Explore the performance of a pre-trained LayoutLMv3 model on unseen document image data in this comprehensive tutorial video. Learn how to upgrade libraries, save the best model, upload and load models from HuggingFace Hub, predict document image classes, and analyze predictions using a confusion matrix. Gain practical insights into document classification using deep learning techniques, with a focus on PyTorch and HuggingFace Transformers libraries.
Evaluate LayoutLMv3 for Document Classification - Save & Load Model to HuggingFace Hub
Overview
Syllabus
- Intro
- Upgrade libraries
- Save the best model
- Upload your model to HuggingFace Hub
- Training metrics
- Load your model from HuggingFace Hub
- Predict the class of a document image
- Explore predictions using a confusion matrix
- Conclusion
Taught by
Venelin Valkov
Related Courses
-
Fine Tune BERT for Text Classification with TensorFlow
-
Deep Learning with Keras and Practical Applications
-
Building and Training Neural Networks with PyTorch
-
Create a Large Language Model from Scratch with Python – Tutorial
-
Understand data science for machine learning
-
Machine Learning: Classification
4.8
Related articles
Reviews
4.0 rating, based on 1 Class Central review
-
This course is a great introduction to the basics of machine learning, including how to upgrade and save libraries, how to train and measure models, and how to upload trained models to HuggingFace Hub. The instructor does a great job of explaining the concepts in a clear and concise way, and the course is well-organized and easy to follow.
One of the things I really liked about this course was the way the instructor demonstrated key steps and techniques towards using a model to predict the class of a document image. He showed how to use a confusion matrix to explore the accuracy of predictions, and he also provided a lot of helpful tips and tricks along the way.
