Load images, resize to 64x64 and cache as .npz
@Sandali0726 is already working on this.
Since Oct 11, 2026.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 55/100
Research direction
Work in src/data.py, adding load_raw_images(root) and get_dataset(). Issue #5 is listed as a dependency, so check whether it has landed and what it provides for locating the 256x256 originals before you start. Done means get_dataset() returns X with shape (3000, 64, 64, 3) and labels 0/1/2 with 1000 each, and the data/animals64.npz cache is written once and reused on later calls.
Written by the indexing model from the issue text.
Description
Resize the 256x256 originals to 64x64 (bilinear) to emulate an edge camera; cache to avoid re-resizing.
Files: src/data.py
Tasks
-
load_raw_images(root)-> X uint8 (N,64,64,3), y int64 (N,) -
get_dataset()buildsdata/animals64.npzonce, loads it afterwards - Convert every image to RGB before resizing
Done when
get_dataset() returns X with shape (3000, 64, 64, 3) and labels 0/1/2, 1000 each.
Depends on
#5
Close with a commit or PR message containing Closes #<this issue>.
- Dominant language
- Jupyter Notebook
- Stars
- 0
- Forks
- 0
- Avg merge
- 1m
- Merged PRs (30d)
- 3
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from VisionForgeCSE/CNN-For-Image-Classification
-
evaluation
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
-
evaluation good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
-
evaluation
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
training
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Optimizer factoryOpentraining
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
All issues in VisionForgeCSE/CNN-For-Image-Classification
Similar issues
-
good first issue hacktoberfest help wanted
Difficulty 2/5 Under an hour Newbie friendliness 76/100
pacocartones/free-llm-api-hub#262 ·
Maintainers usually reply within 1 day
-
automation models
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 93/100
BSData/horus-heresy-3rd-edition#3232 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 92/100
Maintainers usually reply within 2 days
-
lane:discover
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
SPARDiffData/differential-data-collection#33 ·
Maintainers usually reply within 1 day