Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updated --augment sizes and results

This commit is contained in:
Glenn Jocher 2020-04-07 12:27:49 -07:00
parent 4fa3fd2df3
commit 1a511d2906
2 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
README.md
View File

@ -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) 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] 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=0.50:0.95 | area= all | maxDets=100 ] = 0.455
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.644 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.646
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.497 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.496
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.270 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 ] = 0.504 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 ] = 0.577 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 ] = 0.363 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 ] = 0.599 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 ] = 0.668 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 ] = 0.502 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 ] = 0.724 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 ] = 0.805 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 Speed: 21.3/3.0/24.4 ms inference/NMS/total per 640x640 image at batch-size 16
``` ```

8
models.py
View File

@ -241,8 +241,8 @@ class Darknet(nn.Module):
if augment: # https://github.com/ultralytics/yolov3/issues/931 if augment: # https://github.com/ultralytics/yolov3/issues/931
nb = x.shape[0] # batch size nb = x.shape[0] # batch size
x = torch.cat((x, x = torch.cat((x,
torch_utils.scale_img(x.flip(3), 0.9), # flip-lr and scale torch_utils.scale_img(x.flip(3), 0.83), # flip-lr and scale
torch_utils.scale_img(x, 0.7), # scale torch_utils.scale_img(x, 0.67), # scale
), 0) ), 0)
for i, module in enumerate(self.module_list): for i, module in enumerate(self.module_list):
@ -273,9 +273,9 @@ class Darknet(nn.Module):
x = torch.cat(x, 1) # cat yolo outputs x = torch.cat(x, 1) # cat yolo outputs
if augment: # de-augment results if augment: # de-augment results
x = torch.split(x, nb, dim=0) 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[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) x = torch.cat(x, 1)
return x, p return x, p