This YOLOv5 🚀 notebook by Ultralytics presents simple train, validate and predict examples to help start your AI adventure.
See GitHub for community support or contact us for professional support.
Setup
Clone GitHub repository, install dependencies and check PyTorch and GPU.
!git clone https://github.com/ultralytics/yolov5 # clone
%cd yolov5
%pip install -qr requirements.txt # install
import torch
import utils
display = utils.notebook_init() # checks
YOLOv5 🚀 v7.0-3-g61ebf5e Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB) Setup complete ✅ (2 CPUs, 12.7 GB RAM, 22.6/78.2 GB disk)
1. Predict
classify/predict.py runs YOLOv5 Classification inference on a variety of sources, downloading models automatically from the latest YOLOv5 release, and saving results to runs/predict-cls. Example inference sources are:
python classify/predict.py --source 0 # webcam
img.jpg # image
vid.mp4 # video
screen # screenshot
path/ # directory
'path/*.jpg' # glob
'https://youtu.be/LNwODJXcvt4' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
!python classify/predict.py --weights yolov5s-cls.pt --img 224 --source data/images
# display.Image(filename='runs/predict-cls/exp/zidane.jpg', width=600)
[34m[1mclassify/predict: [0mweights=['yolov5s-cls.pt'], source=data/images, data=data/coco128.yaml, imgsz=[224, 224], device=, view_img=False, save_txt=False, nosave=False, augment=False, visualize=False, update=False, project=runs/predict-cls, name=exp, exist_ok=False, half=False, dnn=False, vid_stride=1 YOLOv5 🚀 v7.0-3-g61ebf5e Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB) Downloading https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s-cls.pt to yolov5s-cls.pt... 100% 10.5M/10.5M [00:00<00:00, 12.3MB/s] Fusing layers... Model summary: 117 layers, 5447688 parameters, 0 gradients, 11.4 GFLOPs image 1/2 /content/yolov5/data/images/bus.jpg: 224x224 minibus 0.39, police van 0.24, amphibious vehicle 0.05, recreational vehicle 0.04, trolleybus 0.03, 3.9ms image 2/2 /content/yolov5/data/images/zidane.jpg: 224x224 suit 0.38, bow tie 0.19, bridegroom 0.18, rugby ball 0.04, stage 0.02, 4.6ms Speed: 0.3ms pre-process, 4.3ms inference, 1.5ms NMS per image at shape (1, 3, 224, 224) Results saved to [1mruns/predict-cls/exp[0m
2. Validate
Validate a model's accuracy on the Imagenet dataset's val or test splits. Models are downloaded automatically from the latest YOLOv5 release. To show results by class use the --verbose flag.
# Download Imagenet val (6.3G, 50000 images)
!bash data/scripts/get_imagenet.sh --val
--2022-11-22 19:53:40-- https://image-net.org/data/ILSVRC/2012/ILSVRC2012_img_val.tar Resolving image-net.org (image-net.org)... 171.64.68.16 Connecting to image-net.org (image-net.org)|171.64.68.16|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 6744924160 (6.3G) [application/x-tar] Saving to: ‘ILSVRC2012_img_val.tar’ ILSVRC2012_img_val. 100%[===================>] 6.28G 16.1MB/s in 10m 52s 2022-11-22 20:04:32 (9.87 MB/s) - ‘ILSVRC2012_img_val.tar’ saved [6744924160/6744924160]
# Validate YOLOv5s on Imagenet val
!python classify/val.py --weights yolov5s-cls.pt --data ../datasets/imagenet --img 224 --half
[34m[1mclassify/val: [0mdata=../datasets/imagenet, weights=['yolov5s-cls.pt'], batch_size=128, imgsz=224, device=, workers=8, verbose=True, project=runs/val-cls, name=exp, exist_ok=False, half=True, dnn=False
YOLOv5 🚀 v7.0-3-g61ebf5e Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)
Fusing layers...
