import re
import pickle
import keras
import tensorflow as tf
from keras.models import Sequential
from keras.layers import TFSMLayer
import numpy as np
class CustomNonPaddingTokenLoss(keras.losses.Loss):
def __init__(self, reduction=tf.keras.losses.Reduction.AUTO, name="custom_ner_loss"):
super().__init__(reduction=reduction, name=name)
def call(self, y_true, y_pred):
loss_fn = keras.losses.SparseCategoricalCrossentropy(
from_logits=False, reduction=self.reduction
)
loss = loss_fn(y_true, y_pred)
mask = tf.cast((y_true > 0), dtype=tf.float32)
loss = loss * mask
return tf.reduce_sum(loss) / tf.reduce_sum(mask)
def map_record_to_training_data(record):
record = tf.strings.split(record, sep="\t")
length = tf.strings.to_number(record[0], out_type=tf.int32)
tokens = record[1 : length + 1]
tags = record[length + 1 :]
tags = tf.strings.to_number(tags, out_type=tf.int64)
tags += 1
return tokens, tags
def lookup(tokens):
# Load the list from the file
with open('./resources/vocabulary.pkl', 'rb') as f:
loaded_list = pickle.load(f)
# The StringLookup class will convert tokens to token IDs
lookup_layer = keras.layers.StringLookup(vocabulary=loaded_list)
# No need to lowercase Vietnamese characters
return lookup_layer(tokens)
def format_datatype(data):
tokens = [re.sub(r'[;,]', '', d) for d in data.split(' ')]
#default is 0, since is for prediction
ner_tags = [0 for d in data.split(' ')]
#tab to separate
string_input = str(len(tokens))+ "\t"+ "\t".join(tokens)+ "\t"+ "\t".join(map(str, ner_tags))
string_input = tf.data.Dataset.from_tensor_slices([string_input])
finalize_input = (string_input.map(map_record_to_training_data)
.map(lambda x, y: (lookup(x), y))
.padded_batch(1)
)
return finalize_input
def prediction(data):
# Register the custom loss function with TensorFlow
tf.keras.utils.get_custom_objects()['CustomNonPaddingTokenLoss'] = CustomNonPaddingTokenLoss
loaded_model = Sequential()
loaded_model.add(TFSMLayer("./resources/ner_model", call_endpoint='serving_default'))
all_predicted_tag_ids = []
for x, _ in data:
print("Input Tensor Info:")
print("Data Type:", x.dtype)
print("Shape:", x.shape)
x = tf.cast(x, tf.int64)
output = loaded_model(x, training=False)
predictions = np.argmax(output, axis=-1)
predictions = np.reshape(predictions, [-1])
all_predicted_tag_ids.append(predictions)
all_predicted_tag_ids = np.concatenate(all_predicted_tag_ids)
ner_labels = ["[PAD]", "N", "M", "other"]
mapping = dict(zip(range(len(ner_labels)), ner_labels))
predicted_tags = [mapping[tag] for tag in all_predicted_tag_ids]
return predicted_tags
sample_input = "Hello world, my name is John, I live in New York, my birthday is 10/02/1990."
result = prediction(format_datatype(sample_input))
print(result)
我在 google colab 上训练了模型，然后下载模型并尝试加载到我的窗口电脑上。 *它在谷歌colab上工作正常，即使我重新启动并清除终端并运行这段代码，也没有任何错误。 当我转移到 PC 时，我发现我需要通过很多预先步骤来加载模型，这与 google colab 上的只是 (model = load_model("xxx/xxx"))
我在 TensorFlow 中使用
TFSMLayer---------------------------------------------------------
tensorflow.python.framework.errors_impl.InvalidArgumentError：调用 TFSMLayer.call() 时遇到异常。
无法计算 __inference_signature_wrapper_1285，因为输入 #0（从零开始）预计是 int64 张量，但实际上是浮点张量 [Op:__inference_signature_wrapper_1285]
--------------------------------------------------------
我正在尝试加载一个使用
TFSMLayerTFSMLayer.call()float32int64在将输入张量传递给加载的模型之前，我已经尝试使用
int64tf.cast我不确定为什么输入张量的数据类型被转换为
float32原来可能是tensorflow版本问题。 我尝试在pc（2.16.1）上卸载tensorflow并安装与google colab（2.15.0）相同的版本，原始代码运行顺利。
import re
import pickle
import keras
import tensorflow as tf
import numpy as np
print(tf.__version__)
class CustomNonPaddingTokenLoss(keras.losses.Loss):
def __init__(self, reduction=tf.keras.losses.Reduction.AUTO, name="custom_ner_loss"):
super().__init__(reduction=reduction, name=name)
def call(self, y_true, y_pred):
loss_fn = keras.losses.SparseCategoricalCrossentropy(
from_logits=False, reduction=self.reduction
)
loss = loss_fn(y_true, y_pred)
mask = tf.cast((y_true > 0), dtype=tf.float32)
loss = loss * mask
return tf.reduce_sum(loss) / tf.reduce_sum(mask)
def map_record_to_training_data(record):
record = tf.strings.split(record, sep="\t")
length = tf.strings.to_number(record[0], out_type=tf.int32)
tokens = record[1 : length + 1]
tags = record[length + 1 :]
tags = tf.strings.to_number(tags, out_type=tf.int64)
tags += 1
return tokens, tags
def lookup(tokens):
# Load the list from the file
with open('./resources/vocabulary.pkl', 'rb') as f:
loaded_list = pickle.load(f)
# The StringLookup class will convert tokens to token IDs
lookup_layer = keras.layers.StringLookup(vocabulary=loaded_list)
# No need to lowercase Vietnamese characters
return lookup_layer(tokens)
def format_datatype(data):
tokens = [re.sub(r'[;,]', '', d) for d in data.split(' ')]
#default is 0, since is for prediction
ner_tags = [0 for d in data.split(' ')]
#tab to separate
string_input = str(len(tokens))+ "\t"+ "\t".join(tokens)+ "\t"+ "\t".join(map(str, ner_tags))
string_input = tf.data.Dataset.from_tensor_slices([string_input])
finalize_input = (string_input.map(map_record_to_training_data)
.map(lambda x, y: (lookup(x), y))
.padded_batch(1)
)
return finalize_input
def prediction(data):
# Register the custom loss function with TensorFlow
tf.keras.utils.get_custom_objects()['CustomNonPaddingTokenLoss'] = CustomNonPaddingTokenLoss
loaded_model = tf.keras.models.load_model("./resources/ner_model")
all_predicted_tag_ids = []
for x, _ in data:
print("Input Tensor Info:")
print("Data Type:", x.dtype)
print("Shape:", x.shape)
x = tf.cast(x, tf.int64)
output = loaded_model(x, training=False)
predictions = np.argmax(output, axis=-1)
predictions = np.reshape(predictions, [-1])
all_predicted_tag_ids.append(predictions)
all_predicted_tag_ids = np.concatenate(all_predicted_tag_ids)
ner_labels = ["[PAD]", "N", "M", "other"]
mapping = dict(zip(range(len(ner_labels)), ner_labels))
predicted_tags = [mapping[tag] for tag in all_predicted_tag_ids]
return predicted_tags
sample_input = ""Hello world, my name is John, I live in New York, my birthday is 10/02/1990."
result = prediction(format_datatype(sample_input))
print(result)
print(len(result))