tlkh / pycon-sg19-tensorflow-tutorial

PyCon SG 2019 Tutorial: Optimizing TensorFlow Performance

PyCon SG 2019 Tutorial: Optimizing TensorFlow Performance

This workshop content covers:

• a brief introduction to deep learning and TensorFlow 2.0
• using tf.data and TensorFlow Datasets
• XLA compiler and Automatic Mixed Precision (AMP)
• speeding up CNN (ResNet-50) with XLA and AMP
• speeding up Transformer (BERT) with XLA and AMP

For a quick guide to using Automatic Mixed Precision, check out this TLDR.

Content

Slides are in this Google Drive folder.

Notebooks

Notebook	Link	Solution
TensorFlow Dataset & tf.data
Pet Classification with TF 2.0
Transformers with TF 2.0

For those running the notebooks on the workshop JupyterHub or on your own hardware, you can clone this repository.

git clone https://github.com/NVAITC/pycon-sg19-tensorflow-tutorial

Workshop Information

In-person @ PyCon SG 2019

• Attend the workshop 10am to 1pm on Saturday, October 12 at Republic Polytechnic.
• Get your tickets here.