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

add yolov3-spp-ultralytics.pt

This commit is contained in:
Glenn Jocher 2020-02-16 23:12:07 -08:00
parent 57798278ad
commit e840b7c781
6 changed files with 27 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
README.md
View File

@ -139,39 +139,39 @@ Success: converted 'weights/yolov3-spp.pt' to 'converted.weights'
# mAP # mAP
```bash ```bash
python3 test.py --weights ... --cfg ... $ python3 test.py --cfg yolov3-spp.cfg --weights yolov3-spp-ultralytics.pt
``` ```
- mAP@0.5 run at `--iou-thr 0.5`, mAP@0.5...0.95 run at `--iou-thr 0.7` - mAP@0.5 run at `--iou-thr 0.5`, mAP@0.5...0.95 run at `--iou-thr 0.7`
- YOLOv3-SPP ultralytics is `ultralytics68.pt` with `yolov3-spp.cfg`
- Darknet results: https://arxiv.org/abs/1804.02767 - Darknet results: https://arxiv.org/abs/1804.02767
<i></i> |Size |COCO mAP<br>@0.5...0.95 |COCO mAP<br>@0.5 <i></i> |Size |COCO mAP<br>@0.5...0.95 |COCO mAP<br>@0.5
--- | --- | --- | --- --- | --- | --- | ---
YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**YOLOv3-SPP ultralytics** |320 |14.0<br>28.7<br>30.5<br>**35.6** |29.1<br>51.8<br>52.3<br>**55.4** YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**[YOLOv3-SPP-ultralytics](https://drive.google.com/open?id=1UcR-zVoMs7DH5dj3N1bswkiQTA4dmKF4)** |320 |14.0<br>28.7<br>30.5<br>**36.3** |29.1<br>51.8<br>52.3<br>**55.5**
YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**YOLOv3-SPP ultralytics** |416 |16.0<br>31.2<br>33.9<br>**39.1** |33.0<br>55.4<br>56.9<br>**59.6** YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**[YOLOv3-SPP-ultralytics](https://drive.google.com/open?id=1UcR-zVoMs7DH5dj3N1bswkiQTA4dmKF4)** |416 |16.0<br>31.2<br>33.9<br>**39.8** |33.0<br>55.4<br>56.9<br>**59.6**
YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**YOLOv3-SPP ultralytics** |512 |16.6<br>32.7<br>35.6<br>**40.6** |34.9<br>57.7<br>59.5<br>**61.4** YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**[YOLOv3-SPP-ultralytics](https://drive.google.com/open?id=1UcR-zVoMs7DH5dj3N1bswkiQTA4dmKF4)** |512 |16.6<br>32.7<br>35.6<br>**41.3** |34.9<br>57.7<br>59.5<br>**61.3**
YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**YOLOv3-SPP ultralytics** |608 |16.6<br>33.1<br>37.0<br>**41.1** |35.4<br>58.2<br>60.7<br>**61.7** YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br>**[YOLOv3-SPP-ultralytics](https://drive.google.com/open?id=1UcR-zVoMs7DH5dj3N1bswkiQTA4dmKF4)** |608 |16.6<br>33.1<br>37.0<br>**41.7** |35.4<br>58.2<br>60.7<br>**61.5**
```bash ```bash
$ python3 test.py --img-size 608 --iou-thr 0.6 --weights ultralytics68.pt --cfg yolov3-spp.cfg $ python3 test.py --cfg yolov3-spp.cfg --weights yolov3-spp-ultralytics.pt --img 608
Namespace(batch_size=32, cfg='yolov3-spp.cfg', conf_thres=0.001, data='data/coco2014.data', device='', img_size=608, iou_thres=0.6, save_json=True, task='test', weights='ultralytics68.pt') Namespace(batch_size=32, cfg='yolov3-spp.cfg', conf_thres=0.001, data='data/coco2014.data', device='', img_size=608, iou_thres=0.6, save_json=True, single_cls=False, task='test', weights='last54.pt')
Using CUDA device0 _CudaDeviceProperties(name='Tesla V100-SXM2-16GB', total_memory=16130MB) Using CUDA device0 _CudaDeviceProperties(name='Tesla P100-PCIE-16GB', total_memory=16280MB)
Class Images Targets P R mAP@0.5 F1: 100% 157/157 [03:30<00:00, 1.16it/s]
all 5e+03 3.51e+04 0.0353 0.891 0.606 0.0673 Class Images Targets P R mAP@0.5 F1: 100% 157/157 [04:25<00:00, 1.04it/s]
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.409 all 5e+03 3.51e+04 0.0467 0.886 0.607 0.0875
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.415
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.615 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.615
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.437 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.443
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.242 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.245
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.448 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.458
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.519 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.531
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.337 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.341
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.559
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.612 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.611
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.438 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.441
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.658 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.658
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.746 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.748
``` ```
# Reproduce Our Results # Reproduce Our Results

