Author

Code DAO

We deliver AI algorithm tutorials and the latest news, curated by a team of researchers from Peking University, Shanghai Jiao Tong University, Central South University, and leading AI companies such as Huawei, Kuaishou, and SenseTime. Join us in the AI alchemy—making life better!

100

Articles

Likes

Views

Comments

Latest from Code DAO

100 recent articles max

Code DAO

Jan 15, 2022 · Artificial Intelligence

How Tuun’s Automated Data Augmentation Boosts AI Model Accuracy

The article explains how Tuun, an open‑source Bayesian‑optimization tool, automatically searches data‑augmentation policies for machine‑learning models, details the setup with Microsoft NNI, provides code and configuration examples, and presents experiments on CIFAR‑10/100 and SVHN showing that Tuun‑generated policies match or surpass expert‑tuned strategies and further improve performance when combined.

AutoMLBayesian OptimizationImage Classification

0 likes · 14 min read

How Tuun’s Automated Data Augmentation Boosts AI Model Accuracy

Code DAO

Jan 15, 2022 · Artificial Intelligence

Compressing Unsupervised fastText Models 300× Smaller with Near‑Identical NLP Performance

This article shows how the compress‑fasttext Python library can shrink a 7 GB fastText word‑embedding model to about 21 MB—a 300‑fold reduction—while preserving almost the same accuracy on downstream NLP tasks, and explains the underlying compression techniques, usage examples, and evaluation results.

NLPcompress-fasttextfasttext

0 likes · 9 min read

Compressing Unsupervised fastText Models 300× Smaller with Near‑Identical NLP Performance

Code DAO

Jan 15, 2022 · Artificial Intelligence

Improving Class Imbalance in Machine Learning with Class Weights: A Python Logistic Regression Walkthrough

The article demonstrates, with Python code, how applying class_weight—first using the default logistic regression, then the balanced option, and finally manually tuned weights via grid search—can raise the F1 score from 0 to about 0.16 on imbalanced data, and discusses further techniques such as feature engineering and threshold adjustment.

F1 scorePythonclass weight

0 likes · 7 min read

Improving Class Imbalance in Machine Learning with Class Weights: A Python Logistic Regression Walkthrough

Code DAO

Jan 15, 2022 · Backend Development

Implementing Clean Architecture with ent and gqlgen – Part 2

This article walks through integrating the four Clean Architecture layers—entity, use‑case, interface‑adapter, and framework/driver—into a Go application using ent for ORM and gqlgen for GraphQL, covering folder layout, ULID primary keys, Node interface support, and pagination implementation.

Clean ArchitectureGoGraphQL

0 likes · 19 min read

Implementing Clean Architecture with ent and gqlgen – Part 2

Code DAO

Jan 1, 2022 · Backend Development

Building a Clean Architecture GraphQL App with ent and gqlgen (Part 1)

This tutorial walks through creating a maintainable GraphQL application using Go, demonstrating how to set up a Docker‑based MySQL database, configure Viper and Echo, define ent schemas, run migrations, integrate gqlgen with ent, and implement queries and mutations following Clean Architecture principles.

Clean ArchitectureDockerEcho

0 likes · 22 min read

Building a Clean Architecture GraphQL App with ent and gqlgen (Part 1)

Code DAO

Jan 1, 2022 · Artificial Intelligence

Automating Machine Learning Workflows with Scikit‑Learn Pipelines

This article demonstrates how to build a reproducible fraud‑detection workflow using scikit‑learn's Pipeline class, comparing a manual script with a pipeline‑based approach on the IEEE‑CIS Kaggle dataset and showing the benefits of modular, repeatable ML code.

Pythonfraud detectionmachine learning

0 likes · 8 min read

Automating Machine Learning Workflows with Scikit‑Learn Pipelines

Code DAO

Dec 31, 2021 · Artificial Intelligence

Why RegNet Is the Most Flexible Architecture for Computer Vision

RegNet introduces a scalable design space defined by quantized linear functions, enabling flexible trade‑offs between accuracy, efficiency, and mobile deployment, and demonstrates superior performance compared with ResNet, EfficientNet, and other mobile‑optimized networks.

Computer VisionDeep LearningDesign Space

0 likes · 7 min read

Why RegNet Is the Most Flexible Architecture for Computer Vision

Code DAO

Dec 31, 2021 · Cloud Computing

How to Run Distributed PyTorch Training on AzureML with CLI v2

This article walks through the complete workflow for building, testing, and launching a distributed PyTorch training job on AzureML using the CLI v2, covering local script preparation, Accelerate configuration, Docker environment setup, dataset registration, compute target definition, job YAML creation, and job submission with monitoring.

DockerPyTorchazureml

0 likes · 15 min read

How to Run Distributed PyTorch Training on AzureML with CLI v2

Code DAO

Dec 30, 2021 · Artificial Intelligence

Exemplar Transformers Enable 8× Faster CPU‑Compatible Visual Tracking

Researchers at ETH Zurich introduce Exemplar Transformers, a novel Transformer layer that accelerates visual object tracking by eight times, runs in real‑time on CPUs, and improves robustness when integrated into a Siamese‑based tracker, achieving state‑of‑the‑art performance on six benchmark datasets.

CPUSiamese trackerTransformer

0 likes · 5 min read

Exemplar Transformers Enable 8× Faster CPU‑Compatible Visual Tracking

Code DAO

Dec 30, 2021 · Artificial Intelligence

Revamper: An Intelligent Data Augmentation Engine for Faster DNN Training

The article presents a new data‑refurbishing technique and the Revamper loading system that cut CPU‑heavy data‑augmentation costs while preserving model generalization, showing up to significant throughput gains for ResNet‑50 on ImageNet without sacrificing accuracy.

CPU overheadDNN trainingResNet-50

0 likes · 10 min read

Revamper: An Intelligent Data Augmentation Engine for Faster DNN Training