52. HorovodDistributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
57. HpxThe C++ Standard Library for Parallelism and Concurrency
58. GandissectPytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/
61. MmactionAn open-source toolbox for action understanding based on PyTorch
62. FcisFully Convolutional Instance-aware Semantic Segmentation
64. OpenpcdetOpenPCDet Toolbox for LiDAR-based 3D Object Detection.
65. Pytorch StudioganStudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
66. FlannFast Library for Approximate Nearest Neighbors
67. StyleflowStyleFlow: Attribute-conditioned Exploration of StyleGAN-generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)
69. Blade BuildBlade is a powerful build system from Tencent, supports many mainstream programming languages, such as C/C++, java, scala, python, protobuf...
71. DlibA toolkit for making real world machine learning and data analysis applications in C++
72. Openmvsopen Multi-View Stereo reconstruction library
74. Lc0The rewritten engine, originally for tensorflow. Now all other backends have been ported here.
77. Mobilenet YoloMobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
78. BlazingsqlBlazingSQL is a lightweight, GPU accelerated, SQL engine for Python. Built on RAPIDS cuDF.
79. SpherefaceImplementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.
81. Hedcode for Holistically-Nested Edge Detection
82. M2detM2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
83. RefinedetSingle-Shot Refinement Neural Network for Object Detection, CVPR, 2018
85. DeltaDELTA is a deep learning based natural language and speech processing platform.
86. CaffeCaffe: a fast open framework for deep learning.
87. TheanoTheano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as aesara: www.github.com/pymc-devs/aesara
89. VisionDatasets, Transforms and Models specific to Computer Vision
90. Maskrcnn BenchmarkFast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
91. Vid2vidPytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
93. DglPython package built to ease deep learning on graph, on top of existing DL frameworks.
94. CcvC-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library
96. DainDepth-Aware Video Frame Interpolation (CVPR 2019)
98. DetectronFAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.