在CloudML的在线预测服务的alpha版本中,导出模型的格式为:
inputs = {"x": x, "y_bytes": y}
g.add_to_collection("inputs", json.dumps(inputs))
outputs = {"a": a, "b_bytes": b}
g.add_to_collection("outputs", json.dumps(outputs))
我想将此转换为SavedModel而不重新训练我的模型。我怎么能这样做?
答案 0 :(得分:1)
我们可以通过导入旧模型,创建签名并重新导出它来将其转换为SavedModel。此代码未经测试,但这样的代码应该有效:
import json
import tensorflow as tf
from tensorflow.contrib.session_bundle import session_bundle
# Import the "old" model
session, _ = session_bundle.load_session_bundle_from_path(export_dir)
# Define the inputs and the outputs for the SavedModel
old_inputs = json.loads(tf.get_collection('inputs'))
inputs = {name: tf.saved_model.utils.build_tensor_info(tensor)
for name, tensor in old_inputs}
old_outputs = json.loads(tf.get_collection('outputs'))
outputs = {name: tf.saved_model.utils.build_tensor_info(tensor)
for name, tensor in old_outputs}
signature = tf.saved_model.signature_def_utils.build_signature_def(
inputs=inputs,
outputs=outputs,
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME
)
# Save out the converted model
b = builder.SavedModelBuilder(new_export_dir)
b.add_meta_graph_and_variables(session,
[tf.saved_model.tag_constants.SERVING],
signature_def_map={'serving_default': signature})
b.save()