Question

我是tensorflow的新手，基本上我将示例复制到了某个地方但无法编译。

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()

这给出了错误：

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

倒数第二行。

但是我尝试过loss.eval()，它表示No default session is registered.，但是如果我写

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

它会导致一些非常复杂的错误。如果我写print(loss.numpy())，它说AttributeError: 'Tensor' object has no attribute 'numpy'

我在Internet上搜索的所有解决方案都要求代码运行tf.Session()，而在此示例中却没有。如何打印loss变量的值？

Answer 1

如果您使用的是tf-1.x，则应首先放置tf.enable_eager_execution()。我只添加了这一行，代码就起作用了。

在此示例中，如何打印tensorflow张量值？

1 个答案: