Tensorflow (.pb) format to Keras (.h5)

by

In the Latest Tensorflow Version (2.2), when we Save the Model using tf.keras.models.save_model, the Model will be Saved in not just a pb file but it will be Saved in a Folder, which comprises Variables Folder and Assets Folder, in addition to the saved_model.pb file, as shown in the screenshot below:

Saved Model Folder

For example, if the Model is Saved with the Name, "Model", we have to Load using the Name of the Folder, “Model”, instead of saved_model.pb, as shown below:

loaded_model = tf.keras.models.load_model('Model')

instead of

loaded_model = tf.keras.models.load_model('saved_model.pb')

One more change you can do is to replace

tf.keras.models.save_keras_model

with

tf.keras.models.save_model

Complete working Code to convert a Model from Tensorflow Saved Model Format (pb) to Keras Saved Model Format (h5) is shown below:

import os
import tensorflow as tf
from tensorflow.keras.preprocessing import image

New_Model = tf.keras.models.load_model('Dogs_Vs_Cats_Model') # Loading the Tensorflow Saved Model (PB)
print(New_Model.summary())

Output of the New_Model.summary command is:

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 148, 148, 32)      896       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 74, 74, 32)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 72, 72, 64)        18496     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 36, 36, 64)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 34, 34, 128)       73856     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 17, 17, 128)       0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 15, 15, 128)       147584    
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 7, 7, 128)         0         
_________________________________________________________________
flatten (Flatten)            (None, 6272)              0         
_________________________________________________________________
dense (Dense)                (None, 512)               3211776   
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 513       
=================================================================
Total params: 3,453,121
Trainable params: 3,453,121
Non-trainable params: 0
_________________________________________________________________
None

Continuing the code:

# Saving the Model in H5 Format and Loading it (to check if it is same as PB Format)
tf.keras.models.save_model(New_Model, 'New_Model.h5') # Saving the Model in H5 Format

loaded_model_from_h5 = tf.keras.models.load_model('New_Model.h5') # Loading the H5 Saved Model
print(loaded_model_from_h5.summary())

Output of the command, print(loaded_model_from_h5.summary()) is shown below:

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 148, 148, 32)      896       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 74, 74, 32)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 72, 72, 64)        18496     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 36, 36, 64)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 34, 34, 128)       73856     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 17, 17, 128)       0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 15, 15, 128)       147584    
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 7, 7, 128)         0         
_________________________________________________________________
flatten (Flatten)            (None, 6272)              0         
_________________________________________________________________
dense (Dense)                (None, 512)               3211776   
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 513       
=================================================================
Total params: 3,453,121
Trainable params: 3,453,121
Non-trainable params: 0
_________________________________________________________________

​
As can be seen from the Summary of both the Models above, both the Models are same.

More Related Contents:

  1. Keras, Tensorflow : Merge two different model output into one
  2. How to add attention layer to a Bi-LSTM
  3. How to apply gradient clipping in TensorFlow?
  4. Keras custom loss function: Accessing current input pattern
  5. How can I use a pre-trained neural network with grayscale images?
  6. Removing then Inserting a New Middle Layer in a Keras Model
  7. ImportError: libcublas.so.9.0: cannot open shared object file
  8. Can’t save custom subclassed model
  9. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  10. Choosing number of Steps per Epoch
  11. Make a custom loss function in keras
  12. Could not load dynamic library ‘cudart64_101.dll’ on tensorflow CPU-only installation
  13. Keras : How should I prepare input data for RNN?
  14. Why does loading tensorflow on Mac lead to “Process finished with exit code 132 (interrupted by signal 4: SIGILL)”?
  15. What is the meaning of the “None” in model.summary of KERAS?
  16. Keras replacing input layer
  17. Hyperparameter optimization for Deep Learning Structures using Bayesian Optimization
  18. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  19. How to understand the term `tensor` in TensorFlow?
  20. ResNet: 100% accuracy during training, but 33% prediction accuracy with the same data
  21. How to know if underfitting or overfitting is occuring?
  22. Custom loss function in Keras
  23. Save and load model optimizer state
  24. Is deep learning bad at fitting simple non linear functions outside training scope (extrapolating)?
  25. Obtaining output of an Intermediate layer in TensorFlow/Keras
  26. How do I get the weights of a layer in Keras?
  27. Keras: model.evaluate vs model.predict accuracy difference in multi-class NLP task
  28. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  29. How do I plot a Keras/Tensorflow subclassing API model?
  30. Strange behaviour of the loss function in keras model, with pretrained convolutional base

Leave a Comment