YOLO的tensorrt加速

# TensorRTx TensorRTx aims to implement popular deep learning networks with tensorrt network definition APIs. As we know, tensorrt has builtin parsers, including caffeparser, uffparser, onnxparser, etc. But when we use these parsers, we often run into some "unsupported operations or layers" problems, especially some state-of-the-art models are using new type of layers. So why don't we just skip all parsers? We just use TensorRT network definition APIs to build the whole network, it's not so complicated. I wrote this project to get familiar with tensorrt API, and also to share and learn from the community. All the models are implemented in pytorch/mxnet/tensorflown first, and export a weights file xxx.wts, and then use tensorrt to load weights, define network and do inference. Some pytorch implementations can be found in my repo [Pytorchx](https://github.com/wang-xinyu/pytorchx), the remaining are from polular open-source implementations. ## News - `31 Aug 2021`. [FamousDirector](https://github.com/FamousDirector): update retinaface to support TensorRT 8.0. - `27 Aug 2021`. [HaiyangPeng](https://github.com/HaiyangPeng): add a python wrapper for hrnet segmentation. - `1 Jul 2021`. [freedenS](https://github.com/freedenS): DE⫶TR: End-to-End Object Detection with Transformers. First Transformer model! - `10 Jun 2021`. [upczww](https://github.com/upczww): EfficientNet b0-b8 and l2. - `23 May 2021`. [SsisyphusTao](https://github.com/SsisyphusTao): CenterNet DLA-34 with DCNv2 plugin. - `17 May 2021`. [ybw108](https://github.com/ybw108): arcface LResNet100E-IR and MobileFaceNet. - `6 May 2021`. [makaveli10](https://github.com/makaveli10): scaled-yolov4 yolov4-csp. - `29 Apr 2021`. [upczww](https://github.com/upczww): hrnet segmentation w18/w32/w48, ocr branch also. - `28 Apr 2021`. [aditya-dl](https://github.com/aditya-dl): mobilenetv2, alexnet, densenet121, mobilenetv3 with python API. - `26 Apr 2021`. [makaveli10](https://github.com/makaveli10) add Inceptionv4. - `25 Apr 2021`. YOLOv5 updated to v5.0, supporting s/m/l/x/s6/m6/l6/x6. - `23 Apr 2021`. [irvingzhang0512](https://github.com/irvingzhang0512) add TSM: Temporal Shift Module for Efficient Video Understanding, ICCV2019. - `23 Apr 2021`. [freedenS](https://github.com/freedenS) implement MaskRCNN, till now the MOST complicated model in this repo. - `16 Apr 2021`. [irvingzhang0512](https://github.com/irvingzhang0512) implement lenet and resnet50 with Python API, [freedenS](https://github.com/freedenS) implement FasterRCNN with five plugins, cheers! - `2 Apr 2021`. [mingyu6yang](https://github.com/mingyu6yang) added a python wrapper for retinaface, [makaveli10](https://github.com/makaveli10) added DenseNet-121. ## Tutorials - [Install the dependencies.](./tutorials/install.md) - [A guide for quickly getting started, taking lenet5 as a demo.](./tutorials/getting_started.md) - [The .wts file content format](./tutorials/getting_started.md#the-wts-content-format) - [Frequently Asked Questions (FAQ)](./tutorials/faq.md) - [Migrating from TensorRT 4 to 7](./tutorials/migrating_from_tensorrt_4_to_7.md) - [How to implement multi-GPU processing, taking YOLOv4 as example](./tutorials/multi_GPU_processing.md) - [Check if Your GPU support FP16/INT8](./tutorials/check_fp16_int8_support.md) - [How to Compile and Run on Windows](./tutorials/run_on_windows.md) - [Deploy YOLOv4 with Triton Inference Server](https://github.com/isarsoft/yolov4-triton-tensorrt) - [From pytorch to trt step by step, hrnet as example(Chinese)](./tutorials/from_pytorch_to_trt_stepbystep_hrnet.md) ## Test Environment 1. GTX1080 / Ubuntu16.04 / cuda10.0 / cudnn7.6.5 / tensorrt7.0.0 / nvinfer7.0.0 / opencv3.3 ## How to run Each folder has a readme inside, which explains how to run the models inside. ## Models Following models are implemented. |Name | Description | |-|-| |[lenet](./lenet) | the simplest, as a "hello world" of this project | |[alexnet](./alexnet)| easy to implement, all layers are supported