Skip to content

Using Yolov8n, image detection was trained,and the prediction result was 0. #28

Description

@lijianxin520

Using Yolov8n, image detection was trained. The training results are as follows:

Then, the training model was used for prediction, and the prediction result was 0.
What could be the reason for this?
Parameter configuration is as follows:
Config config = new Config
{
DeviceType = DeviceType.CPU,
ScalarType = ScalarType.Float16,
//RootPath = @"Assets\DataSets\dotav1",
RootPath = @"Assets\DataSets\test2",
TrainDataPath = "train.txt",
ValDataPath = "val.txt",
YoloType = YoloType.Yolov8,
YoloSize = YoloSize.n,
TaskType = TaskType.Detection,
ImageProcessType = ImageProcessType.Letterbox,
ImageSize = 640,
BatchSize = 8,
NumberClass = 3,
PredictThreshold = 0.5f,
IouThreshold = 0.7f,
Workers = 1,
Epochs = 80,
LearningRate = 5e-5f, // 0.00005 1e-4f,
Patience = 20,

};

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions