【发布时间】：2020-12-24 05:17:11
【问题描述】：
我是 Tensorflow/Keras 的新手，我一直在关注《使用 Scikit-Learn 和 Tensorflow 进行机器学习实践》一书。第 12 章涉及自定义 Tensorflow，以及相关的笔记本 (here) 我已经找到了以下自定义模型：
class ReconstructingRegressor(keras.models.Model):
def __init__(self, output_dim, **kwargs):
super().__init__(**kwargs)
self.hidden = [keras.layers.Dense(30, activation="selu",
kernel_initializer="lecun_normal")
for _ in range(5)]
self.out = keras.layers.Dense(output_dim)
def build(self, batch_input_shape):
n_inputs = batch_input_shape[-1]
self.reconstruct = keras.layers.Dense(n_inputs)
super().build(batch_input_shape)
def call(self, inputs, training=None):
Z = inputs
for layer in self.hidden:
Z = layer(Z)
reconstruction = self.reconstruct(Z)
recon_loss = tf.reduce_mean(tf.square(reconstruction - inputs))
self.add_loss(0.05 * recon_loss)
return self.out(Z)
当我使用此模型进行训练时，我收到以下错误：
TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
@tf.function
def has_init_scope():
my_constant = tf.constant(1.)
with tf.init_scope():
added = my_constant * 2
The graph tensor has name: mul:0
问题是self.add_loss(0.05 * recon_loss)；在评论说一切运行良好之后。大概recon_loss 是"Graph" tensor 和self.add_loss() 是op outside of the function building code，但是——如果这适用于add_loss()——我不知道我将如何从call() 中增加损失。
完全披露：当我在编写本书时考虑到 2.1 时，我使用的是 Tensorflow 2.3，所以我并没有真正遵循说明。也就是说，我真的很好奇如何解决这个问题，以我目前的知识水平，我觉得基本上无能为力。它似乎应该可以工作——否则如何添加到损失函数中？任何帮助将不胜感激。
完整示例：
import tensorflow as tf
from tensorflow import keras
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
housing = fetch_california_housing()
X_train_full, X_test, y_train_full, y_test = train_test_split(
housing.data, housing.target.reshape(-1, 1), random_state=42)
X_train, X_valid, y_train, y_valid = train_test_split(
X_train_full, y_train_full, random_state=42)
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_valid_scaled = scaler.transform(X_valid)
X_test_scaled = scaler.transform(X_test)
class ReconstructingRegressor(keras.models.Model):
def __init__(self, output_dim, **kwargs):
super().__init__(**kwargs)
self.hidden = [keras.layers.Dense(30, activation="selu",
kernel_initializer="lecun_normal")
for _ in range(5)]
self.out = keras.layers.Dense(output_dim)
def build(self, batch_input_shape):
n_inputs = batch_input_shape[-1]
self.reconstruct = keras.layers.Dense(n_inputs)
super().build(batch_input_shape)
def call(self, inputs, training=None):
Z = inputs
for layer in self.hidden:
Z = layer(Z)
reconstruction = self.reconstruct(Z)
recon_loss = tf.reduce_mean(tf.square(reconstruction - inputs))
self.add_loss(0.05 * recon_loss)
return self.out(Z)
model = ReconstructingRegressor(1, dynamic=True)
model.compile(loss="mse", optimizer="nadam")
history = model.fit(X_train_scaled, y_train, epochs=2)
【问题讨论】：
标签： python tensorflow keras