[中文](https://docs.ultralytics.com/zh/) | [한국어](https://docs.ultralytics.com/ko/) | [日本語](https://docs.ultralytics.com/ja/) | [Русский](https://docs.ultralytics.com/ru/) | [Deutsch](https://docs.ultralytics.com/de/) | [Français](https://docs.ultralytics.com/fr/) | [Español](https://docs.ultralytics.com/es/) | [Português](https://docs.ultralytics.com/pt/) | [हिन्दी](https://docs.ultralytics.com/hi/) | [العربية](https://docs.ultralytics.com/ar/)
This YOLOv5 🚀 notebook by Ultralytics presents simple train, validate and predict examples to help start your AI adventure.We hope that the resources in this notebook will help you get the most out of YOLOv5. Please browse the YOLOv5 Docs for details, raise an issue on GitHub for support, and join our Discord community for questions and discussions!
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 comet_ml # install
import torch
import utils
display = utils.notebook_init() # checks
YOLOv5 🚀 v7.0-136-g71244ae Python-3.9.16 torch-2.0.0+cu118 CUDA:0 (Tesla T4, 15102MiB) Setup complete ✅ (2 CPUs, 12.7 GB RAM, 23.3/166.8 GB disk)
1. Detect
detect.py runs YOLOv5 inference on a variety of sources, downloading models automatically from the latest YOLOv5 release, and saving results to runs/detect. Example inference sources are:
python detect.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 detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images
# display.Image(filename='runs/detect/exp/zidane.jpg', width=600)
[34m[1mdetect: [0mweights=['yolov5s.pt'], source=data/images, data=data/coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False, vid_stride=1 YOLOv5 🚀 v7.0-136-g71244ae Python-3.9.16 torch-2.0.0+cu118 CUDA:0 (Tesla T4, 15102MiB) Downloading https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s.pt to yolov5s.pt... 100% 14.1M/14.1M [00:00<00:00, 24.5MB/s] Fusing layers... YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 41.5ms image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, 60.0ms Speed: 0.5ms pre-process, 50.8ms inference, 37.7ms NMS per image at shape (1, 3, 640, 640) Results saved to [1mruns/detect/exp[0m
2. Validate
Validate a model's accuracy on the COCO 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 COCO val
torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip') # download (780M - 5000 images)
!unzip -q tmp.zip -d ../datasets && rm tmp.zip # unzip
100%|██████████| 780M/780M [00:12<00:00, 66.6MB/s]
# Validate YOLOv5s on COCO val
!python val.py --weights yolov5s.pt --data coco.yaml --img 640 --half
[34m[1mval: [0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5s.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.6, max_det=300, task=val, device=, workers=8, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True, dnn=False
YOLOv5 🚀 v7.0-136-g71244ae Python-3.9.16 torch-2.0.0+cu118 CUDA:0 (Tesla T4, 15102MiB)
Fusing layers...
YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients
[34m[1mval: [0mScanning /content/datasets/coco/val2017... 4952 images, 48 backgrounds, 0 corrupt: 100% 5000/5000 [00:02<00:00, 2024.59it/s]
[34m[1mval: [0mNew cache created: /content/datasets/coco/val2017.cache
Class Images Instances P R mAP50 mAP50-95: 100% 157/157 [01:25<00:00, 1.84it/s]
all 5000 36335 0.671 0.519 0.566 0.371
Speed: 0.1ms pre-process, 3.1ms inference, 2.3ms NMS per image at shape (32, 3, 640, 640)
Evaluating pycocotools mAP... saving runs/val/exp/yolov5s_predictions.json...
loading annotations into memory...
Done (t=0.43s)
creating index...
index created!
Loading and preparing results...
DONE (t=5.32s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=78.89s).
Accumulating evaluation results...
DONE (t=14.51s).
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.374
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.572
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.402
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.211
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.423
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.489
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.311
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.516
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.566
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.378
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.625
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.722
Results saved to [1mruns/val/exp[0m
3. Train
Close the active learning loop by sampling images from your inference conditions with the roboflow pip package
Train a YOLOv5s model on the COCO128 dataset with --data coco128.yaml, starting from pretrained --weights yolov5s.pt, or from randomly initialized --weights '' --cfg yolov5s.yaml.
- Pretrained Models are downloaded
automatically from the latest YOLOv5 release - Datasets available for autodownload include: COCO, COCO128, VOC, Argoverse, VisDrone, GlobalWheat, xView, Objects365, SKU-110K.
