我尝试使用以下代码将 Keras 文件 (.h5) 中的模型转换为 TensorFlow Lite 文件 (.tflite):
# Save model as .h5 keras file
keras_file = "eSleep.h5"
model_save = tf.keras.models.save_model(model,keras_file,overwrite=True,include_optimizer=True)
# Export keras file to TensorFlow Lite model
converter = tf.lite.TFLiteConverter.from_keras_model_file(keras_file)
tflite_model = converter.convert()
open("eSleep.tflite", "wb").write(tflite_model)
但是,以下行:
tflite_model = converter.convert()
返回错误:
I tensorflow/core/grappler/devices.cc:53] Number of eligible GPUs (core count >= 8): 0 (Note: TensorFlow was not compiled with CUDA support)
I tensorflow/core/grappler/clusters/single_machine.cc:359] Starting new session
E tensorflow/core/grappler/grappler_item_builder.cc:636] Init node dense/kernel/Assign doesn't exist in graph
任何人都可以帮助我理解“图中不存在初始化节点密集/内核/分配”的含义以及如何修复错误吗?
最佳答案
根据我的经验,即使显示此错误,转换后的模型也应该可以正常工作。您可以忽略该错误。
关于TensorFlow Lite : Init node doesn't exist,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/54122044/