lightly-ai / lightly-ai/lightly-train
[FEAT] .npy files training
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.7k
- Forks
- 116
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 6
Description
### 💡 Is your feature request related to a problem?
I am working with DICOM data and wondering is it better to do the pretrain on .npy extracted from DICOM files directly (e.g. using pydicom) instead of image formats presented in docs.
### 🧰 Describe the solution you'd like
Add support to .npy files in addition to image formats presented in docs.
### 🛠 Alternatives you've considered
Just save to img formats presented in docs and keep the same pre-processing while doing downstream task.
Contributor guide
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.
Research direction
The request concerns .npy files extracted from DICOM data with pydicom, alongside the image formats described in the documentation. Start by reviewing the documented image-input and preprocessing path; done means .npy inputs are accepted for training with the expected preprocessing.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- numpy, python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100