ProSelfLC-2021noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.
Stars: ✭ 45 (-53.61%)
AB distillationKnowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons (AAAI 2019)
Stars: ✭ 105 (+8.25%)
isaac ros dnn inferenceHardware-accelerated DNN model inference ROS2 packages using NVIDIA Triton/TensorRT for both Jetson and x86_64 with CUDA-capable GPU
Stars: ✭ 67 (-30.93%)
Jetson InferenceHello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
Stars: ✭ 5,191 (+5251.55%)
awesome-efficient-gnnCode and resources on scalable and efficient Graph Neural Networks
Stars: ✭ 498 (+413.4%)
bert-AADAdversarial Adaptation with Distillation for BERT Unsupervised Domain Adaptation
Stars: ✭ 27 (-72.16%)
Torch2trtAn easy to use PyTorch to TensorRT converter
Stars: ✭ 2,974 (+2965.98%)
TensorRT CV🚀🚀🚀NVIDIA TensorRT 加速推断教程!
Stars: ✭ 125 (+28.87%)
Pretrained Language ModelPretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Stars: ✭ 2,033 (+1995.88%)
flexible-yolov5More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam,dcn and so on), and tensorrt
Stars: ✭ 282 (+190.72%)
LabelRelaxation-CVPR21Official PyTorch Implementation of Embedding Transfer with Label Relaxation for Improved Metric Learning, CVPR 2021
Stars: ✭ 37 (-61.86%)
FGDFocal and Global Knowledge Distillation for Detectors (CVPR 2022)
Stars: ✭ 124 (+27.84%)
ros-yolo-sortYOLO v3, v4, v5, v6, v7 + SORT tracking + ROS platform. Supporting: YOLO with Darknet, OpenCV(DNN), OpenVINO, TensorRT(tkDNN). SORT supports python(original) and C++. (Not Deep SORT)
Stars: ✭ 162 (+67.01%)
BAKESelf-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Stars: ✭ 79 (-18.56%)
InsightFace-RESTInsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.
Stars: ✭ 308 (+217.53%)
TnnTNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and …
Stars: ✭ 3,257 (+3257.73%)
distill-and-selectAuthors official PyTorch implementation of the "DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval" [IJCV 2022]
Stars: ✭ 43 (-55.67%)
BerrynetDeep learning gateway on Raspberry Pi and other edge devices
Stars: ✭ 1,529 (+1476.29%)
MLIC-KD-WSDMulti-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection (ACM MM 2018)
Stars: ✭ 58 (-40.21%)
Pytorch Yolov4PyTorch ,ONNX and TensorRT implementation of YOLOv4
Stars: ✭ 3,690 (+3704.12%)
head-network-distillation[IEEE Access] "Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-constrained Edge Computing Systems" and [ACM MobiCom HotEdgeVideo 2019] "Distilled Split Deep Neural Networks for Edge-assisted Real-time Systems"
Stars: ✭ 27 (-72.16%)
onnx2tensorRttensorRt-inference darknet2onnx pytorch2onnx mxnet2onnx python version
Stars: ✭ 14 (-85.57%)
mediapipe plusThe purpose of this project is to apply mediapipe to more AI chips.
Stars: ✭ 38 (-60.82%)
ACCV TinyGANBigGAN; Knowledge Distillation; Black-Box; Fast Training; 16x compression
Stars: ✭ 62 (-36.08%)
yolov5 tensorrtThis is the implementation that supports yolov5s, yolov5m, yolov5l, yolov5x.
Stars: ✭ 32 (-67.01%)
SemCKDThis is the official implementation for the AAAI-2021 paper (Cross-Layer Distillation with Semantic Calibration).
Stars: ✭ 42 (-56.7%)
FKDA Fast Knowledge Distillation Framework for Visual Recognition
Stars: ✭ 49 (-49.48%)
SAN[ECCV 2020] Scale Adaptive Network: Learning to Learn Parameterized Classification Networks for Scalable Input Images
Stars: ✭ 41 (-57.73%)
mmrazorOpenMMLab Model Compression Toolbox and Benchmark.
Stars: ✭ 644 (+563.92%)
MoTISMobile(iOS) Text-to-Image search powered by multimodal semantic representation models(e.g., OpenAI's CLIP). Accepted at NAACL 2022.
Stars: ✭ 60 (-38.14%)
self-driving-ish computer vision systemThis project generates images you've probably seen in autonomous driving demo. Object Detection, Lane Detection, Road Segmentation, Depth Estimation using TensorRT
Stars: ✭ 254 (+161.86%)
TengineTengine is a lite, high performance, modular inference engine for embedded device
Stars: ✭ 4,012 (+4036.08%)
deepstream tao appsSample apps to demonstrate how to deploy models trained with TAO on DeepStream
Stars: ✭ 274 (+182.47%)
DeepdetectDeep Learning API and Server in C++14 support for Caffe, Caffe2, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
Stars: ✭ 2,306 (+2277.32%)
LDLocalization Distillation for Dense Object Detection (CVPR 2022)
Stars: ✭ 271 (+179.38%)
TensorrtxImplementation of popular deep learning networks with TensorRT network definition API
Stars: ✭ 3,456 (+3462.89%)
trt pose handReal-time hand pose estimation and gesture classification using TensorRT
Stars: ✭ 137 (+41.24%)
Tensorflow Yolov4 TfliteYOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
Stars: ✭ 1,881 (+1839.18%)
yolov4 trt rosYOLOv4 object detector using TensorRT engine
Stars: ✭ 89 (-8.25%)
TensorrtTensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.
Stars: ✭ 4,644 (+4687.63%)
Torch-TensorRTPyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT
Stars: ✭ 1,216 (+1153.61%)
Distill-BERT-TextgenResearch code for ACL 2020 paper: "Distilling Knowledge Learned in BERT for Text Generation".
Stars: ✭ 121 (+24.74%)
Deepstream ProjectThis is a highly separated deployment project based on Deepstream , including the full range of Yolo and continuously expanding deployment projects such as Ocr.
Stars: ✭ 120 (+23.71%)
mtomoMultiple types of NN model optimization environments. It is possible to directly access the host PC GUI and the camera to verify the operation. Intel iHD GPU (iGPU) support. NVIDIA GPU (dGPU) support.
Stars: ✭ 24 (-75.26%)
pnnpnn is Darknet compatible neural nets inference engine implemented in Rust.
Stars: ✭ 17 (-82.47%)
neural-compressorIntel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.
Stars: ✭ 666 (+586.6%)
deepvacPyTorch Project Specification.
Stars: ✭ 507 (+422.68%)
kdtfKnowledge Distillation using Tensorflow
Stars: ✭ 139 (+43.3%)