- Training Results are saved to
runs/train/with incrementing run directories, i.e.runs/train/exp2,runs/train/exp3etc.
A Mosaic Dataloader is used for training which combines 4 images into 1 mosaic.
Label a dataset on Roboflow (optional)
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.
#@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 on COCO128 for 3 epochs
!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache
2023-04-09 14:11:38.063605: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-04-09 14:11:39.026661: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
[34m[1mtrain: [0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest
[34m[1mgithub: [0mup to date with https://github.com/ultralytics/yolov5 ✅
YOLOv5 🚀 v7.0-136-g71244ae Python-3.9.16 torch-2.0.0+cu118 CUDA:0 (Tesla T4, 15102MiB)
[34m[1mhyperparameters: [0mlr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0
[34m[1mClearML: [0mrun 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 🚀 in ClearML
[34m[1mComet: [0mrun 'pip install comet_ml' to automatically track and visualize YOLOv5 🚀 runs in Comet
[34m[1mTensorBoard: [0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/
Dataset not found ⚠️, missing paths ['/content/datasets/coco128/images/train2017']
Downloading https://ultralytics.com/assets/coco128.zip to coco128.zip...
100% 6.66M/6.66M [00:00<00:00, 75.6MB/s]
Dataset download success ✅ (0.6s), saved to [1m/content/datasets[0m
from n params module arguments
0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 18816 models.common.C3 [64, 64, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 2 115712 models.common.C3 [128, 128, 2]
5 -1 1 295424 models.common.Conv [128, 256, 3, 2]
6 -1 3 625152 models.common.C3 [256, 256, 3]
7 -1 1 1180672 models.common.Conv [256, 512, 3, 2]
8 -1 1 1182720 models.common.C3 [512, 512, 1]
9 -1 1 656896 models.common.SPPF [512, 512, 5]
10 -1 1 131584 models.common.Conv [512, 256, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 models.common.Concat [1]
13 -1 1 361984 models.common.C3 [512, 256, 1, False]
14 -1 1 33024 models.common.Conv [256, 128, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 models.common.Concat [1]
17 -1 1 90880 models.common.C3 [256, 128, 1, False]
18 -1 1 147712 models.common.Conv [128, 128, 3, 2]
19 [-1, 14] 1 0 models.common.Concat [1]
20 -1 1 296448 models.common.C3 [256, 256, 1, False]
21 -1 1 590336 models.common.Conv [256, 256, 3, 2]
22 [-1, 10] 1 0 models.common.Concat [1]
23 -1 1 1182720 models.common.C3 [512, 512, 1, False]
24 [17, 20, 23] 1 229245 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Model summary: 214 layers, 7235389 parameters, 7235389 gradients, 16.6 GFLOPs
Transferred 349/349 items from yolov5s.pt
[34m[1mAMP: [0mchecks passed ✅
[34m[1moptimizer:[0m SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 60 weight(decay=0.0005), 60 bias
[34m[1malbumentations: [0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))
[34m[1mtrain: [0mScanning /content/datasets/coco128/labels/train2017... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00<00:00, 1709.36it/s]
[34m[1mtrain: [0mNew cache created: /content/datasets/coco128/labels/train2017.cache
[34m[1mtrain: [0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 264.35it/s]
[34m[1mval: [0mScanning /content/datasets/coco128/labels/train2017.cache... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]
[34m[1mval: [0mCaching images (0.1GB ram): 100% 128/128 [00:01<00:00, 107.05it/s]
[34m[1mAutoAnchor: [0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅
Plotting labels to runs/train/exp/labels.jpg...
Image sizes 640 train, 640 val
Using 2 dataloader workers
Logging results to [1mruns/train/exp[0m
Starting training for 3 epochs...
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
0/2 3.91G 0.04618 0.07209 0.01703 232 640: 100% 8/8 [00:09<00:00, 1.17s/it]
Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 2.01it/s]
all 128 929 0.667 0.602 0.68 0.45
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
1/2 4.76G 0.04622 0.06891 0.01817 201 640: 100% 8/8 [00:02<00:00, 3.78it/s]
Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 2.16it/s]
all 128 929 0.709 0.645 0.722 0.478
Epoch GPU_mem box_loss obj_loss cls_loss Instances Size
2/2 4.76G 0.0436 0.0647 0.01698 227 640: 100% 8/8 [00:01<00:00, 4.19it/s]
Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 2.95it/s]
all 128 929 0.761 0.647 0.735 0.49
3 epochs completed in 0.006 hours.
