如何在张量流中将 TextVectorization 保存到磁盘？

Question

我已经训练了一个 TextVectorization 层（见下文），我想将它保存到磁盘，以便下次重新加载？我试过pickle 和joblib.dump()。它不起作用。

from tensorflow.keras.layers.experimental.preprocessing import TextVectorization 

text_dataset = tf.data.Dataset.from_tensor_slices(text_clean) 
    
vectorizer = TextVectorization(max_tokens=100000, output_mode='tf-idf',ngrams=None)
    
vectorizer.adapt(text_dataset.batch(1024))

生成的错误如下：

InvalidArgumentError: Cannot convert a Tensor of dtype resource to a NumPy array

如何保存？

Answer 1

可以使用一些技巧来做到这一点。构造您的 TextVectorization 对象，然后将其放入模型中。保存模型以保存矢量化器。加载模型将重现矢量化器。请参阅下面的示例。

import tensorflow as tf
from tensorflow.keras.layers.experimental.preprocessing import TextVectorization

data = [
    "The sky is blue.",
    "Grass is green.",
    "Hunter2 is my password.",
]

# Create vectorizer.
text_dataset = tf.data.Dataset.from_tensor_slices(data)
vectorizer = TextVectorization(
    max_tokens=100000, output_mode='tf-idf', ngrams=None,
)
vectorizer.adapt(text_dataset.batch(1024))

# Create model.
model = tf.keras.models.Sequential()
model.add(tf.keras.Input(shape=(1,), dtype=tf.string))
model.add(vectorizer)

# Save.
filepath = "tmp-model"
model.save(filepath, save_format="tf")

# Load.
loaded_model = tf.keras.models.load_model(filepath)
loaded_vectorizer = loaded_model.layers[0]

这是两个矢量化器（原始和加载）产生相同输出的测试。

import numpy as np

np.testing.assert_allclose(loaded_vectorizer("blue"), vectorizer("blue"))

Answer 2

不是腌制对象，而是腌制配置和权重。稍后解开它并使用配置来创建对象并加载保存的权重。官方文档here.

代码

text_dataset = tf.data.Dataset.from_tensor_slices([
                                                   "this is some clean text", 
                                                   "some more text", 
                                                   "even some more text"]) 
# Fit a TextVectorization layer
vectorizer = TextVectorization(max_tokens=10, output_mode='tf-idf',ngrams=None)    
vectorizer.adapt(text_dataset.batch(1024))

# Vector for word "this"
print (vectorizer("this"))

# Pickle the config and weights
pickle.dump({'config': vectorizer.get_config(),
             'weights': vectorizer.get_weights()}
            , open("tv_layer.pkl", "wb"))

print ("*"*10)
# Later you can unpickle and use 
# `config` to create object and 
# `weights` to load the trained weights. 

from_disk = pickle.load(open("tv_layer.pkl", "rb"))
new_v = TextVectorization.from_config(from_disk['config'])
# You have to call `adapt` with some dummy data (BUG in Keras)
new_v.adapt(tf.data.Dataset.from_tensor_slices(["xyz"]))
new_v.set_weights(from_disk['weights'])

# Lets see the Vector for word "this"
print (new_v("this"))

输出：

tf.Tensor(
[[0.         0.         0.         0.         0.91629076 0.
  0.         0.         0.         0.        ]], shape=(1, 10), dtype=float32)
**********
tf.Tensor(
[[0.         0.         0.         0.         0.91629076 0.
  0.         0.         0.         0.        ]], shape=(1, 10), dtype=float32)

Answer 3

借用 @jakub 的模型车辆技巧 - 我无法加载模型 - 我最终通过 JSON 序列化路线进行，如下所示。

注意TextVectorization层需要tensorflow>=2.7，并且需要使用相同的版本来保存和加载层/模型。

所以，从@jakub 的精彩示例开始，

# Save.
model_json = model.to_json()
with open(filepath, "w") as model_json_fh:
    model_json_fh.write(model_json)

# Load.
with open(filepath, 'r') as model_json_fh:
    loaded_model = tf.keras.models.model_from_json(model_json_fh.read())
    vectorization_layer = loaded_model.layers[0]

loaded_model = tf.keras.models.load_model(filepath)
loaded_vectorizer = loaded_model.layers[0]

就是这样。

我不确定一条路线相对于另一条路线的优势。

这也显示了它是如何进行的： https://machinelearningmastery.com/save-load-keras-deep-learning-models

这有助于解决您在旅途中可能遇到的 JSON 错误：

https://github.com/keras-team/keras/issues/6971

Answer 4

如果有人在加载TextVectorization 层的配置时询问自己如何获得dense 张量而不是ragged 张量，请尝试显式设置output_mode。该问题与最近的一个错误有关，其中 output_mode 在来自已保存的配置时未正确设置。

这会产生一个dense 张量：

text_dataset = tf.data.Dataset.from_tensor_slices([
                                                   "this is some clean text", 
                                                   "some more text", 
                                                   "even some more text"]) 
vectorizer = TextVectorization(max_tokens=10, output_mode='int', output_sequence_length = 10)   
vectorizer.adapt(text_dataset.batch(1024))

print(vectorizer("this"))
pickle.dump({'config': vectorizer.get_config(),
             'weights': vectorizer.get_weights()}
            , open("tv_layer.pkl", "wb"))

from_disk = pickle.load(open("tv_layer.pkl", "rb"))
new_vectorizer = TextVectorization(max_tokens=from_disk['config']['max_tokens'],
                                          output_mode='int',
                                          output_sequence_length=from_disk['config']['output_sequence_length'])
new_vectorizer.adapt(tf.data.Dataset.from_tensor_slices(["xyz"]))
new_vectorizer.set_weights(from_disk['weights'])

print(new_vectorizer("this"))

tf.Tensor([5 0 0 0 0 0 0 0 0 0], shape=(10,), dtype=int64)
tf.Tensor([5 0 0 0 0 0 0 0 0 0], shape=(10,), dtype=int64)

这会在加载时产生 ragged 张量：

import tensorflow as tf

text_dataset = tf.data.Dataset.from_tensor_slices([
                                                   "this is some clean text", 
                                                   "some more text", 
                                                   "even some more text"]) 
vectorizer = TextVectorization(max_tokens=10, output_mode='int', output_sequence_length = 10)   
vectorizer.adapt(text_dataset.batch(1024))

print(vectorizer("this"))
pickle.dump({'config': vectorizer.get_config(),
             'weights': vectorizer.get_weights()}
            , open("tv_layer.pkl", "wb"))

from_disk = pickle.load(open("tv_layer.pkl", "rb"))
new_vectorizer = TextVectorization(max_tokens=from_disk['config']['max_tokens'],
                                          output_mode=from_disk['config']['output_mode'],
                                          output_sequence_length=from_disk['config']['output_sequence_length'])
new_vectorizer.adapt(tf.data.Dataset.from_tensor_slices(["xyz"]))
new_vectorizer.set_weights(from_disk['weights'])

print(new_vectorizer("this"))

tf.Tensor([5 0 0 0 0 0 0 0 0 0], shape=(10,), dtype=int64)
tf.Tensor([5], shape=(1,), dtype=int64)