TensorFlow ever higher
summary
Presents how TensorFlow's high-level APIs (eager execution, Autograph, tf.data pipelines) and prebuilt modules for transfer learning let prototypes move to production. Demonstrates wrapping custom models, optimizing throughput with prefetch and parallel_map, and end-to-end pipelines that train, export SavedModel and serve with TensorFlow Serving, TF Lite and TensorFlow.js.
AI-written summary · about
chapters (8)
- 0:00TensorFlow intro
- 2:30Low to high-level APIs
- 7:45Keras in TF
- 10:52Data with tf.data
- 18:20Transfer learning TF Hub
- 24:26Workflow with Estimators
- 33:19Debugging eager
- 35:51TF 2.0 improvements
related talks
01h 18mPutting Tensorflow Models into Production
38mThe Hitchhiker's Guide to Tensorflow: from Tensors to running models in production
42mDeep learning beyond the learning
01h 18mPutting Tensor Flow Models Into Production
18mTensorFlow.js: From prototype to production, what's new in 2022?
31mTensorflow for Janitors
37mSimplifying Training Deep & Serving Learning Models...using Tensorflow
04mTensorFlow and Go