From 1a511d2906df65db7c67aa74a1c1b41428cac1c5 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Tue, 7 Apr 2020 12:27:49 -0700 Subject: [PATCH] updated --augment sizes and results --- README.md | 26 +++++++++++++------------- models.py | 8 ++++---- 2 files changed, 17 insertions(+), 17 deletions(-) diff --git a/README.md b/README.md index c3550840..7e51f15e 100755 --- a/README.md +++ b/README.md @@ -137,20 +137,20 @@ Namespace(augment=True, batch_size=16, cfg='cfg/yolov3-spp.cfg', conf_thres=0.00 Using CUDA device0 _CudaDeviceProperties(name='Tesla V100-SXM2-16GB', total_memory=16130MB) Class Images Targets P R mAP@0.5 F1: 100%|█████████| 313/313 [03:00<00:00, 1.74it/s] - all 5e+03 3.51e+04 0.373 0.744 0.637 0.491 + all 5e+03 3.51e+04 0.375 0.743 0.639 0.493 - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.454 - Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.644 - Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.497 - Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.270 - Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.504 - Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.577 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.363 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.599 - Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.668 - Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.502 - Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.724 - Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.805 + Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.455 + Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.646 + Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.496 + Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.263 + Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.500 + Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.596 + Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.362 + Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.597 + Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.666 + Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.491 + Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.719 + Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.808 Speed: 21.3/3.0/24.4 ms inference/NMS/total per 640x640 image at batch-size 16 ``` diff --git a/models.py b/models.py index 2f93ff22..07db7b1b 100755 --- a/models.py +++ b/models.py @@ -241,8 +241,8 @@ class Darknet(nn.Module): if augment: # https://github.com/ultralytics/yolov3/issues/931 nb = x.shape[0] # batch size x = torch.cat((x, - torch_utils.scale_img(x.flip(3), 0.9), # flip-lr and scale - torch_utils.scale_img(x, 0.7), # scale + torch_utils.scale_img(x.flip(3), 0.83), # flip-lr and scale + torch_utils.scale_img(x, 0.67), # scale ), 0) for i, module in enumerate(self.module_list): @@ -273,9 +273,9 @@ class Darknet(nn.Module): x = torch.cat(x, 1) # cat yolo outputs if augment: # de-augment results x = torch.split(x, nb, dim=0) - x[1][..., :4] /= 0.9 # scale + x[1][..., :4] /= 0.83 # scale x[1][..., 0] = img_size[1] - x[1][..., 0] # flip lr - x[2][..., :4] /= 0.7 # scale + x[2][..., :4] /= 0.67 # scale x = torch.cat(x, 1) return x, p