You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Using CUDA device0 _CudaDeviceProperties(name='Tesla P100-PCIE-16GB', total_memory=16276MB)
device1 _CudaDeviceProperties(name='Tesla P100-PCIE-16GB', total_memory=16276MB)
Class Images Targets P R mAP@0.5 F1: 100%|█████████████████████████████████████████████████████████████████████████████| 1/1 [00:11<00:00, 11.50s/it]
all 39 65 0.962 0.785 0.782 0.864
Using CUDA device0 _CudaDeviceProperties(name='Tesla P100-PCIE-16GB', total_memory=16276MB)
device1 _CudaDeviceProperties(name='Tesla P100-PCIE-16GB', total_memory=16276MB)
Class Images Targets P R mAP@0.5 F1: 100%|███████████████████████████████████████████████████████████████████████████| 10/10 [00:10<00:00, 1.09s/it]
all 39 65 0.927 0.785 0.777 0.85
Do you know where the problem is? Thank you very much!
The text was updated successfully, but these errors were encountered:
@pprp good investigation! This is actually not a bug, it is an effect of the rectangular inference that test.py runs. It orders batches by aspect ratio, grouping images of similar shapes into a batch, and applying the minimum letterbox required to that batch. That means that each of the batches have different letterboxed shapes. See rectangular inference #232
When you do batch-size 64, likely a square letterbox is applied. In any case, the differences should be very minor, as you see. If you had a larger group of test images your results would be even closer I believe.
🐛 Bug
@glenn-jocher Thank you for your excellent work, but I encountered a bug.
I only have 39 pictures for testing.
If batch size > total number of pictures, the F1 score is 86.4% and map is 78.2%.
If batch size <total number of pictures, the F1 score is 85% and the map is 77.7%.
To Reproduce
Steps to reproduce the behavior:
I got:
I got:
Do you know where the problem is? Thank you very much!
The text was updated successfully, but these errors were encountered: