- Notifications
You must be signed in to change notification settings - Fork1.8k
Implementation of popular deep learning networks with TensorRT network definition API
License
NotificationsYou must be signed in to change notification settings
wang-xinyu/tensorrtx
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
TensorRTx aims to implement popular deep learning networks with TensorRT network definition API.
Why don't we use a parser (ONNX parser, UFF parser, caffe parser, etc), but use complex APIs to build a network from scratch? I have summarized the advantages in the following aspects.
- Flexible, easy to modify the network, add/delete a layer or input/output tensor, replace a layer, merge layers, integrate preprocessing and postprocessing into network, etc.
- Debuggable, construct the entire network in an incremental development manner, easy to get middle layer results.
- Educational, learn about the network structure during this development, rather than treating everything as a black box.
The basic workflow of TensorRTx is:
- Get the trained models from pytorch, mxnet or tensorflow, etc. Some pytorch models can be found in my repopytorchx, the remaining are from popular open-source repos.
- Export the weights to a plain text file --.wts file.
- Load weights in TensorRT, define the network, build a TensorRT engine.
- Load the TensorRT engine and run inference.
10 May 2025.pranavm-nvidia:YOLO11 writen inTripy.2 May 2025.fazligorkembal: YOLO1212 Apr 2025.pranavm-nvidia: FirstLenet example writen inTripy.11 Apr 2025.mpj1234:YOLO11-obb22 Oct 2024.lindsayshuo: YOLOv8-obb18 Oct 2024.zgjja: Rafactor docker image.11 Oct 2024.mpj1234: YOLO119 Oct 2024.Phoenix8215: GhostNet V1 and V2.21 Aug 2024.Lemonononon: real-esrgan-general-x4v329 Jul 2024.mpj1234: Check the YOLOv5, YOLOv8 & YOLOv10 in TensorRT 10.x API, branch →trt1029 Jul 2024.mpj1234: YOLOv1021 Jun 2024.WuxinrongY: YOLOv9-T, YOLOv9-S, YOLOv9-M28 Apr 2024.lindsayshuo: YOLOv8-pose22 Apr 2024.B1SH0PP: EfficientAd: Accurate Visual Anomaly Detection at Millisecond-Level Latencies.18 Apr 2024.lindsayshuo: YOLOv8-p2
- How to make contribution
- Install the dependencies.
- A guide for quickly getting started, taking lenet5 as a demo.
- The .wts file content format
- Frequently Asked Questions (FAQ)
- Migrating from TensorRT 4 to 7
- How to implement multi-GPU processing, taking YOLOv4 as example
- Check if Your GPU support FP16/INT8
- How to Compile and Run on Windows
- Deploy YOLOv4 with Triton Inference Server
- From pytorch to trt step by step, hrnet as example(Chinese)
- TensorRT 7.x
- TensorRT 8.x(Some of the models support 8.x)
Each folder has a readme inside, which explains how to run the models inside.
Following models are implemented.
| Name | Description |
|---|---|
| mlp | the very basic model for starters, properly documented |
| lenet | the simplest, as a "hello world" of this project |
| alexnet | easy to implement, all layers are supported in tensorrt |
| googlenet | GoogLeNet (Inception v1) |
| inception | Inception v3, v4 |
| mnasnet | MNASNet with depth multiplier of 0.5 from the paper |
| mobilenet | MobileNet v2, v3-small, v3-large |
| resnet | resnet-18, resnet-50 and resnext50-32x4d are implemented |
| senet | se-resnet50 |
| shufflenet | ShuffleNet v2 with 0.5x output channels |
| squeezenet | SqueezeNet 1.1 model |
| vgg | VGG 11-layer model |
| yolov3-tiny | weights and pytorch implementation fromultralytics/yolov3 |
| yolov3 | darknet-53, weights and pytorch implementation fromultralytics/yolov3 |
| yolov3-spp | darknet-53, weights and pytorch implementation fromultralytics/yolov3 |
| yolov4 | CSPDarknet53, weights fromAlexeyAB/darknet, pytorch implementation fromultralytics/yolov3 |
| yolov5 | yolov5 v1.0-v7.0 ofultralytics/yolov5, detection, classification and instance segmentation |
| yolov7 | yolov7 v0.1, pytorch implementation fromWongKinYiu/yolov7 |
| yolov8 | yolov8, pytorch implementation fromultralytics |
| yolov9 | The Pytorch implementation isWongKinYiu/yolov9. |
| yolov10 | The Pytorch implementation isTHU-MIG/yolov10. |
| yolo11 | The Pytorch implementation isultralytics. |
| yolo12 | The Pytorch implementation isultralytics. |
| yolop | yolop, pytorch implementation fromhustvl/YOLOP |
| retinaface | resnet50 and mobilnet0.25, weights frombiubug6/Pytorch_Retinaface |
| arcface | LResNet50E-IR, LResNet100E-IR and MobileFaceNet, weights fromdeepinsight/insightface |
| retinafaceAntiCov | mobilenet0.25, weights fromdeepinsight/insightface, retinaface anti-COVID-19, detect face and mask attribute |
| dbnet | Scene Text Detection, weights fromBaofengZan/DBNet.pytorch |
| crnn | pytorch implementation frommeijieru/crnn.pytorch |
| ufld | pytorch implementation fromUltra-Fast-Lane-Detection, ECCV2020 |
| hrnet | hrnet-image-classification and hrnet-semantic-segmentation, pytorch implementation fromHRNet-Image-Classification andHRNet-Semantic-Segmentation |
| psenet | PSENet Text Detection, tensorflow implementation fromliuheng92/tensorflow_PSENet |
| ibnnet | IBN-Net, pytorch implementation fromXingangPan/IBN-Net, ECCV2018 |
| unet | U-Net, pytorch implementation frommilesial/Pytorch-UNet |
| repvgg | RepVGG, pytorch implementation fromDingXiaoH/RepVGG |
| lprnet | LPRNet, pytorch implementation fromxuexingyu24/License_Plate_Detection_Pytorch |
| refinedet | RefineDet, pytorch implementation fromluuuyi/RefineDet.PyTorch |
| densenet | DenseNet-121, from torchvision.models |
| rcnn | FasterRCNN and MaskRCNN, model fromdetectron2 |
| tsm | TSM: Temporal Shift Module for Efficient Video Understanding, ICCV2019 |
| scaled-yolov4 | yolov4-csp, pytorch fromWongKinYiu/ScaledYOLOv4 |
| centernet | CenterNet DLA-34, pytorch fromxingyizhou/CenterNet |
| efficientnet | EfficientNet b0-b8 and l2, pytorch fromlukemelas/EfficientNet-PyTorch |
| detr | DE⫶TR, pytorch fromfacebookresearch/detr |
| swin-transformer | Swin Transformer - Semantic Segmentation, only support Swin-T. The Pytorch implementation ismicrosoft/Swin-Transformer |
| real-esrgan | Real-ESRGAN. The Pytorch implementation isreal-esrgan |
| superpoint | SuperPoint. The Pytorch model is frommagicleap/SuperPointPretrainedNetwork |
| csrnet | CSRNet. The Pytorch implementation isleeyeehoo/CSRNet-pytorch |
| EfficientAd | EfficientAd: Accurate Visual Anomaly Detection at Millisecond-Level Latencies. Fromanomalib |
The .wts files can be downloaded from model zoo for quick evaluation. But it is recommended to convert .wts from pytorch/mxnet/tensorflow model, so that you can retrain your own model.
