[英]How do i convert tensorflow 2.0 estimator model to tensorflow lite?
我在下面的以下代码产生了常规的 tensorflow model 但是当我尝试将其转换为 tensorflow lite 它不起作用时,我遵循了以下文档。
https://www.tensorflow.org/tutorials/estimator/linear 1 https://www.tensorflow.org/lite/guide/get_started
export_dir = "tmp"
serving_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(
tf.feature_column.make_parse_example_spec(feat_cols))
estimator.export_saved_model(export_dir, serving_input_fn)
# Convert the model.
converter = tf.lite.TFLiteConverter.from_saved_model("tmp/1571728920/saved_model.pb")
tflite_model = converter.convert()
错误信息
Traceback (most recent call last):
File "C:/Users/Dacorie Smith/PycharmProjects/JamaicaClassOneNotifableModels/ClassOneModels.py", line 208, in <module>
tflite_model = converter.convert()
File "C:\Users\Dacorie Smith\PycharmProjects\JamaicaClassOneNotifableModels\venv\lib\site-packages\tensorflow_core\lite\python\lite.py", line 400, in convert
raise ValueError("This converter can only convert a single "
ValueError: This converter can only convert a single ConcreteFunction. Converting multiple functions is under development.
从文档中提取
TensorFlow Lite converter The TensorFlow Lite converter is a tool available as a Python API that converts trained TensorFlow models into the TensorFlow Lite format. 它还可以引入优化,第 4 节中介绍了优化 model。
以下示例显示了将 TensorFlow SavedModel 转换为 TensorFlow Lite 格式:
导入 tensorflow 作为 tf
转换器 = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir) tflite_model = converter.convert() open("converted_model.tflite", "wb").write(tflite_model)
尝试使用具体的 function:
export_dir = "tmp"
serving_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(
tf.feature_column.make_parse_example_spec(feat_cols))
estimator.export_saved_model(export_dir, serving_input_fn)
# Convert the model.
saved_model_obj = tf.saved_model.load(export_dir="tmp/1571728920/")
concrete_func = saved_model_obj.signatures['serving_default']
converter = tf.lite.TFLiteConverter.from_concrete_functions([concrete_func])
# print(saved_model_obj.signatures.keys())
# converter.optimizations = [tf.lite.Optimize.DEFAULT]
# converter.experimental_new_converter = True
tflite_model = converter.convert()
serving_default
是 SavedModels 中签名的默认密钥。
如果不起作用,请尝试取消注释converter.experimental_new_converter = True
和它上面的两行。
简短说明
基于具体功能指南
TensorFlow 2 中的急切执行会立即评估操作,而无需构建图表。 要保存 model,您需要包含在 python 可调用对象中的图形:具体函数。
您收到的错误是什么?
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.