MoleImg

Results 6 comments of MoleImg

Use dice loss as the loss function,but sometimes loss is less than 0

If you use my code of dice loss directly, you may find it is not the exact Dice loss according to its definition, so it might be possible to become...

Use dice loss as the loss function,but sometimes loss is less than 0

@GusRoth I did not realize the networks EXACTLY according to the specific articles. I just integrated the modules into my networks. I can provide you some as follows: 1. For...

I have not seen the raw implement of attention Unet

Hi. The raw implementation of each attention u-net is in the corresponding .py file. I don't know what are you exactly confused about. Could you please describe your problem in...

I have not seen the raw implement of attention Unet

What do you mean by the raw attention unet? There are two kinds of attention unet in this repo.

Tesseract prints characters differ from lstmeval

Have you solved this problem? Since I met the same problem. I have a quite different OCR output compared with I use the "tesseract" command, using the same model. Could...

Tesseract prints characters differ from lstmeval

> No. We have not. Thanks for pinging. I try to find some time for it next week! Thanks. I'm struggling with this problem for such a long time, but...