# Miscellaneous

## Checkpoint related

* Comparison:
  * Checkpoint(\*.ckpt)
    * Contains three files normally: `model.ckpt.index` `model.ckpt.meta` `model.ckpt.data-00000-of-00001`
    * Saved by `tf.trainer.Saver().save()`, only save the `tf.Variables()`, not including graph model, thus impossible to recover a whole graph with ckpt only.
    * Use `saver.restore(session, checkpoint_path)` to restore.
  * GraphDef(\*.pb)
    * Contains serialized protobuf data and compute graph, but not Variable data.
    * Can only recover compute graph, need checkpoint to inject data.
    * FrozenGraphDef is slightly different, since it will convert all Variable to constant values(which can be loaded from checkpoint), usually used as pre-train model.
  * SavedModel
    * Combination of checkpoint and GraphDef, plus SignatureDef of input and output variables.

Reference: [TensorFlow 到底有几种模型格式？](https://cloud.tencent.com/developer/article/1009979)

### checkpoint

* Print parameters in checkpoint

1. Using internal tool -- `inspect_checkpoint`:

   ```python
   python -m tensorflow.python.tools.inspect_checkpoint --file_name=model.ckpt "$@"
   ```
2. Using `tf.compat.v1.NewCheckpointReader(ckpt_path)`:

   ```python
   ckpt_path = "./model.ckpt"
   reader = tf.compat.v1.train.NewCheckpointReader(ckpt_path)
   var_to_shape_map = reader.get_variable_to_shape_map()
   for key in var_to_shape_map:
       print(f"{key}: {reader.get_tensor(key)}")
   ```

Reference: [如何打印出TensorFlow保存的checkpoint里的参数名](https://www.codelast.com/%E5%8E%9F%E5%88%9B-%E5%A6%82%E4%BD%95%E6%89%93%E5%8D%B0%E5%87%BAtensorflow%E4%BF%9D%E5%AD%98%E7%9A%84checkpoint%E9%87%8C%E7%9A%84%E5%8F%82%E6%95%B0%E5%90%8D/)

### saved\_model

### pb

### keras h5

Keras save its model in h5 format, so we need to know how to read h5 in python if we only want to search for some specific parameters.

```python
# import related lib
import h5py

# init a file object with only-read permission
f = h5py.File(path_to_h5, 'r')

# list its keys
list(f.keys())

# h5 file can be indexed by keywords
list(f['model_weights'].keys()) 

# indexed into deeper layer
f['model_weights']['dense_73']
# Out: <HDF5 group "/model_weights/dense_73" (1 members)>
# Group means it has children leaves, can be indexed deeper by key

f['model_weights']['dense_73']['dense_73']['kernel:0']
# Out: <HDF5 dataset "kernel:0": shape (768, 22), type "<f4">
# dataset means it can be read now

# dataset can be read as list, numpy, etc.
list(f['model_weights']['dense_73']['dense_73']['bias:0'])

# dataset also has shape
f['model_weights']['dense_73']['dense_73']['kernel:0'].shape
# Out: (768, 22)
```

Reference: [模型复现之HDF5文件](https://blog.csdn.net/qq_33866063/article/details/115788312)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://legacy.cookielau.com/framework/tensorflow/99-misc.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.