yolov5_obb
yolov5_obb copied to clipboard
Performance of yolov5m_obb on dota.
I use yolov5m_obb model, following the steps below: python val.py --data 'data/dotav1_poly.yaml' --img 1024 --conf 0.01 --iou 0.4 --task 'test' --batch 16 --save-json --name 'dotav1_test_split' python tools/TestJson2VocClassTxt.py --json_path 'runs/val/dotav1_test_split/best_obb_predictions.json' --save_path 'runs/val/dotav1_test_split/obb_predictions_Txt' python DOTA_devkit/ResultMerge_multi_process.py --scrpath 'runs/val/dotav1_test_split/obb_predictions_Txt' --dstpath 'runs/val/dotav1_test_split/obb_predictions_Txt_Merged' zip the poly format results files and submit it to https://captain-whu.github.io/DOTA/evaluation.html
Get the results below: mAP: 0.7452222870821154 ap of each class: plane:0.8939872082266263, baseball-diamond:0.8576925863003493, bridge:0.5323582124113629, ground-track-field:0.6304663951346061, small-vehicle:0.7537598585856788, large-vehicle:0.8409270519498024, ship:0.8653830558829161, tennis-court:0.9070543864924884, basketball-court:0.7982063493291973, storage-tank:0.881254389430272, soccer-ball-field:0.632606259031958, roundabout:0.4012500797648203, harbor:0.7546234893412097, swimming-pool:0.7339786931293439, helicopter:0.6947862912210991
Hello, why is the txt file I generated a number with a size of about 1? P2803 0.76 0.4 0.5 0.4 0.5 0.4 0.5 0.3 0.5 P2803 0.75 0.7 0.9 0.8 0.9 0.7 1.0 0.7 0.9 P2803 0.74 0.7 0.8 0.7 0.8 0.6 0.9 0.6 0.9 P2803 0.74 0.1 0.7 0.2 0.8 0.1 0.9 0.1 0.9 P2803 0.73 0.4 0.9 0.4 0.9 0.3 1.0 0.3 1.0 P2803 0.73 0.2 0.8 0.2 0.8 0.1 0.9 0.1 0.9 P2803 0.73 0.1 0.7 0.1 0.7 0.1 0.9 0.0 0.8 P2803 0.72 0.6 0.7 0.6 0.7 0.6 0.8 0.6 0.8 P2803 0.72 0.8 0.9 0.8 0.9 0.7 1.0 0.7 1.0 P2803 0.72 0.4 1.3 0.4 1.3 0.3 1.4 0.3 1.4 P2803 0.72 0.7 0.8 0.7 0.8 0.7 0.9 0.6 0.9 P2803 0.71 0.6 1.0 0.7 1.1 0.6 1.2 0.5 1.1 P2803 0.71 0.2 0.4 0.3 0.5 0.2 0.5 0.2 0.5 P2803 0.71 1.3 1.0 1.3 1.0 1.2 0.9 1.2 0.9 P2803 0.69 0.3 0.9 0.3 0.9 0.2 1.0 0.2 1.0 P2803 0.69 1.4 0.9 1.4 0.9 1.3 0.8 1.3 0.8 P2803 0.69 0.5 0.6 0.5 0.6 0.4 0.7 0.4 0.7 P2803 0.69 0.2 0.9 0.3 0.9 0.2 0.9 0.2 0.9 P2803 0.69 0.8 0.4 0.7 0.4 0.6 0.3 0.6 0.3 P2803 0.68 0.5 0.3 0.5 0.3 0.4 0.3 0.4 0.3 P2803 0.68 0.3 0.5 0.3 0.5 0.2 0.6 0.2 0.5 P2803 0.68 0.6 1.2 0.7 1.2 0.6 1.3 0.6 1.3 P2803 0.68 0.6 0.7 0.6 0.7 0.5 0.8 0.5 0.8