You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
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)
The text was updated successfully, but these errors were encountered:
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)
The text was updated successfully, but these errors were encountered: