Skip to content
This repository was archived by the owner on Jul 25, 2024. It is now read-only.

Commit cbfb5a4

Browse files
lilili1111111lilili1111111
committed
Init
1 parent 9637540 commit cbfb5a4

File tree

98 files changed

+109350
-1
lines changed

Some content is hidden

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

98 files changed

+109350
-1
lines changed

‎.gitignore‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
__pycache__/
2+
data/dataests/
3+
/runs
4+
5+
*.jpg
6+
*.jpeg
7+
*.png
8+
*.bmp
9+
*.tiff
10+
*.gif
11+
*.JPG
12+
*.webp
13+
14+
*.pt

‎README.md‎

Lines changed: 288 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1,288 @@
1-
# Food-Recognition-App-Model
1+
# Official YOLOv7
2+
3+
Implementation of paper - [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://arxiv.org/abs/2207.02696)
4+
5+
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/yolov7-trainable-bag-of-freebies-sets-new/real-time-object-detection-on-coco)](https://paperswithcode.com/sota/real-time-object-detection-on-coco?p=yolov7-trainable-bag-of-freebies-sets-new)
6+
[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/yolov7)
7+
<a href="https://colab.research.google.com/gist/AlexeyAB/b769f5795e65fdab80086f6cb7940dae/yolov7detection.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
8+
[![arxiv.org](http://img.shields.io/badge/cs.CV-arXiv%3A2207.02696-B31B1B.svg)](https://arxiv.org/abs/2207.02696)
9+
10+
<div align="center">
11+
<a href="./">
12+
<img src="./figure/performance.png" width="79%"/>
13+
</a>
14+
</div>
15+
16+
## Web Demo
17+
18+
- Integrated into [Huggingface Spaces 🤗](https://huggingface.co/spaces/akhaliq/yolov7) using Gradio. Try out the Web Demo [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/yolov7)
19+
20+
## Performance
21+
22+
MS COCO
23+
24+
| Model | Test Size | AP<sup>test</sup> | AP<sub>50</sub><sup>test</sup> | AP<sub>75</sub><sup>test</sup> | batch 1 fps | batch 32 average time |
25+
| :-- | :-: | :-: | :-: | :-: | :-: | :-: |
26+
| [**YOLOv7**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt) | 640 | **51.4%** | **69.7%** | **55.9%** | 161 *fps* | 2.8 *ms* |
27+
| [**YOLOv7-X**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt) | 640 | **53.1%** | **71.2%** | **57.8%** | 114 *fps* | 4.3 *ms* |
28+
| | | | | | | |
29+
| [**YOLOv7-W6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt) | 1280 | **54.9%** | **72.6%** | **60.1%** | 84 *fps* | 7.6 *ms* |
30+
| [**YOLOv7-E6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt) | 1280 | **56.0%** | **73.5%** | **61.2%** | 56 *fps* | 12.3 *ms* |
31+
| [**YOLOv7-D6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt) | 1280 | **56.6%** | **74.0%** | **61.8%** | 44 *fps* | 15.0 *ms* |
32+
| [**YOLOv7-E6E**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt) | 1280 | **56.8%** | **74.4%** | **62.1%** | 36 *fps* | 18.7 *ms* |
33+
34+
## Installation
35+
36+
Docker environment (recommended)
37+
<details><summary> <b>Expand</b> </summary>
38+
39+
``` shell
40+
# create the docker container, you can change the share memory size if you have more.
41+
nvidia-docker run --name yolov7 -it -v your_coco_path/:/coco/ -v your_code_path/:/yolov7 --shm-size=64g nvcr.io/nvidia/pytorch:21.08-py3
42+
43+
# apt install required packages
44+
apt update
45+
apt install -y zip htop screen libgl1-mesa-glx
46+
47+
# pip install required packages
48+
pip install seaborn thop
49+
50+
# go to code folder
51+
cd /yolov7
52+
```
53+
54+
</details>
55+
56+
## Testing
57+
58+
[`yolov7.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt) [`yolov7x.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt) [`yolov7-w6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt) [`yolov7-e6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt) [`yolov7-d6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt) [`yolov7-e6e.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt)
59+
60+
``` shell
61+
python test.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.65 --device 0 --weights yolov7.pt --name yolov7_640_val
62+
```
63+
64+
You will get the results:
65+
66+
```
67+
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.51206
68+
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.69730
69+
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.55521
70+
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.35247
71+
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.55937
72+
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.66693
73+
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.38453
74+
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.63765
75+
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.68772
76+
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.53766
77+
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.73549
78+
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.83868
79+
```
80+
81+
To measure accuracy, download [COCO-annotations for Pycocotools](http://images.cocodataset.org/annotations/annotations_trainval2017.zip) to the `./coco/annotations/instances_val2017.json`
82+
83+
## Training
84+
85+
Data preparation
86+
87+
``` shell
88+
bash scripts/get_coco.sh
89+
```
90+
91+
* Download MS COCO dataset images ([train](http://images.cocodataset.org/zips/train2017.zip), [val](http://images.cocodataset.org/zips/val2017.zip), [test](http://images.cocodataset.org/zips/test2017.zip)) and [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip). If you have previously used a different version of YOLO, we strongly recommend that you delete `train2017.cache` and `val2017.cache` files, and redownload [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip)
92+
93+
Single GPU training
94+
95+
``` shell
96+
# train p5 models
97+
python train.py --workers 8 --device 0 --batch-size 32 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml
98+
99+
# train p6 models
100+
python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
101+
```
102+
103+
Multiple GPU training
104+
105+
``` shell
106+
# train p5 models
107+
python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml
108+
109+
# train p6 models
110+
python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train_aux.py --workers 8 --device 0,1,2,3,4,5,6,7 --sync-bn --batch-size 128 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
111+
```
112+
113+
## Transfer learning
114+
115+
[`yolov7_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7_training.pt) [`yolov7x_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x_training.pt) [`yolov7-w6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6_training.pt) [`yolov7-e6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6_training.pt) [`yolov7-d6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6_training.pt) [`yolov7-e6e_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e_training.pt)
116+
117+
Single GPU finetuning for custom dataset
118+
119+
``` shell
120+
# finetune p5 models
121+
python train.py --workers 8 --device 0 --batch-size 32 --data data/custom.yaml --img 640 640 --cfg cfg/training/yolov7-custom.yaml --weights 'yolov7_training.pt' --name yolov7-custom --hyp data/hyp.scratch.custom.yaml
122+
123+
# finetune p6 models
124+
python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/custom.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6-custom.yaml --weights 'yolov7-w6_training.pt' --name yolov7-w6-custom --hyp data/hyp.scratch.custom.yaml
125+
```
126+
127+
## Re-parameterization
128+
129+
See [reparameterization.ipynb](tools/reparameterization.ipynb)
130+
131+
## Inference
132+
133+
On video:
134+
``` shell
135+
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source yourvideo.mp4
136+
```
137+
138+
On image:
139+
``` shell
140+
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/horses.jpg
141+
```
142+
143+
<div align="center">
144+
<a href="./">
145+
<img src="./figure/horses_prediction.jpg" width="59%"/>
146+
</a>
147+
</div>
148+
149+
150+
## Export
151+
152+
**Pytorch to CoreML (and inference on MacOS/iOS)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7CoreML.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
153+
154+
**Pytorch to ONNX with NMS (and inference)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7onnx.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
155+
```shell
156+
python export.py --weights yolov7-tiny.pt --grid --end2end --simplify \
157+
--topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 --max-wh 640
158+
```
159+
160+
**Pytorch to TensorRT with NMS (and inference)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7trt.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
161+
162+
```shell
163+
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
164+
python export.py --weights ./yolov7-tiny.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640
165+
git clone https://github.com/Linaom1214/tensorrt-python.git
166+
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16
167+
```
168+
169+
**Pytorch to TensorRT another way** <a href="https://colab.research.google.com/gist/AlexeyAB/fcb47ae544cf284eb24d8ad8e880d45c/yolov7trtlinaom.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <details><summary> <b>Expand</b> </summary>
170+
171+
172+
```shell
173+
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
174+
python export.py --weights yolov7-tiny.pt --grid --include-nms
175+
git clone https://github.com/Linaom1214/tensorrt-python.git
176+
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16
177+
178+
# Or use trtexec to convert ONNX to TensorRT engine
179+
/usr/src/tensorrt/bin/trtexec --onnx=yolov7-tiny.onnx --saveEngine=yolov7-tiny-nms.trt --fp16
180+
```
181+
182+
</details>
183+
184+
Tested with: Python 3.7.13, Pytorch 1.12.0+cu113
185+
186+
## Pose estimation
187+
188+
[`code`](https://github.com/WongKinYiu/yolov7/tree/pose) [`yolov7-w6-pose.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6-pose.pt)
189+
190+
See [keypoint.ipynb](https://github.com/WongKinYiu/yolov7/blob/main/tools/keypoint.ipynb).
191+
192+
<div align="center">
193+
<a href="./">
194+
<img src="./figure/pose.png" width="39%"/>
195+
</a>
196+
</div>
197+
198+
199+
## Instance segmentation
200+
201+
[`code`](https://github.com/WongKinYiu/yolov7/tree/mask) [`yolov7-mask.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-mask.pt)
202+
203+
See [instance.ipynb](https://github.com/WongKinYiu/yolov7/blob/main/tools/instance.ipynb).
204+
205+
<div align="center">
206+
<a href="./">
207+
<img src="./figure/mask.png" width="59%"/>
208+
</a>
209+
</div>
210+
211+
## Instance segmentation
212+
213+
[`code`](https://github.com/WongKinYiu/yolov7/tree/u7/seg) [`yolov7-seg.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-seg.pt)
214+
215+
YOLOv7 for instance segmentation (YOLOR + YOLOv5 + YOLACT)
216+
217+
| Model | Test Size | AP<sup>box</sup> | AP<sub>50</sub><sup>box</sup> | AP<sub>75</sub><sup>box</sup> | AP<sup>mask</sup> | AP<sub>50</sub><sup>mask</sup> | AP<sub>75</sub><sup>mask</sup> |
218+
| :-- | :-: | :-: | :-: | :-: | :-: | :-: | :-: |
219+
| **YOLOv7-seg** | 640 | **51.4%** | **69.4%** | **55.8%** | **41.5%** | **65.5%** | **43.7%** |
220+
221+
## Anchor free detection head
222+
223+
[`code`](https://github.com/WongKinYiu/yolov7/tree/u6) [`yolov7-u6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-u6.pt)
224+
225+
YOLOv7 with decoupled TAL head (YOLOR + YOLOv5 + YOLOv6)
226+
227+
| Model | Test Size | AP<sup>val</sup> | AP<sub>50</sub><sup>val</sup> | AP<sub>75</sub><sup>val</sup> |
228+
| :-- | :-: | :-: | :-: | :-: |
229+
| **YOLOv7-u6** | 640 | **52.6%** | **69.7%** | **57.3%** |
230+
231+
232+
## Citation
233+
234+
```
235+
@article{wang2022yolov7,
236+
title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},
237+
author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
238+
journal={arXiv preprint arXiv:2207.02696},
239+
year={2022}
240+
}
241+
```
242+
243+
```
244+
@article{wang2022designing,
245+
title={Designing Network Design Strategies Through Gradient Path Analysis},
246+
author={Wang, Chien-Yao and Liao, Hong-Yuan Mark and Yeh, I-Hau},
247+
journal={arXiv preprint arXiv:2211.04800},
248+
year={2022}
249+
}
250+
```
251+
252+
253+
## Teaser
254+
255+
Yolov7-semantic & YOLOv7-panoptic & YOLOv7-caption
256+
257+
<div align="center">
258+
<a href="./">
259+
<img src="./figure/tennis.jpg" width="24%"/>
260+
</a>
261+
<a href="./">
262+
<img src="./figure/tennis_semantic.jpg" width="24%"/>
263+
</a>
264+
<a href="./">
265+
<img src="./figure/tennis_panoptic.png" width="24%"/>
266+
</a>
267+
<a href="./">
268+
<img src="./figure/tennis_caption.png" width="24%"/>
269+
</a>
270+
</div>
271+
272+
273+
## Acknowledgements
274+
275+
<details><summary> <b>Expand</b> </summary>
276+
277+
* [https://github.com/AlexeyAB/darknet](https://github.com/AlexeyAB/darknet)
278+
* [https://github.com/WongKinYiu/yolor](https://github.com/WongKinYiu/yolor)
279+
* [https://github.com/WongKinYiu/PyTorch_YOLOv4](https://github.com/WongKinYiu/PyTorch_YOLOv4)
280+
* [https://github.com/WongKinYiu/ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4)
281+
* [https://github.com/Megvii-BaseDetection/YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)
282+
* [https://github.com/ultralytics/yolov3](https://github.com/ultralytics/yolov3)
283+
* [https://github.com/ultralytics/yolov5](https://github.com/ultralytics/yolov5)
284+
* [https://github.com/DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG)
285+
* [https://github.com/JUGGHM/OREPA_CVPR2022](https://github.com/JUGGHM/OREPA_CVPR2022)
286+
* [https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose](https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose)
287+
288+
</details>

‎Test_Verison.py‎

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,20 @@
1+
import torch
2+
3+
# 檢查CUDA是否可用
4+
cuda_available = torch.cuda.is_available()
5+
print("CUDA 可用:", cuda_available)
6+
7+
# 檢查CUDA版本
8+
if cuda_available:
9+
cuda_version = torch.version.cuda
10+
print("CUDA 版本:", cuda_version)
11+
12+
# 檢查cuDNN是否可用
13+
if cuda_available:
14+
cudnn_available = torch.backends.cudnn.enabled
15+
print("cuDNN 可用:", cudnn_available)
16+
17+
# 檢查cuDNN版本
18+
if cuda_available and cudnn_available:
19+
cudnn_version = torch.backends.cudnn.version()
20+
print("cuDNN 版本:", cudnn_version)

‎cfg/baseline/r50-csp.yaml‎

Lines changed: 49 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,49 @@
1+
# parameters
2+
nc: 46 # number of classes
3+
depth_multiple: 1.0 # model depth multiple
4+
width_multiple: 1.0 # layer channel multiple
5+
6+
# anchors
7+
anchors:
8+
- [12,16, 19,36, 40,28] # P3/8
9+
- [36,75, 76,55, 72,146] # P4/16
10+
- [142,110, 192,243, 459,401] # P5/32
11+
12+
# CSP-ResNet backbone
13+
backbone:
14+
# [from, number, module, args]
15+
[[-1, 1, Stem, [128]], # 0-P1/2
16+
[-1, 3, ResCSPC, [128]],
17+
[-1, 1, Conv, [256, 3, 2]], # 2-P3/8
18+
[-1, 4, ResCSPC, [256]],
19+
[-1, 1, Conv, [512, 3, 2]], # 4-P3/8
20+
[-1, 6, ResCSPC, [512]],
21+
[-1, 1, Conv, [1024, 3, 2]], # 6-P3/8
22+
[-1, 3, ResCSPC, [1024]], # 7
23+
]
24+
25+
# CSP-Res-PAN head
26+
head:
27+
[[-1, 1, SPPCSPC, [512]], # 8
28+
[-1, 1, Conv, [256, 1, 1]],
29+
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
30+
[5, 1, Conv, [256, 1, 1]], # route backbone P4
31+
[[-1, -2], 1, Concat, [1]],
32+
[-1, 2, ResCSPB, [256]], # 13
33+
[-1, 1, Conv, [128, 1, 1]],
34+
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
35+
[3, 1, Conv, [128, 1, 1]], # route backbone P3
36+
[[-1, -2], 1, Concat, [1]],
37+
[-1, 2, ResCSPB, [128]], # 18
38+
[-1, 1, Conv, [256, 3, 1]],
39+
[-2, 1, Conv, [256, 3, 2]],
40+
[[-1, 13], 1, Concat, [1]], # cat
41+
[-1, 2, ResCSPB, [256]], # 22
42+
[-1, 1, Conv, [512, 3, 1]],
43+
[-2, 1, Conv, [512, 3, 2]],
44+
[[-1, 8], 1, Concat, [1]], # cat
45+
[-1, 2, ResCSPB, [512]], # 26
46+
[-1, 1, Conv, [1024, 3, 1]],
47+
48+
[[19,23,27], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
49+
]

0 commit comments

Comments
 (0)