Fine-tuning script for pretrained models
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 45/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- python
- Domain
- machine-learning
Research direction
The work goes in scripts/finetune.py, which does not exist yet. Before writing it, read the split and augmentation code that #36 and #20 introduce, since this issue says to reuse them and both are listed as dependencies. The CLI takes --arch, --epochs and --lr. Done means both mobilenetv2_100 and efficientnet_b0 fine-tune end to end and write the best checkpoint and history to results/.
Written by the indexing model from the issue text.
Description
Same split and augmentation as the custom models.
Files: scripts/finetune.py
Tasks
- CLI:
--arch mobilenetv2_100|efficientnet_b0 --epochs 15 --lr 1e-4 - Adam + cosine-annealing scheduler, all layers trainable
- Save best checkpoint and history to
results/
Done when
Both architectures can be fine-tuned with the script.
Depends on
#36 #20
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