Update anchor_generator.py

[djkmarchetto]

Enhance compatibility with SymbolicTensor using ops instead of math

Fixes

TypeError: Exception encountered when calling RetinaNetLabelEncoder.call().

must be real number, not SymbolicTensor

Arguments received by RetinaNetLabelEncoder.call(): • images=tf.Tensor(shape=(64, None, None, 3), dtype=float32) • box_labels={'classes': 'tf.Tensor(shape=(64, 100), dtype=float32)', 'boxes': 'tf.Tensor(shape=(64, 100, 4), dtype=float32)'}

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, Pull Request section?
• [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case.
• [ ] 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?

@divyashreepathihalli @sampathweb

[google-cla[bot]]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.