I’ve been trying to create an object detection model in keras framework from scratch. But can only find possible solutions for RCNN and other prebuild libraries. Kindly tell me a way to create a model in keras that can detect objects with bounding boxex on my own custom model. Am really stuck on it.
Bhack
September 8, 2022, 8:33pm
#3
There some models that are landing in Keras-cv.
E.g. see:
keras-team:master
← qlzh727:maskrcnn
opened 06:05PM - 01 Sep 22 UTC
# Note that this PR is more for a demo and not intend to be submitted at the mom… ent.
# What does this PR do?
Add MaskRCNN model as a test for the wrapper approach with TF model garden code.
1. The current class only contains the model building logic.
2. Most of the tunable params are currently backed in the function, and not exposed to use yet.
3. Verify the model building logic in the test. (will need tfm pip deps to work)
Next step:
1. Configure the input parsing logic for coco, and also anchor generation.
2. Mimic the training loop logic as model.train_step/eval_step
3. Train model e2e.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
- [x] Did you read the [contributor guideline](https://github.com/keras-team/keras-cv/blob/master/.github/CONTRIBUTING.md),
Pull Request section?
- [ ] Was this discussed/approved via a Github issue? Please add a link
to it if that's the case.
- [x] Did you write any new necessary tests?
- [ ] If this adds a new model, can you run a few training steps on TPU in Colab to ensure that no XLA incompatible OP are used?
## Who can review?