Stars
Matlab and OpenCV Code Calculate JND of an image.
positive666 / hyperIQA
Forked from SSL92/hyperIQASource code for the CVPR'20 paper "Blindly Assess Image Quality in the Wild Guided by A Self-Adaptive Hyper Network"
Implementation of paper: Invertible Image Rescaling
positive666 / nb
Forked from lucasjinreal/nbNeural Network Blocks - Collect all kinds of fancy model blocks for you to build more powerful neural network model.
positive666 / CenterNet
Forked from xingyizhou/CenterNetObject detection, 3D detection, and pose estimation using center point detection:
positive666 / torch2trt
Forked from NVIDIA-AI-IOT/torch2trtAn easy to use PyTorch to TensorRT converter
positive666 / deepstream_triton_model_deploy
Forked from NVIDIA-AI-IOT/deepstream_triton_model_deployHow to deploy open source models using DeepStream and Triton Inference Server
Real-time face recognition using Pytorch
positive666 / libovmatting
Forked from kingpeter2015/libovmattingA C++ library for Background Matting
dbnet+crnn Deepstream application
positive666 / faiss_search
Forked from facebookresearch/faissA library for efficient similarity search and clustering of dense vectors.
positive666 / instant-ngp
Forked from NVlabs/instant-ngpInstant neural graphics primitives: lightning fast NeRF and more
based on mediapipe human Estimation project for pytorch, provide function(face_mesh,iris,pose,hand)
This is a highly separated deployment project based on Deepstream , including the full range of Yolo and continuously expanding deployment projects such as Ocr.
Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP & Whisper - Automatically Detect , Segment and Generate Anything with Image, Text, and Speech Inputs
positive666 / VisualGLM_6B
Forked from THUDM/VisualGLM-6BChinese and English multimodal conversational language model | 多模态中英双语对话语言模型
based on yolo-high-level project (detect\pose\classify\segment\):include yolov5\yolov7\yolov8\ core ,improvement research ,SwintransformV2 and Attention Series. training skills, business customizat…
positive666 / Tag2Text
Forked from xinyu1205/recognize-anythingCode for paper: Tag2Text: Guiding Vision-Language Model via Image Tagging
You can do anything by sota AI with prompt ,auto AI tools , VL larger model fine and project
刷算法全靠套路,认准 labuladong 就够了!English version supported! Crack LeetCode, not only how, but also why.
flv video http-flv http flv rtsp rtp over rtsp hls m3u8 ts boost asio webrtc ice dtls srtp
A sample app that will take images and create a movie using AVAssetWriter.
Fast and friendly HTTP server framework for async Rust
deeplearning.ai(吴恩达老师的深度学习课程笔记及资源)
Image Recognition captcha without image segmentation 无需图片分割的验证码识别