tms

YOLOV6 在一些非常明显的前景大目标时无法检测，相比之下YOLOV5要很多好，希望能得到优化

4

https://www.youtube.com/watch?v=yd1DhOf8mW4的1:18秒 可以看出（同样的示例还有很多），YOLOV5要比YOLOV6好不少。YOLOV6对小目标检测不错。但对大目标有很大的问题。我认为这是应当不难得以改善的

convnext onnx export loss precision!

1

**Checklist** 1. I have searched related issues but cannot get the expected help. 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/faq.md) but cannot get the expected help. 3. The bug has...

I try to run gpu model like this: python get_face_boxes_gluoncv.py --gpus 0 I get this: ``` [19:46:58] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take...

how to use tensorboard to visual for yolox?

1

how to use tensorboard to visual for yolox? I couldn't found the tutorials or document for tensorboard with yolox.so,could u help me ?

请问：如何将tensorrt的生成结果（如yolov5)，用在deepstream中？是否需要自己书写相关插件？

How to rubuild trt engine file?

1

I run trt ,and got this error: ~/source/CenterFace/prj-tensorrt# python demo.py [TensorRT] ERROR: INVALID_CONFIG: The engine plan file is generated on an incompatible device, expecting compute 6.1 got compute 7.5, please...

could u support websocket test?

how to convrt mobilenet_yolov3 to caffe model?

1

I try like this: python yolov3_darknet2caffe.py mobilenet_v1_yolov3.cfg mobilenet_v1_yolov3_final.weights mobilenet_yolov3.prototxt mobilenet_yolov3.caffemodel and get an error: F0627 23:02:02.249997 26192 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: ConvolutionDepthwise...

416trt problem,the test picture is all red box.why?is error for prototxt_416 ?

3

I use panbaidu 416 prototxt,and get may red box in dog.jpg.but it's pefect with 608 prototxt. why? I check 608 prototxt diff from 416 protxt,and find only different with resolution...

剪技是针对手的，只能识别出手吗？

4

示例代码使用的手的数据集，那么，如果我想使用Coco80类，需要使用coco数据集处理吗？从你的结果图看上去又不是这样。谢谢