似乎过去在不同的上下文here中发生了错误，但我没有直接转储模型 - 我正在使用ModelCheckpoint回调。知道会出现什么问题吗？
信息：
重现错误的最小示例：
from keras.layers import Input, Lambda, Dense
from keras.models import Model
from keras.callbacks import ModelCheckpoint
from keras.optimizers import Adam
import tensorflow as tf
import numpy as np
x = Input(shape=(30,3))
low = tf.constant(np.random.rand(30, 3).astype('float32'))
high = tf.constant(1 + np.random.rand(30, 3).astype('float32'))
clipped_out_position = Lambda(lambda x, low, high: tf.clip_by_value(x, low, high),
arguments={'low': low, 'high': high})(x)
model = Model(inputs=x, outputs=[clipped_out_position])
optimizer = Adam(lr=.1)
model.compile(optimizer=optimizer, loss="mean_squared_error")
checkpoint = ModelCheckpoint("debug.hdf", monitor="val_loss", verbose=1, save_best_only=True, mode="min")
training_callbacks = [checkpoint]
model.fit(np.random.rand(100, 30, 3), [np.random.rand(100, 30, 3)], callbacks=training_callbacks, epochs=50, batch_size=10, validation_split=0.33)
错误输出：
Train on 67 samples, validate on 33 samples
Epoch 1/50
10/67 [===>..........................] - ETA: 0s - loss: 0.1627Epoch 00001: val_loss improved from inf to 0.17002, saving model to debug.hdf
Traceback (most recent call last):
File "debug_multitask_inverter.py", line 19, in <module>
model.fit(np.random.rand(100, 30, 3), [np.random.rand(100, 30, 3)], callbacks=training_callbacks, epochs=50, batch_size=10, validation_split=0.33)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/site-packages/keras/engine/training.py", line 1631, in fit
▽
validation_steps=validation_steps)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/site-packages/keras/engine/training.py", line 1233, in _fit_loop
callbacks.on_epoch_end(epoch, epoch_logs)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/site-packages/keras/callbacks.py", line 73, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/site-packages/keras/callbacks.py", line 414, in on_epoch_end
self.model.save(filepath, overwrite=True)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/site-packages/keras/engine/topology.py", line 2556, in save
save_model(self, filepath, overwrite, include_optimizer)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/site-packages/keras/models.py", line 107, in save_model
'config': model.get_config()
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/site-packages/keras/engine/topology.py", line 2397, in get_config
return copy.deepcopy(config)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 215, in _deepcopy_list
append(deepcopy(a, memo))
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 180, in deepcopy
y = _reconstruct(x, memo, *rv)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 280, in _reconstruct
state = deepcopy(state, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 150, in deepcopy
y = copier(x, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 240, in _deepcopy_dict
y[deepcopy(key, memo)] = deepcopy(value, memo)
File "/om/user/lnj/openmind_env/tensorflow-gpu/lib/python3.6/copy.py", line 169, in deepcopy
rv = reductor(4)
TypeError: can't pickle _thread.lock objects
答案 0 :(得分：11)
保存Lambda图层时，也会保存传入的arguments。在这种情况下，它包含两个tf.Tensor s。似乎Keras现在不支持在模型配置中序列化tf.Tensor。
但是，numpy数组可以毫无问题地序列化。因此，不是在tf.Tensor中传递arguments，而是传入numpy数组，并将它们转换为lambda函数中的tf.Tensor。
x = Input(shape=(30,3))
low = np.random.rand(30, 3)
high = 1 + np.random.rand(30, 3)
clipped_out_position = Lambda(lambda x, low, high: tf.clip_by_value(x, tf.constant(low, dtype='float32'), tf.constant(high, dtype='float32')),
arguments={'low': low, 'high': high})(x)
上述行的一个问题是，在尝试加载此模型时，您可能会看到NameError: name 'tf' is not defined。那是因为TensorFlow没有导入重建Lambda图层的文件（core.py）。
将tf更改为K.tf可以解决问题。另外，您可以tf.constant()替换K.constant()，low会自动将high和from keras import backend as K
x = Input(shape=(30,3))
low = np.random.rand(30, 3)
high = 1 + np.random.rand(30, 3)
clipped_out_position = Lambda(lambda x, low, high: K.tf.clip_by_value(x, K.constant(low), K.constant(high)),
arguments={'low': low, 'high': high})(x)
转换为float32张量。
public static void main(String[] args)
{
String[] test = {"this", "is", "the", "example", "of", "the", "call"};
String[] result = removeFromArray(test, "the");
System.out.println(Arrays.toString(result));
}
public static String[] removeFromArray(String[] arr, String toRemove)
{
int newLength = 0;
for(int i = 0; i < arr.length; i++)
{
if(arr[i].contains(toRemove))
{
newLength++;
}
}
String[] result = new String[arr.length-newLength];
for(int i = 0; i < (result.length); i++)
{
if(arr[i].contains(toRemove))
{
}
else
{
result[i] = arr[i];
}
}
return result;
}
答案 1 :(得分：1)
在https://github.com/keras-team/keras/issues/8343#issuecomment-470376703上查看我的帖子。
引发此异常是因为您尝试序列化tf.tensor，因此避免该序列化的任何方法都可以使用。包括：
不序列化：仅保存模型权重，因为当您尝试使用json / yaml字符串保存模型结构时，会发生序列化。
消除张量流张量：确保模型中的每个张量均由keras层生成。或尽可能使用ndarray数据，就像@ Yu-Yang建议的一样。
答案 2 :(得分：1)
要澄清一下：这不是不是的问题，Keras无法在Lambda层中腌制张量（其他情况，请参见在下面的），而是尝试将python函数（此处为lambda函数）的参数独立于该函数（此处为lambda函数本身的上下文之外）进行序列化。这适用于“静态”参数，但否则失败。为了避免这种情况，应该将非静态函数参数包装在另一个函数中。
以下是两种解决方法：
low = np.random.rand(30, 3)
high = 1 + np.random.rand(30, 3)
x = Input(shape=(30,3))
clipped_out_position = Lambda(lambda x: tf.clip_by_value(x, low, high))(x)
functools.partial包装lambda函数：import functools
clip_by_value = functools.partial(
tf.clip_by_value,
clip_value_min=low,
clip_value_max=high)
x = Input(shape=(30,3))
clipped_out_position = Lambda(lambda x: clip_by_value(x))(x)
low = tf.constant(np.random.rand(30, 3).astype('float32'))
high = tf.constant(1 + np.random.rand(30, 3).astype('float32'))
def clip_by_value(t):
return tf.clip_by_value(t, low, high)
x = Input(shape=(30,3))
clipped_out_position = Lambda(lambda x: clip_by_value(x))(x)
通知：尽管您有时可以放弃创建显式lambda函数，而使用以下更简洁的代码段：
clipped_out_position = Lambda(clip_by_value)(x)
缺少lambda函数的额外包装层（即 lambda t: clip_by_value(t)）在执行“时，可能仍然导致相同的问题”函数参数的“深层复制”，应避免 。
x = Input(shape=(30,3))
low = Lambda(lambda t: tf.constant(np.random.rand(30, 3).astype('float32')))(x)
high = Lambda(lambda t: tf.constant(1 + np.random.rand(30, 3).astype('float32')))(x)
clipped_out_position = Lambda(lambda x: tf.clip_by_value(*x))((x, low, high))
通知： tf.clip_by_value(*x) 在最后一个Lambda层中只是一个未打包的参数元组，也可以用更详细的形式编写 tf.clip_by_value(x[0], x[1], x[2])代替。
（在下面）：请注意：在这种情况下，您的lambda函数试图捕获类实例的一部分（该实例也将破坏序列化）（由于{{ 3}}）：
class MyModel:
def __init__(self):
self.low = np.random.rand(30, 3)
self.high = 1 + np.random.rand(30, 3)
def run(self):
x = Input(shape=(30,3))
clipped_out_position = Lambda(lambda x: tf.clip_by_value(x, self.low, self.high))(x)
model = Model(inputs=x, outputs=[clipped_out_position])
optimizer = Adam(lr=.1)
model.compile(optimizer=optimizer, loss="mean_squared_error")
checkpoint = ModelCheckpoint("debug.hdf", monitor="val_loss", verbose=1, save_best_only=True, mode="min")
training_callbacks = [checkpoint]
model.fit(np.random.rand(100, 30, 3),
[np.random.rand(100, 30, 3)], callbacks=training_callbacks, epochs=50, batch_size=10, validation_split=0.33)
MyModel().run()
可以通过以下默认参数技巧来确保尽早绑定：
(...)
clipped_out_position = Lambda(lambda x, l=self.low, h=self.high: tf.clip_by_value(x, l, h))(x)
(...)