Does structural pruning support pre-trained model?

System information

• TensorFlow version (you are using):
• Are you willing to contribute it (Yes/No):

Motivation

What is the use case and how does it broadly benefits users? Prioritization and whether a feature is added is based on how it
helps the community and the feature's maintenance costs.

As examples:

1. Instead of, "Enable the technique for my model," "Enable this technique to work better with standard object detection models, including R-CNN (link) and SSD (link)" is stronger.

2. Instead of, "Try something more customized with the technique," "Implement a variant of the algorithm described in equations X and Y of this paper" is clearer.

Does structural pruning support pre-trained model?

I saw Tensorflow tutorial for structural pruning, but it is used for model from scratch. It means that we need to specify pruning configuration in the model building. But it is not the case in practice.

Describe how existing APIs don't satisfy your use case (optional if obvious)

As examples:

1. You tried using APIs X and Y and were able to do Z. However, that was not sufficient because of ...

2. You achieved your use case with the code snippet W. However, this was more difficult than it should be because of ... (e.g. ran into issue X or had
   to do Y).

No source file, test, or entry point is named. Start by reviewing the referenced TensorFlow structural-pruning tutorial and compare its from-scratch configuration with the pre-trained-model use case; done requires a clarified, reproducible request and an agreed scope for API support.