GoogleDrive |BaiduPan pwd: uvv2
Some tricky operations encountered in these models, already solved, but might have better solutions.
| Name | Description |
|---|---|
| BatchNorm | Implement by a scale layer, used in resnet, googlenet, mobilenet, etc. |
| MaxPool2d(ceil_mode=True) | use a padding layer before maxpool to solve ceil_mode=True, see googlenet. |
| average pool with padding | use setAverageCountExcludesPadding() when necessary, see inception. |
| relu6 | useRelu6(x) = Relu(x) - Relu(x-6), see mobilenet. |
| torch.chunk() | implement the 'chunk(2, dim=C)' by tensorrt plugin, see shufflenet. |
| channel shuffle | use two shuffle layers to implementchannel_shuffle, see shufflenet. |
| adaptive pool | use fixed input dimension, and use regular average pooling, see shufflenet. |
| leaky relu | I wrote a leaky relu plugin, but PRelu inNvInferPlugin.h can be used, see yolov3 in branchtrt4. |
| yolo layer v1 | yolo layer is implemented as a plugin, see yolov3 in branchtrt4. |
| yolo layer v2 | three yolo layers implemented in one plugin, see yolov3-spp. |
| upsample | replaced by a deconvolution layer, see yolov3. |
| hsigmoid | hard sigmoid is implemented as a plugin, hsigmoid and hswish are used in mobilenetv3 |
| retinaface output decode | implement a plugin to decode bbox, confidence and landmarks, see retinaface. |
| mish | mish activation is implemented as a plugin, mish is used in yolov4 |
| prelu | mxnet's prelu activation with trainable gamma is implemented as a plugin, used in arcface |
| HardSwish | hard_swish = x * hard_sigmoid, used in yolov5 v3.0 |
| LSTM | Implemented pytorch nn.LSTM() with tensorrt api |
| Models | Device | BatchSize | Mode | Input Shape(HxW) | FPS |
|---|---|---|---|---|---|
| YOLOv3-tiny | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 333 |
| YOLOv3(darknet53) | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 39.2 |
| YOLOv3(darknet53) | Xeon E5-2620/GTX1080 | 1 | INT8 | 608x608 | 71.4 |
| YOLOv3-spp(darknet53) | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 38.5 |
| YOLOv4(CSPDarknet53) | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 35.7 |
| YOLOv4(CSPDarknet53) | Xeon E5-2620/GTX1080 | 4 | FP32 | 608x608 | 40.9 |
| YOLOv4(CSPDarknet53) | Xeon E5-2620/GTX1080 | 8 | FP32 | 608x608 | 41.3 |
| YOLOv5-s v3.0 | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 142 |
| YOLOv5-s v3.0 | Xeon E5-2620/GTX1080 | 4 | FP32 | 608x608 | 173 |
| YOLOv5-s v3.0 | Xeon E5-2620/GTX1080 | 8 | FP32 | 608x608 | 190 |
| YOLOv5-m v3.0 | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 71 |
| YOLOv5-l v3.0 | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 43 |
| YOLOv5-x v3.0 | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 29 |
| YOLOv5-s v4.0 | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 142 |
| YOLOv5-m v4.0 | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 71 |
| YOLOv5-l v4.0 | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 40 |
| YOLOv5-x v4.0 | Xeon E5-2620/GTX1080 | 1 | FP32 | 608x608 | 27 |
| RetinaFace(resnet50) | Xeon E5-2620/GTX1080 | 1 | FP32 | 480x640 | 90 |
| RetinaFace(resnet50) | Xeon E5-2620/GTX1080 | 1 | INT8 | 480x640 | 204 |
| RetinaFace(mobilenet0.25) | Xeon E5-2620/GTX1080 | 1 | FP32 | 480x640 | 417 |
| ArcFace(LResNet50E-IR) | Xeon E5-2620/GTX1080 | 1 | FP32 | 112x112 | 333 |
| CRNN | Xeon E5-2620/GTX1080 | 1 | FP32 | 32x100 | 1000 |
Help wanted, if you got speed results, please add an issue or PR.
Any contributions, questions and discussions are welcomed, contact me by following info.
E-mail:wangxinyu_es@163.com
WeChat ID: wangxinyu0375 (可加我微信进tensorrtx交流群，备注：tensorrtx)
About
Implementation of popular deep learning networks with TensorRT network definition API
Topics
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Packages0
No packages published
Uh oh!
There was an error while loading.Please reload this page.