Model summary: 117 layers, 5447688 parameters, 0 gradients, 11.4 GFLOPs
validating: 100% 391/391 [04:57<00:00, 1.31it/s]
Class Images top1_acc top5_acc
all 50000 0.715 0.902
tench 50 0.94 0.98
goldfish 50 0.88 0.92
great white shark 50 0.78 0.96
tiger shark 50 0.68 0.96
hammerhead shark 50 0.82 0.92
electric ray 50 0.76 0.9
stingray 50 0.7 0.9
cock 50 0.78 0.92
hen 50 0.84 0.96
ostrich 50 0.98 1
brambling 50 0.9 0.96
goldfinch 50 0.92 0.98
house finch 50 0.88 0.96
junco 50 0.94 0.98
indigo bunting 50 0.86 0.88
American robin 50 0.9 0.96
bulbul 50 0.84 0.96
jay 50 0.9 0.96
magpie 50 0.84 0.96
chickadee 50 0.9 1
American dipper 50 0.82 0.92
kite 50 0.76 0.94
bald eagle 50 0.92 1
vulture 50 0.96 1
great grey owl 50 0.94 0.98
fire salamander 50 0.96 0.98
smooth newt 50 0.58 0.94
newt 50 0.74 0.9
spotted salamander 50 0.86 0.94
axolotl 50 0.86 0.96
American bullfrog 50 0.78 0.92
tree frog 50 0.84 0.96
tailed frog 50 0.48 0.8
loggerhead sea turtle 50 0.68 0.94
leatherback sea turtle 50 0.5 0.8
mud turtle 50 0.64 0.84
terrapin 50 0.52 0.98
box turtle 50 0.84 0.98
banded gecko 50 0.7 0.88
green iguana 50 0.76 0.94
Carolina anole 50 0.58 0.96
desert grassland whiptail lizard 50 0.82 0.94
agama 50 0.74 0.92
frilled-necked lizard 50 0.84 0.86
alligator lizard 50 0.58 0.78
Gila monster 50 0.72 0.8
European green lizard 50 0.42 0.9
chameleon 50 0.76 0.84
Komodo dragon 50 0.86 0.96
Nile crocodile 50 0.7 0.84
American alligator 50 0.76 0.96
triceratops 50 0.9 0.94
worm snake 50 0.76 0.88
ring-necked snake 50 0.8 0.92
eastern hog-nosed snake 50 0.58 0.88
smooth green snake 50 0.6 0.94
kingsnake 50 0.82 0.9
garter snake 50 0.88 0.94
water snake 50 0.7 0.94
vine snake 50 0.66 0.76
night snake 50 0.34 0.82
boa constrictor 50 0.8 0.96
African rock python 50 0.48 0.76
Indian cobra 50 0.82 0.94
green mamba 50 0.54 0.86
sea snake 50 0.62 0.9
Saharan horned viper 50 0.56 0.86
eastern diamondback rattlesnake 50 0.6 0.86
sidewinder 50 0.28 0.86
trilobite 50 0.98 0.98
harvestman 50 0.86 0.94
scorpion 50 0.86 0.94
yellow garden spider 50 0.92 0.96
barn spider 50 0.38 0.98
European garden spider 50 0.62 0.98
southern black widow 50 0.88 0.94
tarantula 50 0.94 1
wolf spider 50 0.82 0.92
tick 50 0.74 0.84
centipede 50 0.68 0.82
black grouse 50 0.88 0.98
ptarmigan 50 0.78 0.94
ruffed grouse 50 0.88 1
prairie grouse 50 0.92 1
peacock 50 0.88 0.9
quail 50 0.9 0.94
partridge 50 0.74 0.96
grey parrot 50 0.9 0.96
macaw 50 0.88 0.98
sulphur-crested cockatoo 50 0.86 0.92
lorikeet 50 0.96 1
coucal 50 0.82 0.88
bee eater 50 0.96 0.98
hornbill 50 0.9 0.96
hummingbird 50 0.88 0.96
jacamar 50 0.92 0.94
toucan 50 0.84 0.94
duck 50 0.76 0.94
red-breasted merganser 50 0.86 0.96
goose 50 0.74 0.96
black swan 50 0.94 0.98
tusker 50 0.54 0.92
echidna 50 0.98 1
platypus 50 0.72 0.84
wallaby 50 0.78 0.88
koala 50 0.84 0.92
wombat 50 0.78 0.84