in tensorrt | |[googlenet](./googlenet)| GoogLeNet (Inception v1) | |[inception](./inception)| Inception v3, v4 | |[mnasnet](./mnasnet)| MNASNet with depth multiplier of 0.5 from the paper | |[mobilenet](./mobilenet)| MobileNet v2, v3-small, v3-large | |[resnet](./resnet)| resnet-18, resnet-50 and resnext50-32x4d are implemented | |[senet](./senet)| se-resnet50 | |[shufflenet](./shufflenetv2)| ShuffleNet v2 with 0.5x output channels | |[squeezenet](./squeezenet)| SqueezeNet 1.1 model | |[vgg](./vgg)| VGG 11-layer model | |[yolov3-tiny](./yolov3-tiny)| weights and pytorch implementation from [ultralytics/yolov3](https://github.com/ultralytics/yolov3) | |[yolov3](./yolov3)| darknet-53, weights and pytorch implementation from [ultralytics/yolov3](https://github.com/ultralytics/yolov3) | |[yolov3-spp](./yolov3-spp)| darknet-53, weights and pytorch implementation from [ultralytics/yolov3](https://github.com/ultralytics/yolov3) | |[yolov4](./yolov4)| CSPDarknet53, weights from [AlexeyAB/darknet](https://github.com/AlexeyAB/darknet#pre-trained-models), pytorch implementation from [ultralytics/yolov3](https://github.com/ultralytics/yolov3) | |[yolov5](./yolov5)| yolov5 v1.0-v5.0, pytorch implementation from [ultralytics/yolov5](https://github.com/ultralytics/yolov5) | |[retinaface](./retinaface)| resnet50 and mobilnet0.25, weights from [biubug6/Pytorch_Retinaface](https://github.com/biubug6/Pytorch_Retinaface) | |[arcface](./arcface)| LResNet50E-IR, LResNet100E-IR and MobileFaceNet, weights from [deepinsight/insightface](https://github.com/deepinsight/insightface) | |[retinafaceAntiCov](./retinafaceAntiCov)| mobilenet0.25, weights from [deepinsight/insightface](https://github.com/deepinsight/insightface), retinaface anti-COVID-19, detect face and mask attribute | |[dbnet](./dbnet)| Scene Text Detection, weights from [BaofengZan/DBNet.pytorch](https://github.com/BaofengZan/DBNet.pytorch) | |[crnn](./crnn)| pytorch implementation from [meijieru/crnn.pytorch](https://github.com/meijieru/crnn.pytorch) | |[ufld](./ufld)| pytorch implementation from [Ultra-Fast-Lane-Detection](https://github.com/cfzd/Ultra-Fast-Lane-Detection), ECCV2020 | |[hrnet](./hrnet)| hrnet-image-classification and hrnet-semantic-segmentation, pytorch implementation from [HRNet-Image-Classification](https://github.com/HRNet/HRNet-Image-Classification) and [HRNet-Semantic-Segmentation](https://github.com/HRNet/HRNet-Semantic-Segmentation) | |[psenet](./psenet)| PSENet Text Detection, tensorflow implementation from [liuheng92/tensorflow_PSENet](https://github.com/liuheng92/tensorflow_PSENet) | |[ibnnet](./ibnnet)| IBN-Net, pytorch implementation from [XingangPan/IBN-Net](https://github.com/XingangPan/IBN-Net), ECCV2018 | |[unet](./unet)| U-Net, pytorch implementation from [milesial/Pytorch-UNet](https://github.com/milesial/Pytorch-UNet) | |[repvgg](./repvgg)| RepVGG, pytorch implementation from [DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG) | |[lprnet](./lprnet)| LPRNet, pytorch implementation from [xuexingyu24/License_Plate_Detection_Pytorch](https://github.com/xuexingyu24/License_Plate_Detection_Pytorch) | |[refinedet](./refinedet)| RefineDet, pytorch implementation from [luuuyi/RefineDet.PyTorch](https://github.com/luuuyi/RefineDet.PyTorch) | |[densenet](./densenet)| DenseNet-121, from torchvision.models | |[rcnn](./rcnn)| FasterRCNN and MaskRCNN, model from [detectron2](https://github.com/facebookresearch/detectron2) | |[tsm](./tsm)| TSM: Temporal Shift Module for Efficient Video Understanding, ICCV2019 | |[scaled-yolov4](./scaled-yolov4)| yolov4-csp, pytorch from [WongKinYiu/ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4) | |[centernet](./centernet)| CenterNet DLA-34, pytorch from [xingyizhou/CenterNet](https://github.com/xingyizhou/CenterNet) | |[efficientnet](./efficientnet)| EfficientNet b0-b8 and l2, pytorch from [lukemelas/EfficientNet-PyTorch](https://github.com/lukemelas/EfficientNet-PyTorch) | |[detr](./detr)| DE⫶TR, pytorch from [faceboo