Giters

BMIRDS / deepslide

Code for the Nature Scientific Reports paper "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks." A sliding window framework for classification of high resolution whole-slide images, often microscopy or histopathology images.

Home Page:https://www.nature.com/articles/s41598-019-40041-7

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

inference instructions; pretrained weights (see https://github.com/BMIRDS/deepslide/issues/35)

GeorgeBatch opened this issue · comments

commented

Hello!

Thank you for making this repository! Do you think you could provide more detailed instructions on how to run the inference? I found the instructions here https://github.com/BMIRDS/deepslide#4-testing-on-wsi a bit too concise. In particular, I wanted to try running the inference step on one WSI from the dataset to see that everything works with my software/hardware combination.

I would really appreciate it if you could release the pre-trained weights as asked in Issue #35. This will allow just trying your code on one example to see if everything works just on one WSI without training the models from scratch, which in turn will be a good indicator of how much code I can reuse from this repository.

Best wishes,
George Batchkala

commented

We currently are unable to share the pre-trained model weights publicly. Any potential changes to this decision will be reflected in an update on the README, should they happen.