TensorFlow Hub (TensorFlow Dev Summit 2018)
Andrew Gasparovic and Jeremiah Harmsen dicuss TF Hub, a new library built to foster the publication, discovery, and consumption of reusable parts of machine learning models. The main part of the launch is a repository of modules, which are self-contained pieces of TensorFlow graphs that can be reused across different tasks. Modules contain variables that have been pre-trained for a task using a large dataset. By reusing a module on a related or similar task, a user can train a model with a smaller dataset, improve generalization, or simply speed up training.
Try out the end-to-end example on GitHub → https://goo.gl/4DBvX7
TensorFlow Dev Summit 2018 All Sessions playlist → https://goo.gl/Lsaq1R
Subscribe to the TensorFlow channel → https://goo.gl/ht3WGe
event: TensorFlow Dev Summit 2018; re_ty: Publish; product: TensorFlow - TensorFlow Hub; fullname: Andrew Gasparovic, Jeremiah Harmsen; event: TensorFlow Dev Summit 2018;
Видео TensorFlow Hub (TensorFlow Dev Summit 2018) канала TensorFlow
Try out the end-to-end example on GitHub → https://goo.gl/4DBvX7
TensorFlow Dev Summit 2018 All Sessions playlist → https://goo.gl/Lsaq1R
Subscribe to the TensorFlow channel → https://goo.gl/ht3WGe
event: TensorFlow Dev Summit 2018; re_ty: Publish; product: TensorFlow - TensorFlow Hub; fullname: Andrew Gasparovic, Jeremiah Harmsen; event: TensorFlow Dev Summit 2018;
Видео TensorFlow Hub (TensorFlow Dev Summit 2018) канала TensorFlow
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Layer-wise learning for quantum neural networks (TF Dev Summit '20)Fermi-Hubbard on Sycamore (Quantum Summer Symposium 2020)Introduction to Tensorflow.js and Machine LearningLatest Generative AI products and solutions on Google CloudAdding audio classification to your mobile app with a pre-trained modelGetting involved in the TensorFlow community (TF World '19)Getting started with text classificationQuantum Approximate Optimization (Quantum Summer Symposium 2020)Differentiable convex optimization layers (TF Dev Summit '20)Discover pre-trained models with Kaggle ModelsGoing further with Image ClassificationRetraining a spam detection model to handle new edge casesComment spam detection: Choosing a pre-made tf.js model, quantization, and word vectors explainedTensorFlow and ML from the trenches: The Innovation Experience Center at JPL (TF Dev Summit '20)On-device machine learning in mobile and web apps | Q&ATensorFlow - the deep learning solution for mobile platforms (TensorFlow Meets)Chatting With the TensorFlow Community (TensorFlow Meets)Fairness Indicators for TensorFlow (TF Dev Summit '20)The future of frameworks: Navigate the OSS landscapeAI Experiments: Making AI Accessible through Play (TF Dev Summit ‘19)On-device fetal ultrasound assessment with TensorFlow Lite