train.py giving Function call stack: train_function error.

[jk28jan1990]

Dear Professor,

I am trying to run train.py but receiving this error. please provide guidance so that I can reproduce the results.
Epoch 1/50000
Traceback (most recent call last):
File "c:/Users/2585552k/Downloads/BF-design-with-DL-master/train.py", line 59, in
epochs=50000, verbose=2, validation_split=0.1, callbacks=[reduce_lr, checkpoint])
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 66, in _method_wrapper
return method(self, *args, **kwargs)
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 848, in fit
tmp_logs = train_function(iterator)
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\def_function.py", line 580, in call
result = self._call(*args, **kwds)
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\def_function.py", line 644, in _call
return self._stateless_fn(*args, **kwds)
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 2420, in call
return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 1665, in _filtered_call
self.captured_inputs)
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 1746, in _call_flat
ctx, args, cancellation_manager=cancellation_manager))
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 598, in call
ctx=ctx)
File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\execute.py", line 60, in quick_execute
inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [9] vs. [64]
[[node gradient_tape/model/lambda_1/MatMul/BroadcastGradientArgs (defined at c:/Users/2585552k/Downloads/BF-design-with-DL-master/train.py:59) ]] [Op:__inference_train_function_1689]

Function call stack:
train_function

[TianLin0509]

hello, please first check that if your tensor flowers version is 1.12.0发自我的华为手机-------- 原始邮件 --------发件人： jk28jan1990 <[email protected]>日期： 2021年2月19日周五 凌晨1:36收件人： TianLin0509/BF-design-with-DL <[email protected]>抄送： Subscribed <[email protected]>主 题： [TianLin0509/BF-design-with-DL] train.py giving Function call stack: train_function error. (#8) Dear Professor, I am trying to run train.py but receiving this error. please provide guidance so that I can reproduce the results. Epoch 1/50000 Traceback (most recent call last): File "c:/Users/2585552k/Downloads/BF-design-with-DL-master/train.py", line 59, in epochs=50000, verbose=2, validation_split=0.1, callbacks=[reduce_lr, checkpoint]) File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 66, in _method_wrapper return method(self, *args, **kwargs) File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 848, in fit tmp_logs = train_function(iterator) File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\def_function.py", line 580, in call result = self._call(*args, **kwds) File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\def_function.py", line 644, in _call return self._stateless_fn(*args, **kwds) File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 2420, in call return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 1665, in _filtered_call self.captured_inputs) File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 1746, in _call_flat ctx, args, cancellation_manager=cancellation_manager)) File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 598, in call ctx=ctx) File "C:\Users\2585552k\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\execute.py", line 60, in quick_execute inputs, attrs, num_outputs) tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [9] vs. [64] [[node gradient_tape/model/lambda_1/MatMul/BroadcastGradientArgs (defined at c:/Users/2585552k/Downloads/BF-design-with-DL-master/train.py:59) ]] [Op:__inference_train_function_1689] Function call stack: train_function —You are receiving this because you are subscribed to this thread.Reply to this email directly, view it on GitHub, or unsubscribe.

[Ganesh9100]

kindly try with train v2 as it supports tensorflow > 2