Dear Krah Kouadio ,

n multilabel classification, in contrast to binary and multiclass classification, the deep learning model predicts the probability of each class.

https://www.mathworks.com/help/deeplearning/ug/multilabel-image-classification-using-deep-learning.html

Regards,

Shafagat

# Cargar las librerías necesarias

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense, Conv2D, Flatten

import numpy as np

from tensorflow.keras.datasets import mnist

from tensorflow.keras.utils import to_categorical

# Cargar los datos de MNIST

(X_train, y_train), (X_test, y_test) = mnist.load_data()

# Preprocesar los datos

X_train = X_train.reshape(60000, 28, 28, 1)

X_test = X_test.reshape(10000, 28, 28, 1)

X_train = X_train.astype('float32')

X_test = X_test.astype('float32')

X_train /= 255

X_test /= 255

num_classes = 10

y_train = to_categorical(y_train, num_classes)

y_test = to_categorical(y_test, num_classes)

# Crear el modelo CNN

model = Sequential()

model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))

model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))

model.add(Flatten())

model.add(Dense(num_classes, activation='softmax'))

# Entrenar el modelo

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

model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=5)

# Evaluar el modelo

test_loss, test_acc = model.evaluate(X_test, y_test)

print('Test accuracy:', test_acc)