search

jason-li-831202 / Vehicle-CV-ADAS

The project can achieve FCWS, LDWS, and LKAS functions solely using only visual sensors. using YOLOv5 / YOLOv5-lite / YOLOv6 / YOLOv7 / YOLOv8 / YOLOv9 / EfficientDet and Ultra-Fast-Lane-Detection-v2 .
GNU General Public License v3.0
172 stars 40 forks source link

Trt and onnx files source #1

Open hamaadtahiir opened 1 year ago

hamaadtahiir commented 1 year ago

From where can we get the onnx and/or trt files for the models?

jason-li-831202 commented 1 year ago

you can download YOLOv8 onnx model from https://github.com/ibaiGorordo/ONNX-YOLOv8-Object-Detection image

Ultra-Fast-Lane-Detection-V2 pt nodel from https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2 image , and use convertPytorchToONNX.py in TrafficLaneDetector Folder convet to onnx model.

At last, all onnx model can convert to trt just use convertOnnxToTensorRT.py , remember to modify "onnx_model_path" and "trt_model_path".

nqkhanh2002 commented 1 year ago

Can you provide a link to the drive or zip file or similar, I'm stuck in converting for hours, thanks for that.

jason-li-831202 commented 1 year ago

I can provide a temporary link : https://drive.google.com/drive/folders/1lo_nFwvrm9ey0dj6FbyAaBxCzowol77_?usp=sharing

Perhaps you can share some difficulties you encountered during the converting?

nqkhanh2002 commented 1 year ago

@jason-li-831202 I'm having a hard time working with the NIVIDA GPU so I'm putting the code on colab and it looks good. By the way can I get the test file for you, I have tried searching the internet like no accident videos and the road conditions are pretty good. Thank you very much

balajik27 commented 1 year ago

you can download YOLOv8 onnx model from https://github.com/ibaiGorordo/ONNX-YOLOv8-Object-Detection image

Ultra-Fast-Lane-Detection-V2 pt nodel from https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2 image , and use convertPytorchToONNX.py in TrafficLaneDetector Folder convet to onnx model.

At last, all onnx model can convert to trt just use convertOnnxToTensorRT.py , remember to modify "onnx_model_path" and "trt_model_path".

where i can get yolov8m-coco.onnx file, from the link u have given i didnt get that file.

balajik27 commented 1 year ago

I can provide a temporary link : https://drive.google.com/drive/folders/1lo_nFwvrm9ey0dj6FbyAaBxCzowol77_?usp=sharing

Perhaps you can share some difficulties you encountered during the converting?

this link shows 404 error

Jilin-Cancer commented 11 months ago

I can provide a temporary link : https://drive.google.com/drive/folders/1lo_nFwvrm9ey0dj6FbyAaBxCzowol77_?usp=sharing

Perhaps you can share some difficulties you encountered during the converting?

Hello master, your work is great, I am very interested, your link is invalid, can you share it again, thank you!!!

Sadcato commented 8 months ago

I can provide a temporary link : https://drive.google.com/drive/folders/1lo_nFwvrm9ey0dj6FbyAaBxCzowol77_?usp=sharing

Perhaps you can share some difficulties you encountered during the converting?

Hello master, your work is great, I am very interested, your link is invalid, can you share it again, thank you!!!