25/5000 yolov8 classification model, why can't it recognize anything after training

Discussion
,
1

A strange phenomenon occurred when I was training yolov8’s classification model. My samples are divided into smiley faces and non-smiley faces. The number of smiley faces and non-smiley faces is the same, both being 11w, and the samples have been carefully checked. The samples are almost clean and not mixed with other samples. The smallest image size of the sample is not less than 29 pixels, and the largest is not more than 1080 pixels. By the 11th round of training, the top acc was 0.97. But when I used my trained model to reason, it didn’t recognize either a smiley face or a non-smiley face. When I trained with 20,000 images before, the effect was OK, and the reasoning code was the same. To make the model better, I increased the sample to 110,000, and the reasoning code was still used before. Excuse me, what is the reason for this? I’m open to any suggestions, thank you very much!

Here’s my code:

from ultralytics import YOLO

if name == ‘main’:

model_path = “/root/yolo_train/yolov8s-cls.pt”

model=YOLO(model_path)

model.train(

Data file path, such as coco128.yaml, the classification task can directly write data set folder path

data=‘/root/datasets/Smile_data’,

imgsz=224, # image size

device=0, # Run the device

batch=128,# Number of images per batch (-1 indicates automatic batch)

Scale = 0.3,

Degrees = 0.2,

Hsv_s = 0.3,

Hsv_v = 0.3,

epochs=40,# Number of training cycles

Flipud = 0.3,

)

2

Hello hhhFuture,

Thanks for reaching out and detailing your experience with training the YOLO11 classification model. It’s great to hear you achieved a high top accuracy in training.

Since you’ve previously had success with a smaller dataset and are now encountering issues with a larger one, it’s worth ensuring your dataset structure is correctly set up with train and test directories, and subdirectories for each class as described in Image Classification Datasets Overview.

Also, double check the data argument points correctly to your dataset’s root directory. You can verify your configuration settings are correctly applied as shown in the YOLO Common Issues guide.

If the issue persists, you might want to check if updating to the most recent version of the Ultralytics package helps, as sometimes updates can resolve unexpected issues.

1 Like
3

Thank you very much for your reply. My problem has been solved. It’s not a problem with the model, it’s not a problem with the training code, it’s because I wrote the inference code wrong. The label name of the category is forgotten to change, causing it to always be False when judging

1 Like
4

Thanks for the update, @hhhFuture! It’s great to hear that you’ve resolved the issue and identified the cause in your inference code.

Happy coding with YOLO!