tensorflow model accuracy does not increase for mnist data - tensorflow

Question

I am currently studying the book hands on machine learning. I want to create a simple neural network, as described in the book chapter 10 for the mnist hand written data. But my model is stuck, and the accuracy is not increasing at all.
Here is my code:
import tensorflow as tf
from tensorflow import keras
import pandas as pd
import numpy as np
data = pd.read_csv('sample_data/mnist_train_small.csv', header=None)
test = pd.read_csv('sample_data/mnist_test.csv', header=None)
labels = data[0]
data = data.drop(0, axis=1)
test_labels = test[0]
test = test.drop(0, axis=1)
model = keras.models.Sequential([
keras.layers.Dense(300, activation='relu', input_shape=(784,)),
keras.layers.Dense(100, activation='relu'),
keras.layers.Dense(10, activation='softmax'),
])
model.compile(loss='sparse_categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
keras.utils.plot_model(model, show_shapes=True)
hist = model.fit(data.to_numpy(), labels.to_numpy(), epochs=20, validation_data=(test.to_numpy(), test_labels.to_numpy()))
The first few outputs are :
Epoch 1/20
625/625 [==============================] - 2s 3ms/step - loss: 2055059923226079526912.0000 - accuracy: 0.1115 - val_loss: 2.4539 - val_accuracy: 0.1134
Epoch 2/20
625/625 [==============================] - 2s 3ms/step - loss: 2.4160 - accuracy: 0.1085 - val_loss: 2.2979 - val_accuracy: 0.1008
Epoch 3/20
625/625 [==============================] - 2s 2ms/step - loss: 2.3006 - accuracy: 0.1110 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 4/20
625/625 [==============================] - 2s 3ms/step - loss: 2.3009 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 5/20
625/625 [==============================] - 2s 3ms/step - loss: 2.3009 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 6/20
625/625 [==============================] - 2s 3ms/step - loss: 2.3008 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 7/20
625/625 [==============================] - 2s 3ms/step - loss: 2.3008 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 8/20
625/625 [==============================] - 2s 3ms/step - loss: 2.3008 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 9/20
625/625 [==============================] - 2s 2ms/step - loss: 2.3008 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 10/20
625/625 [==============================] - 2s 3ms/step - loss: 2.3008 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 11/20
625/625 [==============================] - 2s 3ms/step - loss: 2.3008 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136
Epoch 12/20
625/625 [==============================] - 2s 3ms/step - loss: 2.3008 - accuracy: 0.1121 - val_loss: 2.3014 - val_accuracy: 0.1136

Answer 1

Your loss function should be categorical_crossentrophy. Sparse is for large and mostly empty matrixes(word matrixes etc.). And also instead of data[] you can use data.iloc[]. And adam optimizer would be better in this problem.