为什么 keras 模型不准确，不被识别？

Question

我下载了 mnist 数据集 (jpg) 并使用 .hdf (.h5) 创建了一个模型文件。
使用.h5模型识别图片，但识别率低..
.
实际编译时精度偏低..
我是不是做错了什么？.
.
图片使用了灰度的28x28图片..

import os
import cv2
import numpy as np
import tensorflow as tf
from PIL import Image
from matplotlib import pyplot as plt
import matplotlib.image as mpimg
import random

FILENAME = 'model.h5'

WIDTH = 28
HEIGHT = 28
EPOCHES = 100
BATCH_SIZE = 32

def create_dataset(img_folder):
    img_data_array=[]
    class_name=[]
   
    for path in os.listdir(img_folder):
        if path == ".DS_Store":
            continue
        for file in os.listdir(os.path.join(img_folder, path)):
            if file == ".DS_Store":
                continue
            image_path = os.path.join(img_folder, path,  file)

            image = cv2.imread( image_path, cv2.IMREAD_UNCHANGED)


            image = cv2.resize(image, (HEIGHT, WIDTH),interpolation = cv2.INTER_AREA)
            image = np.array(image)
            
            image = image.astype('float32')
            image /= 255 
            img_data_array.append(image)
            class_name.append(path)
    return img_data_array, class_name

img_data, class_name = create_dataset(r'/Users/animalman/Documents/test/grayscale/train')
test, test_class_name = create_dataset(r'/Users/animalman/Documents/test/grayscale/test')

target_dict = {k: v for v, k in enumerate(np.unique(class_name))}
target_val = [target_dict[class_name[i]] for i in range(len(class_name))]

test_dict = {k: v for v, k in enumerate(np.unique(test_class_name))}
test_val = [test_dict[test_class_name[i]] for i in range(len(test_class_name))]

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28)),
    tf.keras.layers.Dense(512, activation=tf.nn.relu),
    tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# tensor
history = model.fit(x=tf.cast(np.array(img_data), tf.float64), y=tf.cast(list(map(int,target_val)),tf.int32), epochs=EPOCHES, batch_size=BATCH_SIZE, validation_split=0.33)

evaluate = model.evaluate(x=tf.cast(np.array(img_data), tf.float64), y=tf.cast(list(map(int,target_val)),tf.int32), batch_size=BATCH_SIZE)
print('Train:', evaluate)

test_evaluate = model.evaluate(x=tf.cast(np.array(test), tf.float64), y=tf.cast(list(map(int,test_val)),tf.int32), batch_size=BATCH_SIZE)
print('Test:', test_evaluate)

mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()

test_loss, test_acc = model.evaluate(x_test, y_test)
print('mnist', test_acc)


model.save(FILENAME)

...
...
纪元 98/100 1257/1257 [==============================] - 3 秒 2 毫秒/步 - 损失：5.5190e-08 - 精度： 1.0000 - val_loss: 43.3440 - val_accuracy: 0.1135
时代 99/100 1257/1257 [==============================] - 3 秒 2 毫秒/步 - 损失：4.0746e-08 - 精度： 1.0000 - val_loss: 43.3764 - val_accuracy: 0.1136
时代 100/100 1257/1257 [==============================] - 3 秒 2 毫秒/步 - 损失：2.3033e-08 - 精度： 1.0000 - val_loss: 43.4628 - val_accuracy: 0.1136

..
..

火车：[14.343465805053711，0.7074833512306213]
313/313 [==============================] - 0s 579us/步 - 损失：14.7582 - 精度：0.6990
测试：[14.758186340332031, 0.6990000009536743]
313/313 [==============================] - 0s 850us/步 - 损失：3887.2236 - 精度：0.6991
mnist：0.6991000175476074

Answer 1

从这里开始

Epoch 100/100 1257/1257 [==============================] - 3s 2ms/step - loss: 2.3033e-08 - accuracy: 1.0000 - val_loss: 43.4628 - val_accuracy: 0.1136

你可以看到训练acc是1.0，验证acc是0.1136

-> 您的模型 过度拟合 训练数据集。

关于过拟合：https://en.wikipedia.org/wiki/Overfitting

为什么 keras 模型不准确，不被识别？

Why is the keras model less accurate and not recognized?

conv-neural-network

keras

tensorflow