fasterrcnn-pytorch-training-pipeline
fasterrcnn-pytorch-training-pipeline copied to clipboard
sovit-123
How evaluate metrics
hi guys i hope you are doing well please i need to know how you find these results 👍
num classes=10 training images = 14 298 valid images= 4057 img
epochs 10
IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.064 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.128 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.059 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.067 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.078 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.116 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.098 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.140 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.146 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.218 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.164 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.177
BEST VALIDATION mAP: 0.06794259734989389
These results are quite poor. Higher the mAP, higher the detection accuracy. Similarly for precision to identify the object. Your scores are very low. Might be train for a bit longer and see how it goes.
