[英]How do i convert tensorflow 2.0 estimator model to tensorflow lite?
我在下面的以下代碼產生了常規的 tensorflow model 但是當我嘗試將其轉換為 tensorflow lite 它不起作用時,我遵循了以下文檔。
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()
錯誤信息
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.
從文檔中提取
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. 它還可以引入優化,第 4 節中介紹了優化 model。
以下示例顯示了將 TensorFlow SavedModel 轉換為 TensorFlow Lite 格式:
導入 tensorflow 作為 tf
轉換器 = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir) tflite_model = converter.convert() open("converted_model.tflite", "wb").write(tflite_model)
嘗試使用具體的 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 中簽名的默認密鑰。
如果不起作用,請嘗試取消注釋converter.experimental_new_converter = True
和它上面的兩行。
簡短說明
基於具體功能指南
TensorFlow 2 中的急切執行會立即評估操作,而無需構建圖表。 要保存 model,您需要包含在 python 可調用對象中的圖形:具體函數。
您收到的錯誤是什么?
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.