Scaled-YOLOv4-TensorRT

Scaled-YOLOv4-TensorRT copied to clipboard

Hi, 我目前操作YOLOv4-p5時, 我有試著改過Depth, Width的Multiple數字, 但目前看起來在createEngine時, 會卡在這個Layer, bottleneck_CSP2 addBatchNorm2d裡面的addScale, 所以想在此詢問一下, 謝謝 ! 目前下面是出現的log yolov4-p5: /home//scaled_yolov4_inference/Scaled-YOLOv4-TensorRT/yolov4-p5-tensorrt/common.hpp:211: nvinfer1::IScaleLayer* addBatchNorm2d(nvinfer1::INetworkDefinition*, std::map&, nvinfer1::ITensor&, std::__cxx11::string, float): Assertion `scale_1' failed. test_inference.sh: line 6: 12739 Aborted (core dumped)...

ysl19971124

high inference times for initial images

1

It takes a long time to do inference for the first few images. Progressively the inference time reduces. Does engine generation optimize according to the device? Any cache/changes needed to...

saimouli

Parameter check failed at: runtime.cpp::deserializeCudaEngine::30, condition: (blob) != nullptr yolov4-p5: /Scaled-YOLOv4-TensorRT/yolov4-p5-tensorrt/yolov4-p5.cpp:208: int main(int, char**): Assertion `engine != nullptr' failed. Aborted (core dumped)

1

I use your provieded yolov5-wts, but get this error, how can i do, some one help me!

thewq

Please help me out with this one: I try to convert sample yolov4-p6.pt.. after generating wts i receive this: "root@3bc22b0a0ace:/yolo/Scaled-YOLOv4-TensorRT/yolov4-p6-tensorrt/build# ./yolov4-p6 -s 1.0 1.0 Loading weights: ../yolov4-p6.wts Building engine, please...

mate-hegedus

yolov4.weights模型生成wts和engine后，检测什么也没有

1

是不是不支持yolov4.weights格式的模型？

wulixunhua

请问一下，这个下载好的yolov4-tiny.wts可以在Xavier AGX 板卡上直接用来生成yolov4-tiny.engine吗？谢谢

2

ShitaoChen

get_wts.py do not work for yolov4-tiny

1

Hi, having torch v 1.8 on jetson device, I am unable to get a .wts file. I think that there is a mismatch between the model it expects and the...

batrlatom

Error in "Build and Run" when execute 'make'

1

Hey This error happened when I execute 'make' in Build and run section ? How to solve ? Thanks 

huyhoangle86

你好 运行yolov4-tiny-tensorrt这个例子时，运行gen_wts.py报错

1

Traceback (most recent call last): File "gen_wts.py", line 13, in model.load_state_dict(torch.load(weights, map_location=device)['model']) File "/home/sany/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for Darknet: Missing key(s) in...

HeuMindFusion

How can I use a webcam in this object?

2

I wanna use a webcam to detect(real-time) what can I do?

TweepingH