Optimizer stripped from runs/train/exp/weights/last.pt, 14.8MB
Optimizer stripped from runs/train/exp/weights/best.pt, 14.8MB
Validating runs/train/exp/weights/best.pt...
Fusing layers...
Model summary: 157 layers, 7225885 parameters, 0 gradients, 16.4 GFLOPs
Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:06<00:00, 1.56s/it]
all 128 929 0.759 0.646 0.734 0.49
person 128 254 0.857 0.706 0.805 0.525
bicycle 128 6 0.773 0.577 0.725 0.414
car 128 46 0.664 0.435 0.551 0.24
motorcycle 128 5 0.587 0.8 0.837 0.635
airplane 128 6 1 0.989 0.995 0.715
bus 128 7 0.635 0.714 0.753 0.651
train 128 3 0.686 0.333 0.72 0.504
truck 128 12 0.604 0.333 0.472 0.259
boat 128 6 0.938 0.333 0.449 0.177
traffic light 128 14 0.778 0.255 0.401 0.217
stop sign 128 2 0.826 1 0.995 0.895
bench 128 9 0.711 0.556 0.661 0.313
bird 128 16 0.962 1 0.995 0.642
cat 128 4 0.868 1 0.995 0.754
dog 128 9 1 0.652 0.899 0.651
horse 128 2 0.853 1 0.995 0.622
elephant 128 17 0.909 0.882 0.934 0.698
bear 128 1 0.696 1 0.995 0.995
zebra 128 4 0.855 1 0.995 0.905
giraffe 128 9 0.788 0.828 0.912 0.701
backpack 128 6 0.835 0.5 0.738 0.311
umbrella 128 18 0.785 0.814 0.859 0.48
handbag 128 19 0.759 0.263 0.366 0.205
tie 128 7 0.983 0.714 0.77 0.492
suitcase 128 4 0.656 1 0.945 0.631
frisbee 128 5 0.721 0.8 0.759 0.724
skis 128 1 0.737 1 0.995 0.3
snowboard 128 7 0.829 0.696 0.83 0.537
sports ball 128 6 0.637 0.667 0.602 0.311
kite 128 10 0.636 0.6 0.599 0.226
baseball bat 128 4 0.501 0.25 0.468 0.205
baseball glove 128 7 0.483 0.429 0.465 0.292
skateboard 128 5 0.932 0.6 0.687 0.493
tennis racket 128 7 0.77 0.429 0.547 0.332
bottle 128 18 0.577 0.379 0.554 0.276
wine glass 128 16 0.704 0.875 0.89 0.51
cup 128 36 0.841 0.667 0.837 0.533
fork 128 6 0.992 0.333 0.45 0.315
knife 128 16 0.768 0.688 0.695 0.403
spoon 128 22 0.838 0.47 0.639 0.384
bowl 128 28 0.764 0.58 0.716 0.513
banana 128 1 0.902 1 0.995 0.301
sandwich 128 2 1 0 0.359 0.326
orange 128 4 0.722 0.75 0.912 0.581
broccoli 128 11 0.547 0.364 0.432 0.317
carrot 128 24 0.619 0.625 0.724 0.495
hot dog 128 2 0.409 1 0.828 0.762
pizza 128 5 0.833 0.995 0.962 0.727
donut 128 14 0.631 1 0.96 0.839
cake 128 4 0.87 1 0.995 0.83
chair 128 35 0.583 0.6 0.608 0.317
couch 128 6 0.907 0.667 0.815 0.544
potted plant 128 14 0.739 0.786 0.823 0.48
bed 128 3 0.985 0.333 0.83 0.441
dining table 128 13 0.821 0.357 0.578 0.342
toilet 128 2 1 0.988 0.995 0.846
tv 128 2 0.57 1 0.995 0.796
laptop 128 3 1 0 0.593 0.312
mouse 128 2 1 0 0.089 0.0445
remote 128 8 1 0.624 0.634 0.538
cell phone 128 8 0.622 0.417 0.421 0.187
microwave 128 3 0.711 1 0.995 0.766
oven 128 5 0.329 0.4 0.43 0.282
sink 128 6 0.437 0.333 0.338 0.265
refrigerator 128 5 0.567 0.8 0.799 0.536
book 128 29 0.597 0.257 0.349 0.154
clock 128 9 0.765 0.889 0.932 0.736
vase 128 2 0.33 1 0.995 0.895
scissors 128 1 1 0 0.497 0.0498
teddy bear 128 21 0.856 0.569 0.841 0.547
toothbrush 128 5 0.8 1 0.928 0.574
Results saved to [1mruns/train/exp[0m
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.