Why is the keras model less accurate and not recognized?

I downloaded the mnist dataset (jpg) and created a model file with .hdf (.h5).
Images were recognized using the .h5 model, but the recognition rate is low..
.
The accuracy is low when actual compile..
Did I do something wrong?.
.
The image used the 28x28 image of the grayscale..

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)  

...
...
Epoch 98/100 1257/1257 [==============================] - 3s 2ms/step - loss: 5.5190e-08 - accuracy: 1.0000 - val_loss: 43.3440 - val_accuracy: 0.1135
Epoch 99/100 1257/1257 [==============================] - 3s 2ms/step - loss: 4.0746e-08 - accuracy: 1.0000 - val_loss: 43.3764 - val_accuracy: 0.1136
Epoch 100/100 1257/1257 [==============================] - 3s 2ms/step - loss: 2.3033e-08 - accuracy: 1.0000 - val_loss: 43.4628 - val_accuracy: 0.1136

..
..

Train: [14.343465805053711, 0.7074833512306213]
313/313 [==============================] - 0s 579us/step - loss: 14.7582 - accuracy: 0.6990
Test: [14.758186340332031, 0.6990000009536743]
313/313 [==============================] - 0s 850us/step - loss: 3887.2236 - accuracy: 0.6991
mnist : 0.6991000175476074

https://stackoverflow.com/questions/66468006/why-is-the-keras-model-less-accurate-and-not-recognized March 04, 2021 at 11:08AM