convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.
APACHE-2.0 License
TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating poin...
A Simple and Versatile Framework for Object Detection and Instance Recognition
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
Deep-learning based semantic and instance segmentation for 3D Electron Microscopy and other bioim...
A collection of computer vision pre-trained models.
Easiest way of fine-tuning HuggingFace video classification models
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such...
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.