break. I changed it to 'label'. Also, the default size you have kept is (128, 128) but if...

abhishekvermasg

Thanks for this amazing work. Would it be possible for you to share the link to the trained model. I wanted to see the inference results. Thanks in advance

kartikwar

replaced hard coded part size with calculated size of partial images moved amount of image parts into variable

TheUser0815