如何在不重新训练模型的情况下更改SavedModel的签名? [英] How do I change the Signatures of my SavedModel without retraining the model?

问题描述

我刚刚完成模型训练，只是发现我导出了一个服务签名模型存在问题的模型.如何更新它们?

I just finished training my model only to find out that I exported a model for serving that had problems with the signatures. How do I update them?

(一个常见的问题是为CloudML Engine设置了错误的形状).

(One common problem is setting the wrong shape for CloudML Engine).

推荐答案

不用担心-您不需要重新训练模型.就是说，还有一点工作要做.您将要创建一个新的(更正后的)投放图表，将检查点加载到该图表中，然后导出该图表.

Don't worry -- you don't need to retrain your model. That said, there is a little work to be done. You're going to create a new (corrected) serving graph, load the checkpoints into that graph, and then export this graph.

例如，假设您添加了一个占位符，但没有设置形状，即使您打算这样做(例如，在CloudML上运行).在这种情况下，您的图形可能看起来像:

For example, suppose you add a placeholder, but didn't set the shape, even though you meant to (e.g., to run on CloudML). In that case, your graph may have looked like:

x = tf.placeholder(tf.float32)
y = foo(x)
...

要纠正此问题:

# Create the *correct* graph
with tf.Graph().as_default() as new_graph:
  x = tf.placeholder(tf.float32, shape=[None])
  y = foo(x)
  saver = tf.train.Saver()

# (Re-)define the inputs and the outputs.
inputs = {"x": tf.saved_model.utils.build_tensor_info(x)}
outputs = {"y": tf.saved_model.utils.build_tensor_info(y)}
signature = tf.saved_model.signature_def_utils.build_signature_def(
    inputs=inputs,
    outputs=outputs,
    method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME
)

with tf.Session(graph=new_graph) as session:
  # Restore the variables
  vars_path = os.path.join(old_export_dir, 'variables', 'variables')
  saver.restore(session, vars_path)

  # Save out the corrected model
  b = builder.SavedModelBuilder(new_export_dir)
  b.add_meta_graph_and_variables(session, ['serving_default'], signature)
  b.save()

这篇关于如何在不重新训练模型的情况下更改SavedModel的签名?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！