benchmark-FP32-FP16-INT8-with-TensorRT

kentaroy47

Benchmark inference speed of CNNs with various quantization methods in Pytorch+TensorRT with Jetson Nano/Xavier

hardware

View on GitHub

56 Stars

3 Forks

56 Watchers

Jupyter Notebook Language

mit License

100 SrcLog Score

Cost to Build

$29.7K

Market Value

$39.5K

How is this calculated?

Growth over time

8 data points · 2021-07-01 → 2026-04-01

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about benchmark-FP32-FP16-INT8-with-TensorRT

Question copied to clipboard

What is the kentaroy47/benchmark-FP32-FP16-INT8-with-TensorRT GitHub project? Description: "Benchmark inference speed of CNNs with various quantization methods in Pytorch+TensorRT with Jetson Nano/Xavier". Written in Jupyter Notebook. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone benchmark-FP32-FP16-INT8-with-TensorRT

Clone via HTTPS

git clone https://github.com/kentaroy47/benchmark-FP32-FP16-INT8-with-TensorRT.git

Clone via SSH

[email protected]:kentaroy47/benchmark-FP32-FP16-INT8-with-TensorRT.git

Download ZIP

Download master.zip

Found an issue?

Report bugs or request features on the benchmark-FP32-FP16-INT8-with-TensorRT issue tracker:

Open GitHub Issues

Similar to benchmark-FP32-FP16-INT8-with-TensorRT

anypixel Marketing-for-Engineers gobot node-serialport openvr platformio-core awesome-electronics Hackintosh-Installer-University librealsense blynk-library lelylan blynk-server periph pyusb awesome-vehicle-security NyuziProcessor go-hardware Neural-Networks-on-Silicon UsbSerial pgtune wrmhl platformio-atom-ide ansible-provisioning w1thermsensor attifyos PipeCNN trezor-mcu node-escpos trezor-agent msi-keyboard