tensorflow / tensorflow/models
I am planning to add class weights to give extra weightage for my classes which has lesser count. I got the concept but I am stuck with where to add this. Can I add this in pipeline config file?? If yes where?.
Open
Nobody has claimed this yet.
models:research:odapi
type:support
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
I am training EfficienDet D4 on my custom dataset using TensorFlow Object Detection API, I have an imbalanced dataset so, I am planning to add class weights to give extra weightage for my classes which has lesser count. I got the concept but I am stuck with where to add this. Can I add this in pipeline config file?? If yes where?. Otherwise which is the file where model.fit lies. Please give suggestions. Or if there is better way of doing this, please let me know. where does class_weights or weighted loss penalize the network? Actually I want to implement the solutions from the above link
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.
Assessment
This issue has not been assessed yet.