Batch Prediction with NCNNN about ultralytics

[glenn-jocher]

@MABatin hello! Thank you for providing detailed information about the issue you're encountering with batch prediction using the NCNN framework.

The error you're seeing, IndexError: amax(): Expected reduction dim 1 to have non-zero size, typically indicates that the predictions tensor is empty. This can happen if the model does not detect any objects in the input images, possibly due to the confidence threshold being too high or other preprocessing steps affecting the visibility of detectable objects.

Here are a few steps you can try to resolve this issue:

1. Check Input Images: Ensure the images you're using contain clear, detectable objects. You might want to test with different images known to contain easily detectable objects.
2. Adjust Confidence Threshold: Lower the confidence threshold when calling the model to see if it starts detecting objects.
3. Review Preprocessing: Ensure that the preprocessing steps (like resizing and normalization) are appropriate for the NCNN model.

If these steps do not resolve the issue, it would be helpful to look into the model's detailed output right before the non-max suppression step to see if the model is producing any predictions at all.

Please let us know if these suggestions help or if you need further assistance!