Tensorflow gradients are None ('No gradients provided for any variable')

Question

When I run the following script I get the error message 'No gradients provided for any variable'. The 'grads' variable is a list of 'None' values. What is possibly going wrong in such a simple script?

import tensorflow as tf
import numpy as np
tf.enable_eager_execution()


class Model(tf.keras.Model):
    def __init__(self):
        super(Model, self).__init__()
        self.layer = tf.keras.layers.Dense(4, activation = "linear")

    def call(self, x):
        y = self.layer(x)

        return y

model = Model()
model._set_inputs(tf.zeros((1, 5)))

optimizer = tf.train.GradientDescentOptimizer(0.5)


# gibberish data
x_train = np.array([[0, 0, 0, 0, 1]], dtype=np.float32)
y_train = np.array([[0.1, 0.1, 0.4, 0.4]])

y_pred = model.call(x_train)

with tf.GradientTape() as tape:
    loss = tf.losses.mean_squared_error(y_train, y_pred)

grads = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(grads, model.trainable_variables))

Vlad · Accepted Answer · 2019-05-26 11:19:40Z

1

The model prediction line

y_pred = model.call(x_train)

has to be inside the with tf.GradientTape() as tape: scope.

edited May 26, 2019 at 11:19

Vlad

8,6255 gold badges38 silver badges47 bronze badges

answered May 25, 2019 at 20:30

Lazy_Beaver

536 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Tensorflow gradients are None ('No gradients provided for any variable')

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related