An easy to use PyTorch to TensorRT converter
Alternatives To Torch2trt
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
4 days ago249Jupyter Notebook
Learn OpenCV : C++ and Python Examples
Deep Learning For Image Processing14,599
22 days ago28gpl-3.0Python
deep learning for image processing including classification and object-detection etc.
Nlp Tutorial12,146
a month ago33mitJupyter Notebook
Natural Language Processing Tutorial for Deep Learning Researchers
Pytorch Tutorial7,372
8 days ago28mitJupyter Notebook
Build your neural network easy and fast, 莫烦Python中文教学
a month ago274mitPython
An easy to use PyTorch to TensorRT converter
Tsai3,2571a day ago41April 19, 202220apache-2.0Jupyter Notebook
Time series Timeseries Deep Learning Machine Learning Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai
Catalyst3,1021910a day ago108April 29, 20224apache-2.0Python
Accelerated deep learning R&D
3 years ago42mitPython
Graph Convolutional Networks in PyTorch
Bert Chinese Text Classification Pytorch2,890
11 days ago127mitPython
Uer Py2,458
18 days ago124apache-2.0Python
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
Alternatives To Torch2trt
Select To Compare

Alternative Project Comparisons


What models are you using, or hoping to use, with TensorRT? Feel free to join the discussion here.

torch2trt is a PyTorch to TensorRT converter which utilizes the TensorRT Python API. The converter is

  • Easy to use - Convert modules with a single function call torch2trt

  • Easy to extend - Write your own layer converter in Python and register it with @tensorrt_converter

If you find an issue, please let us know!

Please note, this converter has limited coverage of TensorRT / PyTorch. We created it primarily to easily optimize the models used in the JetBot project. If you find the converter helpful with other models, please let us know.


Below are some usage examples, for more check out the notebooks.


import torch
from torch2trt import torch2trt
from torchvision.models.alexnet import alexnet

# create some regular pytorch model...
model = alexnet(pretrained=True).eval().cuda()

# create example data
x = torch.ones((1, 3, 224, 224)).cuda()

# convert to TensorRT feeding sample data as input
model_trt = torch2trt(model, [x])


We can execute the returned TRTModule just like the original PyTorch model

y = model(x)
y_trt = model_trt(x)

# check the output against PyTorch
print(torch.max(torch.abs(y - y_trt)))

Save and load

We can save the model as a state_dict., 'alexnet_trt.pth')

We can load the saved model into a TRTModule

from torch2trt import TRTModule

model_trt = TRTModule()



We tested the converter against these models using the script. You can generate the results by calling


The results below show the throughput in FPS. You can find the raw output, which includes latency, in the benchmarks folder.

Model Nano (PyTorch) Nano (TensorRT) Xavier (PyTorch) Xavier (TensorRT)
alexnet 46.4 69.9 250 580
squeezenet1_0 44 137 130 890
squeezenet1_1 76.6 248 132 1390
resnet18 29.4 90.2 140 712
resnet34 15.5 50.7 79.2 393
resnet50 12.4 34.2 55.5 312
resnet101 7.18 19.9 28.5 170
resnet152 4.96 14.1 18.9 121
densenet121 11.5 41.9 23.0 168
densenet169 8.25 33.2 16.3 118
densenet201 6.84 25.4 13.3 90.9
densenet161 4.71 15.6 17.2 82.4
vgg11 8.9 18.3 85.2 201
vgg13 6.53 14.7 71.9 166
vgg16 5.09 11.9 61.7 139
vgg19 54.1 121
vgg11_bn 8.74 18.4 81.8 201
vgg13_bn 6.31 14.8 68.0 166
vgg16_bn 4.96 12.0 58.5 140
vgg19_bn 51.4 121


Note: torch2trt depends on the TensorRT Python API. On Jetson, this is included with the latest JetPack. For desktop, please follow the TensorRT Installation Guide. You may also try installing torch2trt inside one of the NGC PyTorch docker containers for Desktop or Jetson.

Step 1 - Install the torch2trt Python library

To install the torch2trt Python library, call the following

git clone
cd torch2trt
python install

Step 2 (optional) - Install the torch2trt plugins library

To install the torch2trt plugins library, call the following

cmake -B build . && cmake --build build --target install && ldconfig

This includes support for some layers which may not be supported natively by TensorRT. Once this library is found in the system, the associated layer converters in torch2trt are implicitly enabled.

Note: torch2trt now maintains plugins as an independent library compiled with CMake. This makes compiled TensorRT engines more portable. If needed, the deprecated plugins (which depend on PyTorch) may still be installed by calling python install --plugins.

Step 3 (optional) - Install experimental community contributed features

To install torch2trt with experimental community contributed features under torch2trt.contrib, like Quantization Aware Training (QAT)(requires TensorRT>=7.0), call the following,

git clone
cd torch2trt/scripts    

This enables you to run the QAT example located here.

How does it work?

This converter works by attaching conversion functions (like convert_ReLU) to the original PyTorch functional calls (like torch.nn.ReLU.forward). The sample input data is passed through the network, just as before, except now whenever a registered function (torch.nn.ReLU.forward) is encountered, the corresponding converter (convert_ReLU) is also called afterwards. The converter is passed the arguments and return statement of the original PyTorch function, as well as the TensorRT network that is being constructed. The input tensors to the original PyTorch function are modified to have an attribute _trt, which is the TensorRT counterpart to the PyTorch tensor. The conversion function uses this _trt to add layers to the TensorRT network, and then sets the _trt attribute for relevant output tensors. Once the model is fully executed, the final tensors returns are marked as outputs of the TensorRT network, and the optimized TensorRT engine is built.

How to add (or override) a converter

Here we show how to add a converter for the ReLU module using the TensorRT python API.

import tensorrt as trt
from torch2trt import tensorrt_converter

def convert_ReLU(ctx):
    input = ctx.method_args[1]
    output = ctx.method_return
    layer =, type=trt.ActivationType.RELU)  
    output._trt = layer.get_output(0)

The converter takes one argument, a ConversionContext, which will contain the following

  • - The TensorRT network that is being constructed.

  • ctx.method_args - Positional arguments that were passed to the specified PyTorch function. The _trt attribute is set for relevant input tensors.

  • ctx.method_kwargs - Keyword arguments that were passed to the specified PyTorch function.

  • ctx.method_return - The value returned by the specified PyTorch function. The converter must set the _trt attribute where relevant.

Please see this folder for more examples.

See also

  • JetBot - An educational AI robot based on NVIDIA Jetson Nano

  • JetRacer - An educational AI racecar using NVIDIA Jetson Nano

  • JetCam - An easy to use Python camera interface for NVIDIA Jetson

  • JetCard - An SD card image for web programming AI projects with NVIDIA Jetson Nano

Popular Pytorch Projects
Popular Classification Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.