Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework

Last update: Dec 28, 2022

Overview

Google Cloud AI Developer Relations

This repository contains content produced by Google Cloud AI Developer Relations for machine learning and artificial intelligence. The content covers a wide spectrum from educational, training, and research, covering from novices, junior/intermediate to advanced.

The content has been designed both for self-learning, and for being incorporating into instructional material for universities, private coding schools, and professional training. Licensed as Apache 2.0 and CC-BY, organizations are free to integrate and customize the material into their curriculum.

The repository is organized by:

Directory	Description
`handbooks`	Google (FREE) PDF softcopy of handbooks - CC-BY 4.0 license (2019)
`books`	PDF softcopy of books - preview versions
`workshops`	workshops (presentation slides and code labs) - CC-BY 4.0 license (2019)
`notebooks`	notebooks for production-grade solutions
`zoo`	tf.keras model zoo (coded in idiomatic and composable design pattern) - Apache 2.0 license
`community labs`	Labs for community participation in research

Reviewers and Contributors

We thank the following for their reviews and contributions to the Idiomatic Programmer:

Google Cloud AI - Developer Relations

Andrew Ferlitsch
Noah Negrey
Yu-Han Liu
Shahin Saadati
Torry Yang
Gonzalo Gasca Meza
Amy Unruh
Martin Gorner
Brad Miro
Tianzi Cai
Sara Robinson
Puneith Kaul
Crystal Gomes

Other Current/Former Googlers

William Barret
Sharon Maher

Google Developer Experts (GDE)

Margaret Maynard-Reid / Seattle

ML Practioners

Hobson Lane
Enoch Tetteh
Bill Liu
Miklos Toth

Disclaimer

This is not an officially supported Google product.

Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework

Related tags

Overview

Google Cloud AI Developer Relations

Reviewers and Contributors

Disclaimer

Owner

Google Cloud Platform

Convert ONNX model graph to Keras model format.

In the case of your data having only 1 channel while want to use timm models

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

A really easy-to-use and powerful sudoku solver.

Multi-Task Deep Neural Networks for Natural Language Understanding

Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

[ICCV 2021] Learning A Single Network for Scale-Arbitrary Super-Resolution

Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (CVPR 2022, Oral)

Dynamic Slimmable Network (CVPR 2021, Oral)

使用yolov5训练自己数据集(详细过程)并通过flask部署

Self-Supervised Pre-Training for Transformer-Based Person Re-Identification

The official implementation of "Rethink Dilated Convolution for Real-time Semantic Segmentation"

This repository contains the code to replicate the analysis from the paper "Moving On - Investigating Inventors' Ethnic Origins Using Supervised Learning"

FuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space OptimizationFuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space Optimization

Source code and Dataset creation for the paper "Neural Symbolic Regression That Scales"

TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)

[ICML 2020] "When Does Self-Supervision Help Graph Convolutional Networks?" by Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen

Compositional and Parameter-Efficient Representations for Large Knowledge Graphs

Chinese Mandarin tts text-to-speech 中文 (普通话) 语音合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder,

source code for https://arxiv.org/abs/2005.11248 "Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics"

Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework

Related tags

Overview

Google Cloud AI Developer Relations

Reviewers and Contributors

Disclaimer

Owner

Google Cloud Platform

Convert ONNX model graph to Keras model format.

In the case of your data having only 1 channel while want to use timm models

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

A really easy-to-use and powerful sudoku solver.

Multi-Task Deep Neural Networks for Natural Language Understanding

Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

[ICCV 2021] Learning A Single Network for Scale-Arbitrary Super-Resolution

Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (CVPR 2022, Oral)

Dynamic Slimmable Network (CVPR 2021, Oral)

使用yolov5训练自己数据集(详细过程)并通过flask部署

Self-Supervised Pre-Training for Transformer-Based Person Re-Identification

The official implementation of "Rethink Dilated Convolution for Real-time Semantic Segmentation"

This repository contains the code to replicate the analysis from the paper "Moving On - Investigating Inventors' Ethnic Origins Using Supervised Learning"

FuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space OptimizationFuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space Optimization

Source code and Dataset creation for the paper "Neural Symbolic Regression That Scales"

TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)

[ICML 2020] "When Does Self-Supervision Help Graph Convolutional Networks?" by Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen

Compositional and Parameter-Efficient Representations for Large Knowledge Graphs

Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder,

source code for https://arxiv.org/abs/2005.11248 "Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics"

Chinese Mandarin tts text-to-speech 中文 (普通话) 语音合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder,