-----------------------------------
A1. Preinstall
-----------------------------------
sudo apt install python3-lxml
(Do not install python3-pyqt5 python3-pyqt6)
pip3 install --force-reinstall --upgrade --break-system-packages --target=/usr/lib/python3/dist-packages ultralytics MNN onnx onnxslim onnxruntime
pip3 install --force-reinstall --upgrade --break-system-packages --target=/usr/lib/python3/dist-packages labelImg anylabeling
new version recommend:
pip3 install --force-reinstall --upgrade --break-system-packages --target=/usr/lib/python3/dist-packages labelImg x-anylabeling-cvhub[cpu]
-----------------------------------
B1. LabelImg create dataset
-----------------------------------
/usr/local/bin/labelImg
-----------------------------------
B2. Directories structure
-----------------------------------
mnndataset/
|-- yolo.yaml # yolo train config file
|-- images/ # all images
| |-- train/ # training images
| | |-- worker_001.jpg
| | |-- worker_002.png
| | `-- ...
| |-- val/ # validation images
| | |-- worker_101.jpg
| | `-- ...
| `-- test/ # test images (optional)
| `-- worker_201.jpg
`-- labels/ # all YOLO label files (.txt)
|-- train/ # must match images/train filenames
| |-- worker_001.txt
| |-- worker_002.txt
| `-- ...
|-- val/ # must match images/val filenames
| |-- worker_101.txt
| `-- ...
`-- test/ # optional
`-- worker_201.txt
-----------------------------------
B3. gedit /mnt/upload/projects/mnndataset/yolo.yaml
-----------------------------------
path: /mnt/upload/projects/mnndataset
train: images/train
val: images/val
test: images/test
nc: 1
names:
0: car
xxxxx.txt example:
0 0.451200 0.523000 0.210000 0.480000
-----------------------------------
B4. train
-----------------------------------
start train:
yolo detect train data=/mnt/upload/projects/mnndataset/yolo.yaml model=yolov8n.pt epochs=100 imgsz=640 batch=16
resume train:
yolo detect train resume=True
add train epochs:
yolo detect train \
data=/mnt/upload/projects/mnndataset/yolo.yaml \
model=runs/detect/train/weights/last.pt \
epochs=200 imgsz=640 batch=16 device=0
Device Table
+------------+-----------------------------------+
| device | Meaning |
+------------+-----------------------------------+
| device=0 | Use the first GPU, most common |
| device=1 | Use the second GPU |
| device=0,1 | Use two GPUs together |
| device=cpu | Use CPU only, very slow |
| not set | Auto select, use GPU if available |
+------------+-----------------------------------+
convert to .mnn
python3 -c "from ultralytics import YOLO; YOLO('/mnt/upload/projects/runs/detect/train/weights/best.pt').export(format='mnn', imgsz=640)"
Model Table
+---------+---------+--------+---------+----------+
| Model | Meaning | Params | Speed | Accuracy |
+---------+---------+--------+---------+----------+
| yolov8n | nano | ~3.2M | Fastest | Lowest |
| yolov8s | small | ~11.2M | Fast | Medium |
| yolov8m | medium | ~25.9M | Normal | Higher |
| yolov8l | large | ~43.7M | Slow | High |
| yolov8x | xlarge | ~68.2M | Slowest | Highest |
+---------+---------+--------+---------+----------+
-----------------------------------
C1. Anylabeling create dataset
-----------------------------------
python3 -c \
"import os, json, glob
from PIL import Image
img_dir = '/mnt/upload/projects/mnndataset/images/train'
label_dir = '/mnt/upload/projects/mnndataset/labels/train'
for tf in glob.glob(label_dir + '/*.txt'):
name = os.path.basename(tf).replace('.txt','')
img_path = None
for ext in ['.jpg','.png','.jpeg']:
p = os.path.join(img_dir, name + ext)
if os.path.exists(p):
img_path = p
break
if not img_path: continue
w, h = Image.open(img_path).size
shapes = []
for line in open(tf).read().strip().splitlines():
if not line.strip(): continue
c, xc, yc, bw, bh = map(float, line.split())
x1 = (xc - bw/2) * w
y1 = (yc - bh/2) * h
x2 = (xc + bw/2) * w
y2 = (yc + bh/2) * h
shapes.append({'label':'car','points':[[x1,y1],[x2,y2]],'shape_type':'rectangle','flags':{}})
data = {'version':'0.0.0','flags':{},'shapes':shapes,'imagePath':os.path.basename(img_path),'imageData':None,'imageWidth':w,'imageHeight':h}
json.dump(data, open(os.path.join(img_dir, name + '.json'), 'w'))
print('done')"
#after run this command put xxxxx.jpg xxxxx.json in the same directory
-----------------------------------
C2. gedit /mnt/upload/projects/mnndataset/anylabel.yaml
-----------------------------------
name: userAI
display_name: MNN YOLOv8
type: yolov8
model_path: /mnt/upload/asustor_projects/mnndataset/yolov8n.onnx
input_width: 640
input_height: 640
confidence_threshold: 0.85
score_threshold: 0.5
nms_threshold: 0.5
classes:
- car
-----------------------------------
C3. Labeling 20% of all pictures then train
-----------------------------------
yolo detect train data=/mnt/upload/projects/mnndataset/yolo.yaml model=yolov8n.pt epochs=100 imgsz=640 batch=16
-----------------------------------
C4. Auto labeling
-----------------------------------
run: /usr/lib/python3/dist-packages/bin/anylabeling
click left down a brain like icon "Auto Labeling"
~or
run: /usr/lib/python3/dist-packages/bin/xanylabeling
click top right a cross like icon "Auto Labeling"
in "Auto" field select anylabel.yaml
Press Run
ps: If the wrong category is identified, you can modify the corresponding config.yaml file under ~/anylabeling_data/models. For example: ~/anylabeling_data/models/yolov8x-r20230415/config.yaml
refer to:
https://github.com/CVHub520/X-AnyLabeling/blob/main/docs/en/get_started.md
沒有留言:
張貼留言