tensorflow / tensorflow/models
There is a lot of bounding box around image after the detection
Open
@jch1 is already working on this.
Since May 12, 2020.
models:research:odapi
type:support
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
I trained the faster_rcnn_inception_v2_coco model with 64173 step on my dataset (1700 train, 400 test). I got last 10 losses around 0,002-0,008 but when I use that model on a test image , I got a lot of bounding box in that image moreover in incorrect places.
like this.
I did all configurations according to this github repo
I trained it on google colap
Note: the class "plaka" means "plate"
What should I do to get min correct bounding box ?
Thanks in advance
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.