install tensorrt on colab
#Download TensorRT. [from this link, OR, upload the version you want and replace the file name and dl link here]
!wget -O nv-tensorrt-repo-ubuntu1804-cuda10.0-trt5.1.2.2-rc-20190227_1-1_amd64.deb https://www.dropbox.com/s/45pz13r4e8ip4bl/nv-tensorrt-repo-ubuntu1804-cuda10.0-trt5.1.2.2-rc-20190227_1-1_amd64.deb?dl=0
#Install. [rename the .deb file if you donloaded another verion in the 1st and 2nd line below]
!dpkg -i nv-tensorrt-repo-ubuntu1804-cuda10.0-trt5.1.2.2-rc-20190227_1-1_amd64.deb
!apt-key add /var/nv-tensorrt-repo-cuda10.0-trt5.1.2.2-rc-20190227/7fa2af80.pub
!apt-get update
#not sure if these 2 lines are needed, worked without for me.
#!apt-get install -y --no-install-recommends libnvinfer5=5.1.2-1+cuda10.0
#!apt-get install -y --no-install-recommends libnvinfer-dev=5.1.2-1+cuda10.0
!apt-get install tensorrt
!apt-get install python3-libnvinfer-dev
!apt-get install uff-converter-tf
#Verify installation.
!dpkg -l | grep TensorRT
# i downloaded another version of trt file (cuda11.0-trt7.2.3.4) so for me the output is:
ii graphsurgeon-tf 7.2.3-1+cuda11.0 amd64 GraphSurgeon for TensorRT package
ii libnvinfer-dev 8.0.0-1+cuda11.3 amd64 TensorRT development libraries and headers
ii libnvinfer-plugin-dev 8.0.0-1+cuda11.3 amd64 TensorRT plugin libraries
ii libnvinfer-plugin8 8.0.0-1+cuda11.3 amd64 TensorRT plugin libraries
ii libnvinfer8 8.0.0-1+cuda11.3 amd64 TensorRT runtime libraries
ii libnvonnxparsers-dev 8.0.0-1+cuda11.3 amd64 TensorRT ONNX libraries
ii libnvonnxparsers8 8.0.0-1+cuda11.3 amd64 TensorRT ONNX libraries
ii libnvparsers-dev 8.0.0-1+cuda11.3 amd64 TensorRT parsers libraries
ii libnvparsers8 8.0.0-1+cuda11.3 amd64 TensorRT parsers libraries
ii python3-libnvinfer 8.0.0-1+cuda11.3 amd64 Python 3 bindings for TensorRT
ii python3-libnvinfer-dev 8.0.0-1+cuda11.3 amd64 Python 3 development package for TensorRT
ii uff-converter-tf 7.2.3-1+cuda11.0 amd64 UFF converter for TensorRT package