jellyfish 50 0.88 0.96
sea anemone 50 0.72 0.9
brain coral 50 0.88 0.96
flatworm 50 0.8 0.98
nematode 50 0.86 0.9
conch 50 0.74 0.88
snail 50 0.78 0.88
slug 50 0.74 0.82
sea slug 50 0.88 0.98
chiton 50 0.88 0.98
chambered nautilus 50 0.88 0.92
Dungeness crab 50 0.78 0.94
rock crab 50 0.68 0.86
fiddler crab 50 0.64 0.86
red king crab 50 0.76 0.96
American lobster 50 0.78 0.96
spiny lobster 50 0.74 0.88
crayfish 50 0.56 0.86
hermit crab 50 0.78 0.96
isopod 50 0.66 0.78
white stork 50 0.88 0.96
black stork 50 0.84 0.98
spoonbill 50 0.96 1
flamingo 50 0.94 1
little blue heron 50 0.92 0.98
great egret 50 0.9 0.96
bittern 50 0.86 0.94
crane (bird) 50 0.62 0.9
limpkin 50 0.98 1
common gallinule 50 0.92 0.96
American coot 50 0.9 0.98
bustard 50 0.92 0.96
ruddy turnstone 50 0.94 1
dunlin 50 0.86 0.94
common redshank 50 0.9 0.96
dowitcher 50 0.84 0.96
oystercatcher 50 0.86 0.94
pelican 50 0.92 0.96
king penguin 50 0.88 0.96
albatross 50 0.9 1
grey whale 50 0.84 0.92
killer whale 50 0.92 1
dugong 50 0.84 0.96
sea lion 50 0.82 0.92
Chihuahua 50 0.66 0.84
Japanese Chin 50 0.72 0.98
Maltese 50 0.76 0.94
Pekingese 50 0.84 0.94
Shih Tzu 50 0.74 0.96
King Charles Spaniel 50 0.88 0.98
Papillon 50 0.86 0.94
toy terrier 50 0.48 0.94
Rhodesian Ridgeback 50 0.76 0.98
Afghan Hound 50 0.84 1
Basset Hound 50 0.8 0.92
Beagle 50 0.82 0.96
Bloodhound 50 0.48 0.72
Bluetick Coonhound 50 0.86 0.94
Black and Tan Coonhound 50 0.54 0.8
Treeing Walker Coonhound 50 0.66 0.98
English foxhound 50 0.32 0.84
Redbone Coonhound 50 0.62 0.94
borzoi 50 0.92 1
Irish Wolfhound 50 0.48 0.88
Italian Greyhound 50 0.76 0.98
Whippet 50 0.74 0.92
Ibizan Hound 50 0.6 0.86
Norwegian Elkhound 50 0.88 0.98
Otterhound 50 0.62 0.9
Saluki 50 0.72 0.92
Scottish Deerhound 50 0.86 0.98
Weimaraner 50 0.88 0.94
Staffordshire Bull Terrier 50 0.66 0.98
American Staffordshire Terrier 50 0.64 0.92
Bedlington Terrier 50 0.9 0.92
Border Terrier 50 0.86 0.92
Kerry Blue Terrier 50 0.78 0.98
Irish Terrier 50 0.7 0.96
Norfolk Terrier 50 0.68 0.9
Norwich Terrier 50 0.72 1
Yorkshire Terrier 50 0.66 0.9
Wire Fox Terrier 50 0.64 0.98
Lakeland Terrier 50 0.74 0.92
Sealyham Terrier 50 0.76 0.9
Airedale Terrier 50 0.82 0.92
Cairn Terrier 50 0.76 0.9
Australian Terrier 50 0.48 0.84
Dandie Dinmont Terrier 50 0.82 0.92
Boston Terrier 50 0.92 1
Miniature Schnauzer 50 0.68 0.9
Giant Schnauzer 50 0.72 0.98
Standard Schnauzer 50 0.74 1
Scottish Terrier 50 0.76 0.96
Tibetan Terrier 50 0.48 1
Australian Silky Terrier 50 0.66 0.96
Soft-coated Wheaten Terrier 50 0.74 0.96
West Highland White Terrier 50 0.88 0.96
Lhasa Apso 50 0.68 0.96
Flat-Coated Retriever 50 0.72 0.94
Curly-coated Retriever 50 0.82 0.94
Golden Retriever 50 0.86 0.94
Labrador Retriever 50 0.82 0.94
Chesapeake Bay Retriever 50 0.76 0.96
German Shorthaired Pointer 50 0.8 0.96
Vizsla 50 0.68 0.96
English Setter 50 0.7 1
