Triplet loss on MNIST using TF tfa.losses.triplet_semihard_loss

mnist_triplet_loss.py

import tensorflow as tf
import tensorflow_addons as tfa
from tensorflow.keras.optimizers import Adam


# load and normalize data
(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()
X_train = X_train.astype('float32')
X_train /= 255.
X_test = X_test.astype('float32')
X_test /= 255.

# reshape input data
X_train = X_train.reshape(
    X_train.shape[0], 28, 28, 1)
X_test = X_test.reshape(
    X_test.shape[0], 28, 28, 1)


def create_model(image_input_shape):

    input_image = tf.keras.layers.Input(shape=image_input_shape)

    x = tf.keras.layers.Conv2D(32,
                                 (3, 3),
                                 input_shape=(28, 28, 1),
                                 activation='relu')(input_image)
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)
    x = tf.keras.layers.Dropout(0.3)(x)
    
    x = tf.keras.layers.Conv2D(64, 3, activation='relu')(x)
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)
    x = tf.keras.layers.Dropout(0.3)(x)
        
    x = tf.keras.layers.Conv2D(128, 3, activation='relu')(x)
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)
    x = tf.keras.layers.Dropout(0.3)(x)
    
    x = tf.keras.layers.Flatten()(x)
    x = tf.keras.layers.Dense(128, activation='relu')(x)
    x = tf.keras.layers.Dense(64)(x)
    x = tf.math.l2_normalize(x, axis=1)
    
    return tf.keras.models.Model(inputs=input_image, outputs=x)         

model = create_model((28, 28, 1))


model.compile(loss=tfa.losses.triplet_semihard_loss, optimizer=Adam(lr=0.001),
              metrics=['accuracy'], weighted_metrics=['accuracy'])



model.fit(X_train, y_train, validation_data=(X_test, y_test),
          epochs=20,
          batch_size=1024,
          shuffle=True)

Hi,
What is the training accuracy that got with this model?