zhanghang1989 / zhanghang1989/PyTorch-Encoding
Changing the number of input channels for segmentation.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
Hello Hang Zhang!
Thanks for this nice repo!
I would like to try using DeepLabV3 with ResNeSt in a unconventional way: I am doing pixel regression (regression on images) and my input image only has one channel. I then have to retrain the full model.
I looked into the code, and there is no argument for the input channels, and the pretrained is set to True. I'd like to branch, but I am scared that I will be behind master after some time.
What can we do about this?
Do you think it is going to work without using a pretrained backbone?
If yes, would you be opened to a pull request adding the possibility to change the number of input channels with an optional argument (I would add the feature to all backbones)?
Thanks in advance!
Best,
Nicolas
Contributor guide
No contributing guide indexed for this repository
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 issue names no files or tests. Start by tracing DeepLabV3 with ResNeSt model construction and the pretrained backbone setup, then determine how an optional input-channel setting would apply across all backbones; done means the requested one-channel use case works with and without pretrained weights.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100