Irish Setter 50 0.8 0.9
Gordon Setter 50 0.84 0.92
Brittany 50 0.84 0.96
Clumber Spaniel 50 0.92 0.96
English Springer Spaniel 50 0.88 1
Welsh Springer Spaniel 50 0.92 1
Cocker Spaniels 50 0.7 0.94
Sussex Spaniel 50 0.72 0.92
Irish Water Spaniel 50 0.88 0.98
Kuvasz 50 0.66 0.9
Schipperke 50 0.9 0.98
Groenendael 50 0.8 0.94
Malinois 50 0.86 0.98
Briard 50 0.52 0.8
Australian Kelpie 50 0.6 0.88
Komondor 50 0.88 0.94
Old English Sheepdog 50 0.94 0.98
Shetland Sheepdog 50 0.74 0.9
collie 50 0.6 0.96
Border Collie 50 0.74 0.96
Bouvier des Flandres 50 0.78 0.94
Rottweiler 50 0.88 0.96
German Shepherd Dog 50 0.8 0.98
Dobermann 50 0.68 0.96
Miniature Pinscher 50 0.76 0.88
Greater Swiss Mountain Dog 50 0.68 0.94
Bernese Mountain Dog 50 0.96 1
Appenzeller Sennenhund 50 0.22 1
Entlebucher Sennenhund 50 0.64 0.98
Boxer 50 0.7 0.92
Bullmastiff 50 0.78 0.98
Tibetan Mastiff 50 0.88 0.96
French Bulldog 50 0.84 0.94
Great Dane 50 0.54 0.9
St. Bernard 50 0.92 1
husky 50 0.46 0.98
Alaskan Malamute 50 0.76 0.96
Siberian Husky 50 0.46 0.98
Dalmatian 50 0.94 0.98
Affenpinscher 50 0.78 0.9
Basenji 50 0.92 0.94
pug 50 0.94 0.98
Leonberger 50 1 1
Newfoundland 50 0.78 0.96
Pyrenean Mountain Dog 50 0.78 0.96
Samoyed 50 0.96 1
Pomeranian 50 0.98 1
Chow Chow 50 0.9 0.96
Keeshond 50 0.88 0.94
Griffon Bruxellois 50 0.84 0.98
Pembroke Welsh Corgi 50 0.82 0.94
Cardigan Welsh Corgi 50 0.66 0.98
Toy Poodle 50 0.52 0.88
Miniature Poodle 50 0.52 0.92
Standard Poodle 50 0.8 1
Mexican hairless dog 50 0.88 0.98
grey wolf 50 0.82 0.92
Alaskan tundra wolf 50 0.78 0.98
red wolf 50 0.48 0.9
coyote 50 0.64 0.86
dingo 50 0.76 0.88
dhole 50 0.9 0.98
African wild dog 50 0.98 1
hyena 50 0.88 0.96
red fox 50 0.54 0.92
kit fox 50 0.72 0.98
Arctic fox 50 0.94 1
grey fox 50 0.7 0.94
tabby cat 50 0.54 0.92
tiger cat 50 0.22 0.94
Persian cat 50 0.9 0.98
Siamese cat 50 0.96 1
Egyptian Mau 50 0.54 0.8
cougar 50 0.9 1
lynx 50 0.72 0.88
leopard 50 0.78 0.98
snow leopard 50 0.9 0.98
jaguar 50 0.7 0.94
lion 50 0.9 0.98
tiger 50 0.92 0.98
cheetah 50 0.94 0.98
brown bear 50 0.94 0.98
American black bear 50 0.8 1
polar bear 50 0.84 0.96
sloth bear 50 0.72 0.92
mongoose 50 0.7 0.92
meerkat 50 0.82 0.92
tiger beetle 50 0.92 0.94
ladybug 50 0.86 0.94
ground beetle 50 0.64 0.94
longhorn beetle 50 0.62 0.88
leaf beetle 50 0.64 0.98
dung beetle 50 0.86 0.98
rhinoceros beetle 50 0.86 0.94
weevil 50 0.9 1
fly 50 0.78 0.94
bee 50 0.68 0.94
ant 50 0.68 0.78
grasshopper 50 0.5 0.92
cricket 50 0.64 0.92
stick insect 50 0.64 0.92
cockroach 50 0.72 0.8
mantis 50 0.64 0.86
cicada 50 0.9 0.96
leafhopper 50 0.88 0.94
3. Train
Close the active learning loop by sampling images from your inference conditions with the roboflow pip package
Train a YOLOv5s Classification model on the Imagenette dataset with --data imagenet, starting from pretrained --pretrained yolov5s-cls.pt.
