Невозможно уменьшить значение val_loss при обучении компьютерному зрению

import cv2
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D
from keras.utils import to_categorical
import os
import tensorflow as tf
from sklearn.utils.class_weight import compute_class_weight
from sklearn.model_selection import train_test_split
 
classes = 5
 
# Функция для загрузки и предобработки изображений из папки
def load_images_from_folder(folder):
    images = []
    labels = []
    class_names = os.listdir(folder)
    for class_name in class_names:
        class_path = os.path.join(folder, class_name)
        for filename in os.listdir(class_path):
            img = cv2.imread(os.path.join(class_path, filename))
            if img is not None:
                img = cv2.resize(img, (32, 32))  # Изменение размера до 64x64
                img = img.astype('float32') / 255
                images.append(img)
                labels.append(class_names.index(class_name))
    return np.array(images), to_categorical(np.array(labels), classes), labels
 
# Load and preprocess images from the dataset folder
dataset_folder = 'E:\\MSHI_2_KYRS_2_SIM\\5.v5\\dataset\\train'
x_train, y_train, y_labels = load_images_from_folder(dataset_folder)
 
# Split data into training and testing sets
x_train, x_test, y_train, y_test = train_test_split(x_train, y_train, test_size=0.3, random_state=42)
 
# Calculate class weights
class_weights = dict(enumerate(compute_class_weight(class_weight='balanced', classes=np.unique(y_labels), y=y_labels)))
 
# Create and compile the model
 
# Create and compile the model with weighted loss
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(5, activation='softmax'))
 
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
 
 
# Train the model with class weights
model.fit(x_train, y_train, batch_size=32, epochs=50, verbose=1, validation_data=(x_test, y_test), class_weight=class_weights)
 
 
# Save and load the model as before
 
# Save the model
save_path = 'E:\\MSHI_2_KYRS_2_SIM\\5.v5\\my_model.keras'
model.save(save_path)
 
# Load the model
loaded_model = tf.keras.models.load_model(save_path)
 
# Load and preprocess an image for prediction
img_path = 'E:\\MSHI_2_KYRS_2_SIM\\5.v5\\dataset\\train\\healthy\\20220101_085747_jpg.rf.8e8f3a8931b9f5a43b77e87937b875a7.jpg'
img = cv2.imread(img_path)
img = cv2.resize(img, (32, 32))
img = img.astype('float32') / 255
img = np.expand_dims(img, axis=0)
 
# Make predictions using the loaded model
predictions = loaded_model.predict(img)
class_names = ['algal', 'brown_blight', 'gray_blight', 'healthy', 'red_spot']
predicted_class = np.argmax(predictions)
predicted_class_name = class_names[predicted_class]
predicted_prob = predictions[0][predicted_class]
 
print('Predicted class:', predicted_class_name)
print('Probability:', predicted_prob)