From 6ca8277de26e5587821bd778bea3a61feb1c8d15 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Wed, 11 Mar 2020 21:30:47 -0700 Subject: [PATCH] updates --- README.md | 2 +- utils/utils.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index b10092a0..3119e277 100755 --- a/README.md +++ b/README.md @@ -159,7 +159,7 @@ Namespace(batch_size=32, cfg='yolov3-spp.cfg', conf_thres=0.001, data='data/coco Using CUDA device0 _CudaDeviceProperties(name='Tesla V100-SXM2-16GB', total_memory=16130MB) Class Images Targets P R mAP@0.5 F1: 100%|█████| 157/157 [02:46<00:00, 1.06s/it] - all 5e+03 3.51e+04 0.822 0.433 0.611 0.551 + all 5e+03 3.51e+04 0.51 0.667 0.611 0.574 Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.419 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.618 diff --git a/utils/utils.py b/utils/utils.py index 52d45918..16e0c8bf 100755 --- a/utils/utils.py +++ b/utils/utils.py @@ -188,7 +188,7 @@ def ap_per_class(tp, conf, pred_cls, target_cls): unique_classes = np.unique(target_cls) # Create Precision-Recall curve and compute AP for each class - pr_score = 0.5 # score to evaluate P and R https://github.com/ultralytics/yolov3/issues/898 + pr_score = 0.1 # score to evaluate P and R https://github.com/ultralytics/yolov3/issues/898 s = [len(unique_classes), tp.shape[1]] # number class, number iou thresholds (i.e. 10 for mAP0.5...0.95) ap, p, r = np.zeros(s), np.zeros(s), np.zeros(s) for ci, c in enumerate(unique_classes):