- Pretrained Models are downloaded
automatically from the latest YOLOv5 release - Training Results are saved to
runs/train-cls/with incrementing run directories, i.e.runs/train-cls/exp2,runs/train-cls/exp3etc.
A Mosaic Dataloader is used for training which combines 4 images into 1 mosaic.
Train on Custom Data with Roboflow 🌟 NEW
Roboflow enables you to easily organize, label, and prepare a high quality dataset with your own custom data. Roboflow also makes it easy to establish an active learning pipeline, collaborate with your team on dataset improvement, and integrate directly into your model building workflow with the roboflow pip package.
- Custom Training Example: https://blog.roboflow.com/train-yolov5-classification-custom-data/
- Custom Training Notebook:
Label images lightning fast (including with model-assisted labeling)
#@title Select YOLOv5 🚀 logger {run: 'auto'}
logger = 'Comet' #@param ['Comet', 'ClearML', 'TensorBoard']
if logger == 'Comet':
%pip install -q comet_ml
import comet_ml; comet_ml.init()
elif logger == 'ClearML':
%pip install -q clearml
import clearml; clearml.browser_login()
elif logger == 'TensorBoard':
%load_ext tensorboard
%tensorboard --logdir runs/train
# Train YOLOv5s Classification on Imagenette160 for 3 epochs
!python classify/train.py --model yolov5s-cls.pt --data imagenette160 --epochs 5 --img 224 --cache
[34m[1mclassify/train: [0mmodel=yolov5s-cls.pt, data=imagenette160, epochs=5, batch_size=64, imgsz=224, nosave=False, cache=ram, device=, workers=8, project=runs/train-cls, name=exp, exist_ok=False, pretrained=True, optimizer=Adam, lr0=0.001, decay=5e-05, label_smoothing=0.1, cutoff=None, dropout=None, verbose=False, seed=0, local_rank=-1
[34m[1mgithub: [0mup to date with https://github.com/ultralytics/yolov5 ✅
YOLOv5 🚀 v7.0-3-g61ebf5e Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)
[34m[1mTensorBoard: [0mStart with 'tensorboard --logdir runs/train-cls', view at http://localhost:6006/
Dataset not found ⚠️, missing path /content/datasets/imagenette160, attempting download...
Downloading https://github.com/ultralytics/yolov5/releases/download/v1.0/imagenette160.zip to /content/datasets/imagenette160.zip...
100% 103M/103M [00:00<00:00, 347MB/s]
Unzipping /content/datasets/imagenette160.zip...
Dataset download success ✅ (3.3s), saved to [1m/content/datasets/imagenette160[0m
[34m[1malbumentations: [0mRandomResizedCrop(p=1.0, height=224, width=224, scale=(0.08, 1.0), ratio=(0.75, 1.3333333333333333), interpolation=1), HorizontalFlip(p=0.5), ColorJitter(p=0.5, brightness=[0.6, 1.4], contrast=[0.6, 1.4], saturation=[0.6, 1.4], hue=[0, 0]), Normalize(p=1.0, mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225), max_pixel_value=255.0), ToTensorV2(always_apply=True, p=1.0, transpose_mask=False)
Model summary: 149 layers, 4185290 parameters, 4185290 gradients, 10.5 GFLOPs
[34m[1moptimizer:[0m Adam(lr=0.001) with parameter groups 32 weight(decay=0.0), 33 weight(decay=5e-05), 33 bias
Image sizes 224 train, 224 test
Using 1 dataloader workers
Logging results to [1mruns/train-cls/exp[0m
Starting yolov5s-cls.pt training on imagenette160 dataset with 10 classes for 5 epochs...
