求助pycharm警告：＜frozen importlib._bootstrap＞:228: RuntimeWarning: scipy._lib.messagestream.MessageStrea

使用的是pycharm，pytorch框架：

python3.7.6
torch == 1.8.1
numpy == 1.20.1
scipy == 1.6.1
mne == 0.22.0
scikit-learn == 0.23.2
pyriemann == 0.2.6
本来是准备先画一下别人给出的绘制loss的图，找到的别人的loss代码如下如下：

from keras.models import Model
from keras.preprocessing import sequence
from keras.layers import Input
from keras.layers import Dense, Activation
from keras.layers import Embedding
from keras.layers import Conv1D, GlobalMaxPooling1D
from keras.datasets import imdb
from keras import optimizers
import matplotlib
matplotlib.use('agg')
import matplotlib.pyplot as plt

# set parameters:
batch_size = 32
embedding_dims = 200
filters = 250
kernel_size = 3


# load the dataset but only keep the top n words, zero the rest
top_words = 5000
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=top_words)
# pad dataset to a maximum review length in words
max_words = 500
x_train = sequence.pad_sequences(x_train, maxlen=max_words)
x_test = sequence.pad_sequences(x_test, maxlen=max_words)

# Build model
sentence = Input(batch_shape=(None, max_words), dtype='int32', name='sentence')
embedding_layer = Embedding(top_words, embedding_dims, input_length=max_words)
sent_embed = embedding_layer(sentence)
conv_layer = Conv1D(filters, kernel_size, padding='valid', activation='relu')
sent_conv = conv_layer(sent_embed)
sent_pooling = GlobalMaxPooling1D()(sent_conv)
sent_repre = Dense(250)(sent_pooling)
sent_repre = Activation('relu')(sent_repre)
sent_repre = Dense(1)(sent_repre)
pred = Activation('sigmoid')(sent_repre)
model = Model(inputs=sentence, outputs=pred)

#underfit
epochs = 10
sgd = optimizers.sgd(lr=0.01)
history = model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy'])

#overfit
# epochs = 30
# sgd = optimizers.sgd(lr=0.01)
# history = model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy'])

loss = history.history['loss']
val_loss = history.history['val_loss']
plt.plot(loss, label='loss')
plt.plot(val_loss, label='val_loss')
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'valid'], loc='upper left')
plt.savefig('./loss.png')

然后我试着在我的pycharm软件上运行，结果出错了，具体我忘记是什么错误了，应该是跟’keras’有关，然后网上查解决方法说是让安装keras。
安装keras以后，我再跑我自己其他的py文件。
然后此时报错了，大概是说和scikit-learn冲突了吧，我觉得是安装keras导致出错误了。
然后我卸载了keras，出现了另一个错误。然后我就一顿乱操作。
一顿乱操作以后错误没了又出了个警告 ：
<frozen importlib._bootstrap>:228: RuntimeWarning: scipy._lib.messagestream.MessageStream size changed, may indicate binary incompatibility. Expected 56 from C header, got 64 from PyObject。

所以这个警告有大佬知道是咋回事吗？

如果有遇到过这个警告，并且成功解决的大佬还请麻烦几分钟说一下具体的解决办法，万分感谢！！！