Embed LR schedule and initialization with the model
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
I tried to implement SqueezeNet as a torchvision model and train it via ImageNet example, and found that it doesn't converge as is. The reference code differs in two aspect:
- All but the last convolutions are initialized with Xavier Glorot initializer, the last is normal with stdev 0.01
- The learning rate is linearly decreased (polynomial schedule with power=1).
In PyTorch these aspects are hard-coded inside the ImageNet example, but I think it makes sense to make them part of the model definition in torch.vision. What's your position on it?
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
Start by comparing the linked SqueezeNet reference with the PyTorch ImageNet example, focusing on convolution initialization and the linear learning-rate schedule. Then inspect the torchvision model definition to determine how these concerns could be represented, and define completion around matching the reference training behavior without relying on hard-coded example settings.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100