Bobo-y / flexible-yolov5

More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

Bobo-y/flexible-yolov5 Issues

SE and CBAM module implementation error
Updated 19 days ago
Quantization error
Updated a month ago1
delete
Closed 2 months ago
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？
Closed 3 months ago30
repvgg做为backbone时，保存的pt模型是多分支结构还是单路结构？
Closed 4 months ago5
Error help please
Closed 7 months ago3
Drop layer
Closed 7 months ago1
求教
Closed 8 months ago1
error during compile
Closed 10 months ago11
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)
Closed a year ago5
使用mobilenetv3作为主干网络，无法导出onnx，并且没有错误提示。
Closed a year ago5
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
Closed a year ago2
Add True negative data to training dataset
Closed a year ago2
请问模型的flops应该在哪输出
Closed a year ago3
About the Resume
Closed a year ago1
作者大大是否有跟进YOLOv5 V7.0版本实例分割功能的打算？
Closed a year ago2
0 gradients 问题
Closed 2 years ago2
请问yaml文件中有关head的网络结构
Closed a year ago4
有关head的问题
Closed a year ago3
更改backbone
Closed a year ago1
数据增强
Closed a year ago1
ModuleNotFoundError: No module named 'od.models'; 'od' is not a package
Closed 2 years ago1
Can add the score display for the prediction box in detector.py
Closed 2 years ago2
MobilenetV3主干网络中scale的作用是什么？
Closed 2 years ago4
YOLOv5中验证代码存在一定问题，需要更改
Closed 2 years ago1
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
Closed 2 years ago2
想咨询一下如何在验证图片的时候显示置信度呢
Closed 2 years ago1
请问v2分支是基于yolov5 6.1版本吗？
Closed 2 years ago1
关于模型搭建和初始化权重时的若干问题
Closed 2 years ago3
Why is the Swin-Transformer model only outputting 2nd features onwards?
Closed 2 years ago12
u版现在yolov5s的map为37.4，但本项目只有35
Closed 2 years ago2
@Bobo-y
Closed 2 years ago2
Tips on training using Swin-T on YOLO?
Closed 2 years ago4
does swin transformer have to do input normalization?
Closed 2 years ago3
采用swin transoforme的预训练权重问题
Closed 2 years ago9
Can't I use another pre-trained model after changing the backbone?
Closed 2 years ago4
如何添加FPN层以实现更好的小目标检出
Closed 2 years ago2
Using EfficientNet backbone leads to precision and recall equal to zero
Closed 2 years ago14
What is the map value of using swin-transformer as backbone?
Closed 2 years ago
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
Closed 2 years ago1
TypeError: load() missing 1 required positional argument: 'Loader'
Closed 2 years ago7
Squeeze and Excitation Conv vs Linear
Closed 2 years ago7
GNN is Graph Neural Network?
Closed 2 years ago1
cls_loss is always 0
Closed 2 years ago2
Can you share some weights to run the network?
Closed 2 years ago3
windows下：模型和数据集的yaml文件找不到
Closed 2 years ago3
ModuleNotFoundError: No module named 'od.models'; 'od' is not a package
Closed 2 years ago3
c++ sample code for trt inference
Closed 2 years ago35
似乎因为模型细微错误导致精度低2个点！？
Closed 2 years ago14
un-reproducible result
Closed 2 years ago1