Skip to content

🧑‍💻 Modify pretrained_models.yaml to Contain Catalog Information with description and tissue type - #1106

Open
mraoaakash wants to merge 28 commits into
developfrom
pretrainedmodels
Open

mraoaakash wants to merge 28 commits into
developfrom
pretrainedmodels

Conversation

@mraoaakash

Copy link
Copy Markdown
Collaborator

Partial PR for addition of pre-trained model documentation to the pretrained_model.yaml file. Includes the addition of a new filed called catalog to each model yaml entry. The entry is structured in the following manner:

catalog:
        description: >
                multi-line 
                model description
        primary_site:  primary site that model is supported for (agnostic for site-agnostic or multi-site models)
        supported_sites: 
            - other
            - supported 
            - sites

Fields can be read nested and used for downstream filtering tasks as necessary.

NOTE: This is a partial PR and does not contain the complete set of catalog entries as it proved difficult to ascertain the required catalog entries for some models. Someone with more complete knowledge of some models would have to take up the completion of the remaining catalog entries.

Description, primary site, and supported sites:

  • resnet34-idars-cimp
  • resnet34-idars-cin
  • resnet34-idars-tp53
  • resnet34-idars-hm
  • mapde-crchisto
  • sccnn-crchisto

Description only:

  • micronet-consep
  • mapde-conic
  • sccnn-conic
  • nuclick_original-pannuke
  • nuclick_light-pannuke

@mraoaakash mraoaakash self-assigned this Jul 30, 2026
@mraoaakash mraoaakash added documentation Improvements or additions to documentation enhancement New feature or request labels Jul 30, 2026
@mraoaakash mraoaakash changed the title Pretrainedmodels Modified pretrained_models.yaml to contain model catalog information with description, primary site, and supported sites. Jul 30, 2026
Comment thread tiatoolbox/data/pretrained_model.yaml Resolved
@@ -1,5 +1,11 @@
alexnet-kather100k:
hf_repo_id: TIACentre/TIAToolbox_pretrained_weights

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@gozdeg please can you add any missing information in this PR from the models.json file?

@@ -1,5 +1,11 @@
alexnet-kather100k:
hf_repo_id: TIACentre/TIAToolbox_pretrained_weights
catalog:

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add a field for engines.

num_output_channels: 5
encoder: "resnet50"
decoder_block: [3, 3]
class_dict: {0: "Tumour", 1: "Stroma", 2: "Inflamatory", 3: "Necrosis", 4: "Others"}

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We do not need to remove class_dict. Instead we should add these for the missing ones.

Comment thread uv.lock Outdated
@@ -0,0 +1,3 @@
version = 1

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please remove this file.

Comment thread tiatoolbox/data/pretrained_model.yaml Outdated
hf_repo_id: TIACentre/TIAToolbox_pretrained_weights
catalog:
description: >
Predict Normal, Debri, Tumor, Adipose, Mucus, Smooth, Stroma, Lymphocytes regions at a patch level in colon images.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Predict Normal, Debri, Tumor, Adipose, Mucus, Smooth, Stroma, Lymphocytes regions at a patch level in colon images.
Predict Normal, Debris, Tumor, Adipose, Mucus, Smooth, Stroma, Lymphocytes regions at a patch level in colon images.

Comment thread tiatoolbox/data/pretrained_model.yaml Outdated
hf_repo_id: TIACentre/TIAToolbox_pretrained_weights
catalog:
description: >
Predict Normal, Debri, Tumor, Adipose, Mucus, Smooth, Stroma, Lymphocytes regions at a patch level in colon images.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Predict Normal, Debri, Tumor, Adipose, Mucus, Smooth, Stroma, Lymphocytes regions at a patch level in colon images.
Predict Normal, Debris, Tumor, Adipose, Mucus, Smooth, Stroma, Lymphocytes regions at a patch level in colon images.

Comment thread tiatoolbox/data/pretrained_model.yaml Outdated
description: >
Predict Normal, Debri, Tumor, Adipose, Mucus, Smooth, Stroma, Lymphocytes regions at a patch level in colon images.
primary_site: colon
supported_sites:

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Remove supported_sites

Comment thread tiatoolbox/data/pretrained_model.yaml Outdated
catalog:
description: >
Predict Normal, Debri, Tumor, Adipose, Mucus, Smooth, Stroma, Lymphocytes regions at a patch level in colon images.
primary_site: colon

@shaneahmed shaneahmed Aug 7, 2026 •

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
primary_site: colon
tissue_types: colon

@@ -1,5 +1,11 @@
alexnet-kather100k:

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

At the top of the file, explain in comments what different fields mean in this file.

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Only for the catalog field or all possible fields for a given model entry in the yaml?

@codecov

codecov Bot commented Sep 11, 2026 •

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 99.91%. Comparing base (c4a5afa) to head (b717ece).

Additional details and impacted files
@@           Coverage Diff            @@
##           develop    #1106   +/-   ##
========================================
  Coverage    99.91%   99.91%           
========================================
  Files          117      117           
  Lines        13587    13587           
  Branches      1624     1624           
========================================
  Hits         13576    13576           
  Misses           5        5           
  Partials         6        6           

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@mraoaakash

Copy link
Copy Markdown
Collaborator Author

Have added the major components and changes. Will be visiting the remaining models on idars and crchisto soon.

@mraoaakash

Copy link
Copy Markdown
Collaborator Author

Added in all required descriptions except for Nuclick - will clarify and update.

@shaneahmed shaneahmed changed the title Modified pretrained_models.yaml to contain model catalog information with description, primary site, and supported sites. 🧑‍💻 Modify pretrained_models.yaml to Contain Catalog Information with description, primary site, and supported sites. Nov 6, 2026
@mraoaakash mraoaakash changed the title 🧑‍💻 Modify pretrained_models.yaml to Contain Catalog Information with description, primary site, and supported sites. 🧑‍💻 Modify pretrained_models.yaml to Contain Catalog Information with description and tissue type Nov 6, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants