Skip to content

Commit 5ab15c4

Browse files
committed
NEW
1 parent 24af99d commit 5ab15c4

File tree

171 files changed

+18741
-25
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

171 files changed

+18741
-25
lines changed

.idea/PythonnotJava.github.io.iml

Lines changed: 0 additions & 18 deletions
This file was deleted.

.idea/vcs.xml

Lines changed: 0 additions & 6 deletions
This file was deleted.

.idea/.gitignore renamed to temp/backup/whatido/.idea/.gitignore

Lines changed: 3 additions & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

temp/backup/whatido/.idea/csv-editor.xml

Lines changed: 16 additions & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

temp/backup/whatido/.idea/inspectionProfiles/Project_Default.xml

Lines changed: 19 additions & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

temp/backup/whatido/.idea/inspectionProfiles/profiles_settings.xml

Lines changed: 6 additions & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

temp/backup/whatido/.idea/misc.xml

Lines changed: 7 additions & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

.idea/modules.xml renamed to temp/backup/whatido/.idea/modules.xml

Lines changed: 1 addition & 1 deletion
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

temp/backup/whatido/.idea/whatido.iml

Lines changed: 8 additions & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

temp/backup/whatido/CV/args.md

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
| 模型 | 尺寸 (像素) | mAP姿态 50-95 | mAP姿态 50 | CPU ONNX 速度 (毫秒) | A100 TensorRT 速度 (毫秒) | 浮点数运算 (B) | 参数 (M) |
2+
|-----------------|---------|-------------|------------|------------------|--------------------------|------------|--------|
3+
| YOLOv8n-pose | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 9.2 | 3.3 |
4+
| YOLOv8s-pose | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 30.2 | 11.6 |
5+
| YOLOv8m-pose | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 81.0 | 26.4 |
6+
| YOLOv8l-pose | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 168.6 | 44.4 |
7+
| YOLOv8x-pose | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 263.2 | 69.4 |
8+
| YOLOv8x-pose-p6 | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 1066.4 | 99.1 |
9+
10+
## 参数解释
11+
尺寸 (像素): 输入图像的分辨率。
12+
mAP姿态 50-95: 模型在多种IoU阈值(从0.50到0.95)上的平均准确率,用于评估模型在姿态估计任务上的总体性能。
13+
mAP姿态 50: 在IoU为0.50的阈值上的模型准确率,通常更容易达成,用于评估模型对较大误差的容忍度。
14+
CPU ONNX 速度 (毫秒): 在CPU上使用ONNX格式运行时的推理速度。
15+
A100 TensorRT 速度 (毫秒): 在NVIDIA A100 GPU上使用TensorRT优化时的推理速度。
16+
参数 (M): 模型中的参数数量,以百万为单位。参数越多,模型通常越复杂。
17+
浮点数运算 (B): 执行一次前向传播所需的浮点运算次数,以十亿为单位。这反映了模型的计算复杂度。
18+
## 模型解释
19+
YOLOv8n-pose: “n”代表“nano”,是系列中最轻量级的模型,适用于计算资源受限的环境。
20+
YOLOv8s-pose: “s”代表“small”,是相对轻量级但性能更好的模型,平衡了速度和准确度。
21+
YOLOv8m-pose: “m”代表“medium”,是中等大小的模型,提供较高的准确度,适用于需要更准确结果的场景。
22+
YOLOv8l-pose: “l”代表“large”,是较大的模型,具有更高的准确度,但速度较慢,适用于高精度要求的应用。
23+
YOLOv8x-pose: “x”代表“extra large”,是系列中最大最精确的模型,但速度最慢,适用于对准确度有极高要求的场景。
24+
YOLOv8x-pose-p6: 是YOLOv8x的一个变种,使用更大的输入尺寸(1280像素),提供了更高的准确度,但需要更多的计算资源。
25+

0 commit comments

Comments
 (0)