tensorrt_demos icon indicating copy to clipboard operation
tensorrt_demos copied to clipboard

TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet

Results 27 tensorrt_demos issues
Sort by recently updated
recently updated
newest added

I have finished coverting yolo to onnx but when converting onnx to tensorrt I have problem: [W] If this is not the desired behavior, please modify the weights or retrain...

Does it also support DRIVE AGX Orin?

When I use do_inference_v2, I need the reshape operation to get the correct result, but I find that the reshape operation takes a lot of time, which defeats the purpose...

I'm using jetson AGX Orin for my project. I installed jetpack 5.1.2 CUDA 11.4, CUDNN 8.6.0 and TensorRT 8.5.2.2 with nvidia-sdkmanager. While I follow the instruction of this project, the...

Hi my create yolo code: trt_yolo = yolo_with_plugins.TrtYOLO(trt_file_path, category_num, letter_box, ctx) When I call trt_yolo.__del__() and trt_yolo = None, memory is not freed How do I actively free up memory?

Does this code work with AGX Orin? I am facing a lot of issues while I try to run it on Orin EVK.

When running `python3 onnx_to_tensorrt.py -m yolov4-416 --int8` An error occurs ``` [07/12/2023-11:55:50] [TRT] [E] 10: Could not find any implementation for node 002_convolutional. [07/12/2023-11:55:50] [TRT] [E] 10: [optimizer.cpp::computeCosts::3869] Error Code...

Hi, I use my own pruned yolov4.weights and .cfg which was trained on three class(person、vehicle、bike), and I try to covert the .weights to .trt according to the Demo4 But there...

I used the example given in https://github.com/jkjung-avt/tensorrt_demos#demo-5-yolov4 to convert my tiny yolov3 to int8 but the issue is that when I use --verbose on onnx_to_tensorrt.py step I see that the...

Hello! Your work is really admirable. Is there any possibility you could share a yolov3 onnx implementation in a suitable version for a previous tensorrt version such as 5 to...