Epoch GPU_mem train_loss val_loss top1_acc top5_acc
1/5 1.47G 1.05 0.974 0.828 0.975: 100% 148/148 [00:38<00:00, 3.82it/s]
2/5 1.73G 0.895 0.766 0.911 0.994: 100% 148/148 [00:36<00:00, 4.03it/s]
3/5 1.73G 0.82 0.704 0.934 0.996: 100% 148/148 [00:35<00:00, 4.20it/s]
4/5 1.73G 0.766 0.664 0.951 0.998: 100% 148/148 [00:36<00:00, 4.05it/s]
5/5 1.73G 0.724 0.634 0.959 0.997: 100% 148/148 [00:37<00:00, 3.94it/s]
Training complete (0.052 hours)
Results saved to [1mruns/train-cls/exp[0m
Predict: python classify/predict.py --weights runs/train-cls/exp/weights/best.pt --source im.jpg
Validate: python classify/val.py --weights runs/train-cls/exp/weights/best.pt --data /content/datasets/imagenette160
Export: python export.py --weights runs/train-cls/exp/weights/best.pt --include onnx
PyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', 'runs/train-cls/exp/weights/best.pt')
Visualize: https://netron.app
4. Visualize
Comet Logging and Visualization 🌟 NEW
Comet is now fully integrated with YOLOv5. Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and visualize your model predictions with Comet Custom Panels! Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of all sizes!
Getting started is easy:
pip install comet_ml # 1. install
export COMET_API_KEY=<Your API Key> # 2. paste API key
python train.py --img 640 --epochs 3 --data coco128.yaml --weights yolov5s.pt # 3. train
To learn more about all of the supported Comet features for this integration, check out the Comet Tutorial. If you'd like to learn more about Comet, head over to our documentation. Get started by trying out the Comet Colab Notebook:
ClearML Logging and Automation 🌟 NEW
ClearML is completely integrated into YOLOv5 to track your experimentation, manage dataset versions and even remotely execute training runs. To enable ClearML (check cells above):
pip install clearml- run
clearml-initto connect to a ClearML server (deploy your own open-source server, or use our free hosted server)
You'll get all the great expected features from an experiment manager: live updates, model upload, experiment comparison etc. but ClearML also tracks uncommitted changes and installed packages for example. Thanks to that ClearML Tasks (which is what we call experiments) are also reproducible on different machines! With only 1 extra line, we can schedule a YOLOv5 training task on a queue to be executed by any number of ClearML Agents (workers).
You can use ClearML Data to version your dataset and then pass it to YOLOv5 simply using its unique ID. This will help you keep track of your data without adding extra hassle. Explore the ClearML Tutorial for details!
Local Logging
Training results are automatically logged with Tensorboard and CSV loggers to runs/train, with a new experiment directory created for each new training as runs/train/exp2, runs/train/exp3, etc.
This directory contains train and val statistics, mosaics, labels, predictions and augmentated mosaics, as well as metrics and charts including precision-recall (PR) curves and confusion matrices.
Environments
YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):
- Notebooks with free GPU:
- Google Cloud Deep Learning VM. See GCP Quickstart Guide
- Amazon Deep Learning AMI. See AWS Quickstart Guide
- Docker Image. See Docker Quickstart Guide
Status
If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (val.py), inference (detect.py) and export (export.py) on macOS, Windows, and Ubuntu every 24 hours and on every commit.
Appendix
Additional content below.
# YOLOv5 PyTorch HUB Inference (DetectionModels only)
import torch
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True, trust_repo=True) # or yolov5n - yolov5x6 or custom
im = 'https://ultralytics.com/images/zidane.jpg' # file, Path, PIL.Image, OpenCV, nparray, list
results = model(im) # inference
results.print() # or .show(), .save(), .crop(), .pandas(), etc.