tensorflow / tensorflow/models
Faster rcnn nas loss doesn't go down
Open
@pkulzc is already working on this.
Since Jun 19, 2020.
models:research:odapi
type:support
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I am training custom objects on faster_rcnn_nas but total loss doesn't go down 0.9 or takes so long. I trained same dataset with faster_rcnn_inception_resnet_v2 loss goes under 0.1 around a couple hours (2k-3k steps).
Should i train more?
Here my tensorboard loss graph (faster_rcnn_nas):
System information
- **TensorFlow version: 1.14
- GPU model and memory: Nvidia quadro p5000
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.