Bobo-y/flexible-yolov5

Issues

• Quantization error

  #159 opened 19 days ago by ratom
  1

• SE and CBAM module implementation error

  #160 opened a month ago by ratom
  0

• delete

  #158 opened 3 months ago by Bobo-y
  0

• 使用repvgg训练，然后参数deploy为true，即改成单路推理结构时，出现训练无法收敛的情况？是不是由于每一次训练都直接转成了单路结构的原因？

  #157 opened 4 months ago by wjli-debug
  30

• repvgg做为backbone时，保存的pt模型是多分支结构还是单路结构？

  #156 opened 4 months ago by wjli-debug
  5

• Error help please

  #154 opened 7 months ago by ratom
  3

• Drop layer

  #153 opened 8 months ago by ratom
  1

• 求教

  #152 opened 8 months ago by iu110
  1

• error during compile

  #151 opened a year ago by PraveenMNaik
  11

• ONNX: export failure: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument other in method wrapper__equal)

  #150 opened a year ago by taoxunqiang
  5

• 使用mobilenetv3作为主干网络，无法导出onnx，并且没有错误提示。

  #147 opened a year ago by LaoJiuMoYang
  5

• 使用替换backbone为swimtransformer的yolov5时，detect的时候，只能框住物体，不能显示置信度和种类

  #149 opened a year ago by richgx
  2

• Add True negative data to training dataset

  #148 opened a year ago by a227799770055
  2

• 请问模型的flops应该在哪输出

  #144 opened a year ago by cds221
  3

• About the Resume

  #146 opened a year ago by zhaoxixixi
  1

• 作者大大是否有跟进YOLOv5 V7.0版本实例分割功能的打算？

  #145 opened a year ago by pengcheng4181452
  2

• 0 gradients 问题

  #138 opened 2 years ago by huangzizheng01
  2

• 请问yaml文件中有关head的网络结构

  #143 opened a year ago by cds221
  4

• 有关head的问题

  #142 opened a year ago by cds221
  3

• 更改backbone

  #141 opened a year ago by AustinzzZ-1997
  1

• 数据增强

  #140 opened a year ago by cds221
  1

• ModuleNotFoundError: No module named 'od.models'; 'od' is not a package

  #139 opened 2 years ago by Yolo-kang
  1

• Can add the score display for the prediction box in detector.py

  #135 opened 2 years ago by songyangsun
  2

• MobilenetV3主干网络中scale的作用是什么？

  #134 opened 2 years ago by LaoJiuMoYang
  4

• YOLOv5中验证代码存在一定问题，需要更改

  #132 opened 2 years ago by Huster-Hq
  1

• 我用HRNet32作Backbone时，训练完出现了RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!这个问题

  #131 opened 2 years ago by ChenShuai-CA
  2

• 想咨询一下如何在验证图片的时候显示置信度呢

  #129 opened 2 years ago by jiezai18
  1

• 请问v2分支是基于yolov5 6.1版本吗？

  #130 opened 2 years ago by cds221
  1

• 关于模型搭建和初始化权重时的若干问题

  #128 opened 2 years ago by danchaofan-git
  3

• Why is the Swin-Transformer model only outputting 2nd features onwards?

  #126 opened 2 years ago by sarmientoj24
  12

• u版现在yolov5s的map为37.4，但本项目只有35

  #122 opened 2 years ago by nobody-cheng
  2

• @Bobo-y

  #123 opened 2 years ago by farzadimanpour
  2

• Tips on training using Swin-T on YOLO?

  #125 opened 2 years ago by sarmientoj24
  4

• does swin transformer have to do input normalization?

  #124 opened 2 years ago by sarmientoj24
  3

• 采用swin transoforme的预训练权重问题

  #121 opened 2 years ago by cds221
  9

• Can't I use another pre-trained model after changing the backbone?

  #115 opened 2 years ago by yuhao-q
  4

• 如何添加FPN层以实现更好的小目标检出

  #97 opened 2 years ago by cydiachen
  2

• Using EfficientNet backbone leads to precision and recall equal to zero

  #118 opened 2 years ago by farzadips
  14

• What is the map value of using swin-transformer as backbone?

  #120 opened 2 years ago by cds221
  0

• RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

  #111 opened 2 years ago by Samuelmicer
  1

• TypeError: load() missing 1 required positional argument: 'Loader'

  #119 opened 2 years ago by Tareq361
  7

• Squeeze and Excitation Conv vs Linear

  #117 opened 2 years ago by seermer
  7

• GNN is Graph Neural Network?

  #116 opened 2 years ago by daiyuanm
  1

• cls_loss is always 0

  #113 opened 2 years ago by a227799770055
  2

• Can you share some weights to run the network?

  #112 opened 2 years ago by qianmin
  3

• windows下：模型和数据集的yaml文件找不到

  #110 opened 2 years ago by StandGreat
  3

• ModuleNotFoundError: No module named 'od.models'; 'od' is not a package

  #109 opened 2 years ago by StandGreat
  3

• c++ sample code for trt inference

  #98 opened 2 years ago by kaishijeng
  35

• 似乎因为模型细微错误导致精度低2个点！？

  #96 opened 2 years ago by LinB203
  14

• un-reproducible result

  #101 opened 2 years ago by wykhan
  1