PyCharmで(ImportError: DLL load failed: 指定されたプロシージャが見つかりません。)というエラーが出て、tensorflowが上手く実行されません。

前提・実現したいこと

githubで挙げられていたニューラルネットワークに関するプログラムを実行させることです。

発生している問題・エラーメッセージ

全エラーメッセージ文は以下の通り

2020-11-15 14:37:41.202428: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2020-11-15 14:37:41.202834: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
  File "C:/Users/student/AppData/Roaming/JetBrains/PyCharmCE2020.2/scratches/pydens_sem(all).py", line 4, in <module>
    import tensorflow as tf
  File "C:\Users\student\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\__init__.py", line 41, in <module>
    from tensorflow.python.tools import module_util as _module_util
  File "C:\Users\student\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\__init__.py", line 41, in <module>
    from tensorflow.python.eager import context
  File "C:\Users\student\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\eager\context.py", line 32, in <module>
    from tensorflow.core.framework import function_pb2
  File "C:\Users\student\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\core\framework\function_pb2.py", line 7, in <module>
    from google.protobuf import descriptor as _descriptor
  File "C:\Users\student\AppData\Local\Programs\Python\Python36\lib\site-packages\google\protobuf\descriptor.py", line 48, in <module>
    from google.protobuf.pyext import _message
ImportError: DLL load failed: 指定されたプロシージャが見つかりません。

該当のソースコード

python
1import sys
2sys.path.append('../')
3import tensorflow as tf
4import numpy as np
5from tqdm import tqdm_notebook
6import matplotlib.pyplot as plt
7from ipywidgets import interact
8
9from pydens import add_tokens, Solver, NumpySampler, cart_prod, ConstantSampler
10from pydens import plot_loss, plot_pair_1d, plot_2d, plot_sections_2d
11add_tokens()
12# describing pde-problem in pde-dict
13pde = {'n_dims': 2,
14       'form': lambda u, x, t: D(u, t) - D(D(u, x), x) - 5 * x * (1 - x),
15       'initial_condition': lambda x: x * (1 - x) * 4}
16
17# put it together in model-config
18config = {'pde': pde,
19          'decay': {'name': 'invtime', 'learning_rate':0.01, 'decay_steps': 100, 'decay_rate': 0.05}}
20
21# uniform sampling scheme
22s = NumpySampler('u', dim=2)
23
24# train the network on batches of 100 points
25model = Solver(config)
26model.fit(batch_size=500, sampler=s, n_iters=1200, bar='notebook')
27
28plot_loss(model.loss, color='cornflowerblue')
29plot_sections_2d(model, timestamps=(0, 0.01, 0.1, 0.3, 0.4, 0.7), ylim=(0.0, 1.0))
30