CNN model gives accuracy 0f 63% on Validation Images but when predicted on the same validation set, accuracy is 36%

when fitting the CNN model,

training accuracy = 68%

validation accuracy = 63%

but when I try to evaluate the same CNN model with the same validation data and training data the results are,

Training Loss 1.86870 Training Accuracy = 36.16%

Val Loss 1.89060 val Accuracy = 36.54%

Testing Loss 1.86273 Testing Accuracy = 36.36%

There is a big gap between these accuracies. What can be the reason behind this? The CNN model:

import tensorflow as tf
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Activation ,Dropout, Normalization, AveragePooling2D, BatchNormalization
from tensorflow.keras.optimizers import Adam, Adamax
from tensorflow.python.keras import regularizers

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(height, width, 3), padding='same', activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2)))
model.add(Conv2D(32, (3, 3), input_shape=(height, width, 3), padding='same', activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2)))
model.add(Conv2D(32, (3, 3), input_shape=(height, width, 3), padding='same', activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2)))
model.add(Conv2D(32, (3, 3), input_shape=(height, width, 3), padding='same', activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2)))
model.add(Conv2D(64, (3, 3), padding='same', activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2)))
model.add(Dropout(.2))
model.add(Conv2D(64, (3, 3), padding='same', activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2)))
model.add(Dropout(.2))
model.add(Conv2D(64, (3, 3), padding='same', activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2)))
model.add(Dropout(.2))
model.add(Conv2D(64, (3, 3), padding='same', activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), padding='same', strides=(2)))
model.add(Flatten())  # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(256, activation="relu"))
model.add(BatchNormalization())
model.add(Dropout(.5))
model.add(Dense(126, activation="relu"))
model.add(BatchNormalization())
model.add(Dropout(.5))
model.add(Dense(4,activation='softmax'))

Adam(learning_rate=0.001, name='Adam')
model.compile(optimizer = 'Adam',loss = 'categorical_crossentropy',metrics = ['accuracy'])

epochs = 50
from tensorflow.keras import callbacks
import time
import keras
from keras.callbacks import EarlyStopping
es_callback = keras.callbacks.EarlyStopping(monitor='val_accuracy', patience=20)

datagen = ImageDataGenerator(
        horizontal_flip=True,  
        vertical_flip=True,
        featurewise_std_normalization=True,
        samplewise_std_normalization=True
        )  

checkpoint = callbacks.ModelCheckpoint(
                                       filepath='/content/drive/MyDrive/model.{epoch:02d}-{accuracy:.2f}-{val_accuracy:.2f}.h5',
                                       monitor='val_accuracy',
                                       verbose=1,
                                       save_best_only=True,
                                       mode='auto'
                                       )

datagen.fit(X_train)
history5 = model.fit(datagen.flow(X_train,y_train, batch_size=batch_size),
                              epochs = epochs, validation_data = datagen.flow(X_val,y_val, batch_size=batch_size),
                              callbacks=[ checkpoint]
                              )

stop = time.time()