git clone https://github.com/bozcani/TensorFlow2-tutorial
cd TensorFlow2-tutorial
conda create -n tensorflow2.0-practice python=3.7
conda activate tensorflow2.0-practice
pip install tf-nightly-gpu-2.0-preview==2.0.0.dev20190526
See individual tutorial's README for details
A tutorial of Image classification with ResNet.
- Data pipeline with TensorFlow Dataset API
- Model pipeline with Keras (TensorFlow 2's offical high level API)
- Multi-GPU with distributed strategy
- Customized training with callbacks (TensorBoard, Customized learning schedule)
This tutorial explains how to do transfer learning with TensorFlow 2. We will cover:
- Handling Customized Dataset
- Restore Backbone with Keras's application API
- Restore backbone from disk
This tutorial explains how use checkpoint to save and restore model during training.
- Use
tf.keras.ModelCheckpoint
to save checkpoint - Resume training from a pre-saved checkpoint
This tutorial explains how to implement early stopping in TensorFlow 2.
- Use
tf.keras.EarlyStopping
callback to achieve early stopping.
This tutorial explains how to do distributed training across multiple nodes:
- Code boilerplate for multi-node distributed training
- Run code across multiple machines
This tutorial explains how to train on large datasets:
- Create and use generators to create data
- Use
tf.data.Dataset.from_generator
to crate Dataset object from a generator.
This repo is my extension of https://github.com/lambdal/TensorFlow2-tutorial Appearantly, the origin repo is not maintained.