Keras model evaluate returns triggered tf.function retracing warning


I am training the following model using Keras as shown:

model = tf.keras.models.Sequential([tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(256, 256, 3)),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
tf.keras.layers.Dense(12, activation=tf.nn.relu),
tf.keras.layers.Dense(10, activation=tf.nn.relu),
tf.keras.layers.Dense(1, activation=tf.sigmoid)])

model.compile(optimizer = tf.keras.optimizers.Adam(learning_rate=0.0001),loss,'binary_crossentropy, metrics=['accuracy']), y_train, epochs=20)

When running the following to check the accuracy on the test set


I get the following warning:

WARNING:tensorflow:5 out of the last 13 calls to .test_function at 0x000001E51AA92AE8> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to and for more details. 2/2 [==============================] - 0s 94ms/step - loss: 0.6660 - accuracy: 0.5909

Can you please help me understand why?

Why should this post be closed?


0 answers

Sign up to answer this question »