如何编辑yolov5模型中自定义类的yaml文件？

Question

我正在为自定义数据集训练yolov5模型。我只有一节课。我已将.yaml文件更改为数据，如下所示。

train: /content/yolov5/DataSet/ForYolov5/images/train  # train images (relative to 'path') 128 images
val: /content/yolov5/DataSet/ForYolov5/images/test  # val images (relative to 'path') 128 images
test:  # test images (optional)

# Classes
names:
  0: vehicle

但这辆车的名字并没有显示在探测器上。只显示“0”。我也尝试了以下格式。但它会抛出错误。

#Classes
nc:1
names:['vehicle']

任何帮助都将不胜感激。

Answer 1

在创建自定义数据集(我认为您有2个文件夹序列和有效)之后，您也应该使用以下代码自定义YAML文件：

%cat data.yaml
# define number of classes based on YAML
# data.yaml contains the information about number of classes and their labels required for this project
import yaml
with open("data.yaml", 'r') as stream:
    num_classes = str(yaml.safe_load(stream)['nc'])
    #customize iPython writefile so we can write variables
from IPython.core.magic import register_line_cell_magic

@register_line_cell_magic
def writetemplate(line, cell):
    with open(line, 'w') as f:
        f.write(cell.format(**globals()))

%%writetemplate /content/dataset/data.yaml

train: /content/dataset/train/images/
val:  /content/dataset/valid/images/

nc: 1 #define number of class = 1
names: ['vehicule'] #class label

然后，您必须检查架构文件中的类是否已更改：

%cat /content/yolov5/models/yolov5n.yaml
%%writetemplate /content/yolov5/models/yolov5n.yaml

# Parameters
nc: 1 # number of classes