TensorFlow Tutorial 06 - Save & Load Models

New Tutorial series about TensorFlow 2! Learn all the basics you need to get started with this deep learning framework!

Part 06: Save & Load Models

In this part we learn how we can save and load our model.

~~~~~~~~~~~~~~ GREAT PLUGINS FOR YOUR CODE EDITOR ~~~~~~~~~~~~~~

Get my Free NumPy Handbook:

🚀🚀 Get exclusive content on Patreon: 🚀🚀

If you enjoyed this video, please subscribe to the channel!

Course material is available on GitHub:

Links:

🚀🚀 JOIN MY NEWSLETTER 🚀🚀

You can find me here:

#Python

Course Parts:
01 TensorFlow Installation
02 TensorFlow Tensor Basics
03 TensorFlow Neural Net
04 TensorFlow Linear Regression
05 TensorFlow CNN (Convolutional Neural Nets)
06 TensorFlow Save & Load Models
07 TensorFlow Functional API
08 TensorFlow Multi-output Project
09 TensorFlow Transfer Learning
10 TensorFlow RNN / LSTM / GRU
11 TensorFlow NLP

TensorFlow 2, Keras, Deep Learning, TensorFlow Course, TensorFlow Beginner Course, TensorFlow Tutorial

----------------------------------------------------------------------------------------------------------
* This is a sponsored link. By clicking on it you will not have any additional costs, instead you will support me and my project. Thank you so much for the support! 🙏

[FanaticAuthorship]

total scammer, he didnt explained how to load and predict using pb file

[rudyrachman]

Sir, before I asked, thx for post good video, I wanted to ask if we wanted load model from SavedModel so we only load the pb file there, or maybe have another way?

[canernm]

Hi, thanks for the great video! I have one quick question: if I choose to only save the weights and then load them, what is my next step? I dont think that fitting the model again is required, but how to I utilize these weights? Thanks in advance

[panthpatel]

Is anyone else having issues with load_model() when they save a model that has a custom layer (even tho it extends Layer class)

[taido]

Hello Patrick. Thanks for the great video!

For the save-weight method, when I create a new model with the saved weights and train on the test set, I get an error saying that "You must compile your model before training/testing". I don't think that fitting the model again is required?

[NguyenNam-wksc]

hi, i tried to save the train model but it wasn't worked. The error message is 'FailedPreconditionError: ./models is not a directory' without having this path

[ZOBAER]

Say we are going to save a trained CNN model. Can we save only the trained convolutional base part instead of saving the entire model including the fully connected part? The purpose is mainly to use the convolutional base as pretrained feature extractor and fine tune the fully-connected part. How can we do that?

[thusharmohan]

Thank you for the video! it was really informative :)

So saving our model in which format is the best?

[dutchy]

hi, if I for instance trained a model with 3 features (for stock price prediction), close price, volume and a moving average. The length of the data is the last 20 points. Then when I have saved the model and load it back up can I extract information from the saved model which features have been used and how many data points are used? Assuming I can't remember which features I used to train that particular model. Say I load the model 1 week after I trained it and I do not know or can't remember the features and sequence length I used. How would you retrieve this info? Can it be retrieved from a H5 file? Thanks

[orjihvy]

Which of the 3 method is most often used? I assume saving the entire model.

[TESRG]

Good video, thank you!
Can you explain the issue with the accuracy after loading a saved model? I watched that part a few times and I'm still not sure what you meant with regards to this point. Why and how would I look at accuracy after loading the model? Isn't this something that we track during training?