在Spyder界面中使用tensorflow进行fashion_mnist数据集学习，结果loss为非数，并且准确率一直未变

Question

1.建立了一个3个全连接层的神经网络；
2.代码如下：

import matplotlib as mpl
import matplotlib.pyplot as plt
#%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras

print(tf.__version__)

print(sys.version_info)
for module in mpl, np, sklearn, tf, keras:
    print(module.__name__,module.__version__)

fashion_mnist  = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]



#tf.keras.models.Sequential
model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape= [28,28]))
model.add(keras.layers.Dense(300, activation="relu"))
model.add(keras.layers.Dense(100, activation="relu"))
model.add(keras.layers.Dense(10,activation="softmax"))
###sparse为最后输出为index类型，如果为one hot类型，则不需加sparse
model.compile(loss = "sparse_categorical_crossentropy",optimizer = "sgd", metrics = ["accuracy"])

#model.layers
#model.summary()
history = model.fit(x_train, y_train, epochs=10, validation_data=(x_valid,y_valid))

3.输出结果：

runfile('F:/new/new world/deep learning/tensorflow/ex2/tf_keras_classification_model.py', wdir='F:/new/new world/deep learning/tensorflow/ex2')
2.0.0
sys.version_info(major=3, minor=7, micro=4, releaselevel='final', serial=0)
matplotlib 3.1.1
numpy 1.16.5
sklearn 0.21.3
tensorflow 2.0.0
tensorflow_core.keras 2.2.4-tf
Train on 55000 samples, validate on 5000 samples
Epoch 1/10
WARNING:tensorflow:Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x0000025EAB633798> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: 
WARNING: Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x0000025EAB633798> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: 
55000/55000 [==============================] - 3s 58us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 2/10
55000/55000 [==============================] - 3s 48us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 3/10
55000/55000 [==============================] - 3s 47us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 4/10
55000/55000 [==============================] - 3s 48us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 5/10
55000/55000 [==============================] - 3s 47us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 6/10
55000/55000 [==============================] - 3s 48us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 7/10
55000/55000 [==============================] - 3s 47us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 8/10
55000/55000 [==============================] - 3s 48us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 9/10
55000/55000 [==============================] - 3s 48us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914
Epoch 10/10
55000/55000 [==============================] - 3s 48us/sample - loss: nan - accuracy: 0.1008 - val_loss: nan - val_accuracy: 0.0914

Answer 1

不知道你这个问题是否已经解决, 如果还没有解决的话:

• 这篇文章：（保姆教程)Spyder 配置Tensorflow(2.5.0)和keras(2.4.3) 也许有你想要的答案，你可以看看

如果你已经解决了该问题, 非常希望你能够分享一下解决方案, 写成博客, 将相关链接放在评论区, 以帮助更多的人 ^-^