在每次迭代训练模型时打印输入

Question

我想检查输入中有什么数据，或者检查某个层的输出。为此，我执行以下操作：

import tensorflow.keras.backend as K
import tensorflow as tf
import numpy as np

x = [[i, i * 3 + 1] for i in range(100)]
y = [2 * i + 1 for i in range(100)]
x = np.array(x)
y = np.array(y)

print_weights = tf.keras.callbacks.LambdaCallback(
    on_batch_end=lambda batch, logs: print(K.get_value(model.layers[1].input)))


def sobaka():
    a = tf.keras.Input(shape=(2,))
    b = tf.keras.layers.Dense(1)
    c = b(a)
    model = tf.keras.models.Model(a, c)
    optimizer = tf.keras.optimizers.Adam(lr=0.1)
    model.compile(loss='mean_squared_error', optimizer=optimizer, metrics=['accuracy'])
    return model


kek = tf.placeholder(tf.float32, shape=(2,))
model = sobaka()
model.fit(x, y, batch_size=1, epochs=2, callbacks=[print_weights])

所以每批（一个训练样本）它都会打印输入张量。但是，我得到一个错误：

You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,2]

请帮助我了解如何在我的代码中放置占位符。是否有任何可能的解决方案来每次迭代打印信息？（例如，当批次为 10 时？）

Answer 1

一种选择是使用[自定义回调][1]

像这样：

class MyCallback(tf.keras.callbacks.Callback):

    def __init__(self, patience=0):
        super(MyCallback, self).__init__()

    def on_epoch_begin(self, epoch, logs=None):
        tf.print(self.model.get_weights())

model.fit(
        x_train, 
        y_train, 
        epochs=epochs,
        batch_size=batch_size,
        callbacks=[MyCallback()],
        validation_data=(x_test, y_test),
    )

在每次迭代训练模型时打印输入

Print input while training model on every iteration

placeholder

python-3.x

keras

tensorflow