2
detect.py
View File

@ -159,7 +159,7 @@ if __name__ == '__main__':
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='*.cfg path') parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='*.cfg path')
parser.add_argument('--names', type=str, default='data/coco.names', help='*.names path') parser.add_argument('--names', type=str, default='data/coco.names', help='*.names path')
parser.add_argument('--weights', type=str, default='weights/ultralytics68.pt', help='path to weights file') parser.add_argument('--weights', type=str, default='weights/yolov3-spp-ultralytics.pt', help='weights path')
parser.add_argument('--source', type=str, default='data/samples', help='source') # input file/folder, 0 for webcam parser.add_argument('--source', type=str, default='data/samples', help='source') # input file/folder, 0 for webcam
parser.add_argument('--output', type=str, default='output', help='output folder') # output folder parser.add_argument('--output', type=str, default='output', help='output folder') # output folder
parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)') parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')

3
models.py
View File

@ -434,7 +434,8 @@ def attempt_download(weights):
'darknet53.conv.74': '1WUVBid-XuoUBmvzBVUCBl_ELrzqwA8dJ', 'darknet53.conv.74': '1WUVBid-XuoUBmvzBVUCBl_ELrzqwA8dJ',
'yolov3-tiny.conv.15': '1Bw0kCpplxUqyRYAJr9RY9SGnOJbo9nEj', 'yolov3-tiny.conv.15': '1Bw0kCpplxUqyRYAJr9RY9SGnOJbo9nEj',
'ultralytics49.pt': '158g62Vs14E3aj7oPVPuEnNZMKFNgGyNq', 'ultralytics49.pt': '158g62Vs14E3aj7oPVPuEnNZMKFNgGyNq',
'ultralytics68.pt': '1Jm8kqnMdMGUUxGo8zMFZMJ0eaPwLkxSG'} 'ultralytics68.pt': '1Jm8kqnMdMGUUxGo8zMFZMJ0eaPwLkxSG',
'yolov3-spp-ultralytics.pt': '1UcR-zVoMs7DH5dj3N1bswkiQTA4dmKF4'}
file = Path(weights).name file = Path(weights).name
if file in d: if file in d:

2
test.py
View File

@ -210,7 +210,7 @@ if __name__ == '__main__':
parser = argparse.ArgumentParser(prog='test.py') parser = argparse.ArgumentParser(prog='test.py')
parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='*.cfg path') parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='*.cfg path')
parser.add_argument('--data', type=str, default='data/coco2014.data', help='*.data path') parser.add_argument('--data', type=str, default='data/coco2014.data', help='*.data path')
parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file') parser.add_argument('--weights', type=str, default='weights/yolov3-spp-ultralytics.pt', help='weights path')
parser.add_argument('--batch-size', type=int, default=32, help='size of each image batch') parser.add_argument('--batch-size', type=int, default=32, help='size of each image batch')
parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)') parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold') parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')

2
train.py
View File

@ -406,7 +406,7 @@ if __name__ == '__main__':
parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters') parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket') parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
parser.add_argument('--cache-images', action='store_true', help='cache images for faster training') parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
parser.add_argument('--weights', type=str, default='weights/ultralytics68.pt', help='initial weights') parser.add_argument('--weights', type=str, default='weights/yolov3-spp-ultralytics.pt', help='initial weights path')
parser.add_argument('--arc', type=str, default='default', help='yolo architecture') # default, uCE, uBCE parser.add_argument('--arc', type=str, default='default', help='yolo architecture') # default, uCE, uBCE
parser.add_argument('--name', default='', help='renames results.txt to results_name.txt if supplied') parser.add_argument('--name', default='', help='renames results.txt to results_name.txt if supplied')
parser.add_argument('--device', default='', help='device id (i.e. 0 or 0,1 or cpu)') parser.add_argument('--device', default='', help='device id (i.e. 0 or 0,1 or cpu)')

2
utils/utils.py
View File

@ -369,7 +369,7 @@ def compute_loss(p, targets, model, giou_flag=True): # predictions, targets, mo
tcls, tbox, indices, anchor_vec = build_targets(model, targets) tcls, tbox, indices, anchor_vec = build_targets(model, targets)
h = model.hyp # hyperparameters h = model.hyp # hyperparameters
arc = model.arc # # (default, uCE, uBCE) detection architectures arc = model.arc # # (default, uCE, uBCE) detection architectures
red = 'sum' # Loss reduction (sum or mean) red = 'mean' # Loss reduction (sum or mean)
# Define criteria # Define criteria
BCEcls = nn.BCEWithLogitsLoss(pos_weight=ft([h['cls_pw']]), reduction=red) BCEcls = nn.BCEWithLogitsLoss(pos_weight=ft([h['cls_pw']]), reduction=red)