I use tensorflow=2.2.0 and merely use pip install -r requirements.txt

2023-05-24 12:37:08.097755: E tensorflow/stream_executor/cuda/cuda_blas.cc:428] failed to run cu$
LAS routine: CUBLAS_STATUS_NOT_SUPPORTED
2023-05-24 12:37:08.097805: E tensorflow/stream_executor/cuda/cuda_blas.cc:2301] Internal: faile$
BLAS call, see log for details
Traceback (most recent call last):
File "example_pcm.py", line 32, in
predict = model.m.predict(pcm)
File "/home/usslab/anaconda3/envs/jinghui_2/lib/python3.7/site-packages/tensorflow/python/kera$
/engine/training.py", line 88, in _method_wrapper
return method(self, *args, **kwargs)
File "/home/usslab/anaconda3/envs/jinghui_2/lib/python3.7/site-packages/tensorflow/python/kera$
/engine/training.py", line 1268, in predict
tmp_batch_outputs = predict_function(iterator)
File "/home/usslab/anaconda3/envs/jinghui_2/lib/python3.7/site-packages/tensorflow/python/eager
/def_function.py", line 580, in call
result = self._call(*args, **kwds)
File "/home/usslab/anaconda3/envs/jinghui_2/lib/python3.7/site-packages/tensorflow/python/eager
/def_function.py", line 650, in _call
return self._concrete_stateful_fn._filtered_call(canon_args, canon_kwds) # pylint: disable=p
rotected-access
File "/home/usslab/anaconda3/envs/jinghui_2/lib/python3.7/site-packages/tensorflow/python/eager
/function.py", line 1665, in _filtered_call
self.captured_inputs)
File "/home/usslab/anaconda3/envs/jinghui_2/lib/python3.7/site-packages/tensorflow/python/eager
/function.py", line 1746, in _call_flat
ctx, args, cancellation_manager=cancellation_manager))
File "/home/usslab/anaconda3/envs/jinghui_2/lib/python3.7/site-packages/tensorflow/python/eager
/function.py", line 598, in call
ctx=ctx)
File "/home/usslab/anaconda3/envs/jinghui_2/lib/python3.7/site-packages/tensorflow/python/eager
/execute.py", line 60, in quick_execute
inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InternalError: Blas xGEMMBatched launch failed : a.shape
=[3,459,257], b.shape=[1,257,64], m=459, n=64, k=257, batch_size=3
[[{{node ResCNN/lambda/PartitionedCall/MatMul}}]] [Op:__inference_predict_function_5121]

Function call stack:
predict_function