weecology / weecology/DeepForest

More cookbooks for quick start

Open
#754 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
774
Forks
265
PR merge metrics
No merged PRs in 30d

Description

User asks

we were wondering if you have any sample scripts that you share that e.g., load images, load annotations, train canopy delineation/extent model on image subset, run model on the entire image, assess accuracy of canopy delineation, attribute tree species based on field data collection, and assess accuracy of tree species. We can figure this out ourselves (possibly with some additional help from you), but I just thought I’d ask if you have a sample script for these tasks.

My sense is that all of this already exists within the docs, but the user started to look for it, couldn't find what they wanted and email me. @henrykironde this is part of the broader effort to improve navigation within the docs.
For each, let's point to location we would expect the user to find them in docs and figure out how to name and direct them there more cleanly.

  • load images
  • load annotations
  • train model on image subset (i'm not sure exactly what subset means here, crop?)
  • run model on entire image
  • assess accuracy of model
  • Multi-class point data to boxes
  • Train Multi-class Model and Validate.

We could approach this as one long use case for a particular project in the example/ dir with jupyter notebooks, or we can make them tiny gists in a cookbook section. @ethanwhite thoughts?
Let's use this issue to keep track of the different places

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the existing documentation for the listed workflows and locating the example/ directory; the issue also mentions Jupyter notebooks and a possible cookbook section. Map each checklist item to the clearest existing location before deciding between one use-case project and smaller cookbook examples. Done means the workflows are discoverable through clearer documentation navigation and the scope and format are resolved.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, python
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.