Skip to content

Frequently Asked Questions

Tasneem edited this page Jun 16, 2022 · 15 revisions

We collect feedbacks and sorted them into a FAQ section here:

How to Install PyTorch?


The general guides for installing Pytorch can be summarized as follows:

  1. Check your NVIDIA GPU Compute Capability @ https://developer.nvidia.com/cuda-gpus
  2. Download CUDA Toolkit @ https://developer.nvidia.com/cuda-downloads
  3. Install PyTorch command can be found @ https://pytorch.org/get-started/locally/

How to keep track of model ID? What do they mean?


  • For a given project, the database contains the latest model id under the "iteration" column.
  • A model_id of -1 means no AI model has been trained at all.
  • A model_id of 0 represents the initial autoencoder.
  • A model_id of >=1 represents the deep learning iteration.

How to install OpenSlide?


Since PatchSorter currently does not support WSIs, the users need to divide WSI into smaller image tiles.

However, we received feedbacks that many Windows users had difficulty in OpenSlide. Therefore, we provide a detailed tutorial for installing and importing OpenSlide in Windows.

  1. Find and install OpenSlide Python with proper python version @ https://pypi.org/project/openslide-python/
  2. Find and install OpenSlide Window Binaries @ https://openslide.org/download/
  3. Add openslide\bin to system environment path. (Many of our testers forget to add OpenSlide to path, so they could not import OpenSlide properly.)
    Control Panel -> System Properties -> Advanced -> Environment Variables 
    -> System variables -> *Path* 

What are the various types of Mask image supported by PatchSorter(PS)?

PS supports four types of masks,

  1. QuickAnnotator Masks(Masks obtained out of QuickAnnotator)
Some synthetic examples of QA mask.

  1. Binary Mask
Some synthetic examples of binary mask.

  1. Indexed Mask
A synthetic example of an indexed mask.

  1. Labelled Mask
Some synthetic examples of labelled mask.

What is the format of File list Upload?

FileList - would contain 3 columns.
Column 1 - should contain image name with its absolute filepath
Column 2 - should contain image mask name with its absolute filepath
Column 3 - should contain image csvlabels file name with its absolute filepath.

If user chooses not have a mask or a csvlabels file, that column should be left empty
Example below is a file with no mask names