Closed ahong007007 closed 3 years ago
@ahong007007 yolo.py has built-in profiling:
$ python models/yolo.py --cfg yolov5s.yaml --profile
YOLOv5 🚀 v5.0-458-g6b02015 torch 1.9.0 CPU
Model Summary: 283 layers, 7276605 parameters, 7276605 gradients, 17.1 GFLOPs
time (ms) GFLOPs params module
22.62 0.72 3520 models.common.Focus
17.97 0.95 18560 models.common.Conv
38.30 0.96 18816 models.common.C3
13.23 0.95 73984 models.common.Conv
35.74 2.01 156928 models.common.C3
11.31 0.95 295424 models.common.Conv
28.18 2.00 625152 models.common.C3
11.92 0.94 1180672 models.common.Conv
18.97 0.53 656896 models.common.SPP
14.34 0.95 1182720 models.common.C3
1.83 0.11 131584 models.common.Conv
0.24 0.00 0 torch.nn.modules.upsampling.Upsample
0.46 0.00 0 models.common.Concat
17.28 1.16 361984 models.common.C3
2.03 0.11 33024 models.common.Conv
0.33 0.00 0 torch.nn.modules.upsampling.Upsample
1.26 0.00 0 models.common.Concat
22.19 1.16 90880 models.common.C3
6.41 0.47 147712 models.common.Conv
0.27 0.00 0 models.common.Concat
14.58 0.95 296448 models.common.C3
6.27 0.47 590336 models.common.Conv
0.09 0.00 0 models.common.Concat
13.81 0.95 1182720 models.common.C3
12.94 0.74 229245 Detect
312.55 - - Total
👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.
Access additional YOLOv5 🚀 resources:
Access additional Ultralytics ⚡ resources:
Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!
Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!
Can the time of the entire network architecture be calculated? For example, the estimated time of the three parts of the backbone, neck, and head?