Additional utils and helpers to extend TensorFlow when build recommendation systems, contributed and maintained by SIG Recommenders.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

A collection of handy Bash One-Liners and terminal tricks for data processing and Linux system maintenance.

📚 Awesome CS Books/Series(.pdf by git lfs) Warehouse for Geeks, ProgrammingLanguage, SoftwareEngineering, Web, AI, ServerSideApplication, Infrastructure, FE etc. 💫 优秀计算机科学与技术领域相关的书籍归档

pytorch cuda extension of grid_sample1d

Model Quantization Benchmark

Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs,…

Actively maintained ONNX Optimizer

10x faster matrix and vector operations

Tensorflow Backend for ONNX

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

oneAPI Deep Neural Network Library (oneDNN)

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…

Neural Network Compression Framework for enhanced OpenVINO™ inference

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

System for AI Education Resource.

Apache Flink

The official implementation of You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient.

厦门大学研究生学位论文 LaTeX 模板

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

Torchmetrics - Machine learning metrics for distributed, scalable PyTorch applications.

《美国反对美国》是王沪宁先生在上世纪80年代末赴美观察写作的。我们知道在那个年代中国对西方特别是美国的追捧有多高，所以突然看到一个学者在80年代就有如此清楚的认识，十分钦佩。由于网上只有效果很差的PDF扫描版，所以我想利用OCR技术和肉眼（人体OCR）来转成现代化的文本格式。目前已经全部完成。

The papers of Deepfakes Detection.

互联网首份程序员考公指南，由3位已经进入体制内的前大厂程序员联合献上。

PArameterized Max Scale

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale