CODEWITHSUNDEEP
pythontensorflow
seilgu
seilgu

Reputation: 384

How to print tensorflow tensor value in this example?

I'm new to tensorflow and basically I copied the example somewhere but cannot compile it.

import  tensorflow as tf
from    tensorflow.keras import datasets, layers, optimizers, Sequential, metrics

(xs, ys),_ = datasets.mnist.load_data()
print('datasets:', xs.shape, ys.shape, xs.min(), xs.max())

xs = tf.convert_to_tensor(xs, dtype=tf.float32) / 255.
db = tf.data.Dataset.from_tensor_slices((xs,ys))
db = db.batch(32).repeat(10)

network = Sequential([layers.Dense(256, activation='relu'),
    layers.Dense(256, activation='relu'),
    layers.Dense(256, activation='relu'),
    layers.Dense(10)])
network.build(input_shape=(None, 28*28))
network.summary()

optimizer = optimizers.SGD(lr=0.01)
acc_meter = metrics.Accuracy()

for step, (x,y) in enumerate(db):

    with tf.GradientTape() as tape:
        x = tf.reshape(x, (-1, 28*28))
        out = network(x)

        y_onehot = tf.one_hot(y, depth=10)
        loss = tf.square(out-y_onehot)
        loss = tf.reduce_sum(loss) / 32
        acc_meter.update_state(tf.argmax(out, axis=1), y)
        grads = tape.gradient(loss, network.trainable_variables)
        optimizer.apply_gradients(zip(grads, network.trainable_variables))

        if step % 200==0:
            print(float(loss))
            exit()

This gives the error :

TypeError: float() argument must be a string or a number, not 'Tensor'

on the second-last line.

However I've tried loss.eval(), which says No default session is registered. But if I write 

tf.Session() as sess:
    print(sess.run(loss))

it leads to some really complicated error. If I write print(loss.numpy()), it says AttributeError: 'Tensor' object has no attribute 'numpy'

Everything solution I searched on the internet required the code to have a tf.Session() running, which in this example there isn't. How do I print out the value of the loss variable?

Upvotes: 0

Views: 66

Answers (1)

zihaozhihao
zihaozhihao

Reputation: 4475

If you're using tf-1.x, you should put tf.enable_eager_execution() at first. I only add this line and the code works.

Upvotes: 1

Related Questions