Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TypeError: Could not build a TypeSpec for KerasTensor(type_spec=TensorSpec(shape=(None, None, 4), dtype=tf.float32, name=None), name='tf.math.truediv/truediv:0' #3056

Open
poor-soul opened this issue Nov 8, 2024 · 0 comments

Comments

@poor-soul
Copy link

We are trying to train Mask RCNN in
Python 3.10.12
tensorflow=2.9.1
keras=2.9.0

our dataset is annotated with 30 images, a sample to know how well it works.
we have encountered the error:
TypeError: Could not build a TypeSpec for KerasTensor(type_spec=TensorSpec(shape=(None, None, 4), dtype=tf.float32, name=None), name='tf.math.truediv/truediv:0', description="created by layer 'tf.math.truediv'") of unsupported type <class 'keras.engine.keras_tensor.KerasTensor'>.

Please help me in having a better understanding on encountering the error and how to solve it
Could anyone provide guidance on how to train Mask RCNN in in given specification(present tensorflow starts from 2.8.0), also providing insights on:

->dataset size
->How long will it take for training(to run one epoch and the whole training process as well)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant