Model Training

[caesiummm]

Describe the bug
When I run train.py, I received the below error. I changed the main method into model training, using the ds dataset at first. But then, I keep receiving the error as mentioned below, I reckoned it has something to do with the class WarmUpLearningRate. Help me to solve the issue.

IMPORTANT The issue will be closed directly if you don't provide the image and the issue relates to transcription bugs.

Full Traceback
Traceback (most recent call last):
File "D:\OMR Project (9)-oemer\oemer-main\oemer\train.py", line 588, in
model = train_model(dataset_path)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\OMR Project (9)-oemer\oemer-main\oemer\train.py", line 452, in train_model
optim = tf.keras.optimizers.Adam(learning_rate=WarmUpLearningRate(learning_rate))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\keras\src\optimizers\adam.py", line 122, in init
self._learning_rate = self._build_learning_rate(learning_rate)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\keras\src\optimizers\optimizer.py", line 1282, in _build_learning_rate
return super()._build_learning_rate(learning_rate)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\keras\src\optimizers\optimizer.py", line 385, in _build_learning_rate
learning_rate(self.iterations)
File "D:\OMR Project (9)-oemer\oemer-main\oemer\train.py", line 383, in call
warm_lr = self.min_lr + self.warm_step_size * step
~~~~~~~~~~~~~~~~~~~~^~~~~~
File "D:\Python\Lib\site-packages\tensorflow\python\ops\variables.py", line 1013, in _run_op
return tensor_oper(a.value(), *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\tensorflow\python\util\traceback_utils.py", line 153, in error_handler
raise e.with_traceback(filtered_tb) from None
File "D:\Python\Lib\site-packages\tensorflow\python\framework\constant_op.py", line 102, in convert_to_eager_tensor
return ops.EagerTensor(value, ctx.device_name, dtype)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Cannot convert 4.999899999999999e-07 to EagerTensor of dtype int64

Command You Execute
python train.py

[3DThangs]

Try running it with python3 train.py instead of python train.py
Using python3 runs it with the python 3 interpreter, where as just python runs it as python 2.

[liebharc]

I hit the same issue as I looked into training, but at the time decided to ignore it as I was focusing on other parts. I used Python 3 so I don't think that's the issue. I was wondering if there was a change in Keras which causes that error, but it's a wild guess as I so far didn't find the time to look into this.