Glenn Jocherandpre-commit-ci[bot]
ec4de43a8a
* Update Colab Notebook CI * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Created using Colaboratory * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update tutorial.ipynb Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
56 KiB
Vendored
56 KiB
Vendored
This is the official YOLOv5 🚀 notebook by Ultralytics, and is freely available for redistribution under the GPL-3.0 license. For more information please visit https://github.com/ultralytics/yolov5 and https://ultralytics.com. Thank you!
In [ ]:
!git clone https://github.com/ultralytics/yolov5 # clone
%cd yolov5
%pip install -qr requirements.txt # install
import torch
import utils
display = utils.notebook_init() # checksYOLOv5 🚀 v6.1-257-g669f707 Python-3.7.13 torch-1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)
Setup complete ✅ (8 CPUs, 51.0 GB RAM, 38.8/166.8 GB disk)
In [ ]:
!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 YOLOv5 🚀 v6.1-257-g669f707 Python-3.7.13 torch-1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB) Downloading https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s.pt to yolov5s.pt... 100% 14.1M/14.1M [00:00<00:00, 225MB/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, Done. (0.013s) image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.015s) Speed: 0.6ms pre-process, 14.1ms inference, 23.9ms NMS per image at shape (1, 3, 640, 640) Results saved to [1mruns/detect/exp[0m
In [ ]:
# Download COCO val
torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')
!unzip -q tmp.zip -d ../datasets && rm tmp.zip0%| | 0.00/780M [00:00<?, ?B/s]
In [ ]:
# Run YOLOv5x on COCO val
!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half[34m[1mval: [0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, 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 🚀 v6.1-257-g669f707 Python-3.7.13 torch-1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)
Downloading https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5x.pt to yolov5x.pt...
100% 166M/166M [00:04<00:00, 39.4MB/s]
Fusing layers...
YOLOv5x summary: 444 layers, 86705005 parameters, 0 gradients
Downloading https://ultralytics.com/assets/Arial.ttf to /root/.config/Ultralytics/Arial.ttf...
100% 755k/755k [00:00<00:00, 47.9MB/s]
[34m[1mval: [0mScanning '/content/datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupt: 100% 5000/5000 [00:00<00:00, 8742.34it/s]
[34m[1mval: [0mNew cache created: /content/datasets/coco/val2017.cache
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:11<00:00, 2.21it/s]
all 5000 36335 0.743 0.625 0.683 0.504
Speed: 0.1ms pre-process, 4.9ms inference, 1.2ms NMS per image at shape (32, 3, 640, 640)
Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...
loading annotations into memory...
Done (t=0.42s)
creating index...
index created!
Loading and preparing results...
DONE (t=4.91s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=77.89s).
Accumulating evaluation results...
DONE (t=15.36s).
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.506
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.549
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.340
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.557
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.651
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.382
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.631
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.684
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.528
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.737
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.833
Results saved to [1mruns/val/exp[0m
In [ ]:
# Download COCO test-dev2017
torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017labels.zip', 'tmp.zip')
!unzip -q tmp.zip -d ../datasets && rm tmp.zip
!f="test2017.zip" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f -d ../datasets/coco/imagesIn [ ]:
# Run YOLOv5x on COCO test
!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half --task test3. Train
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.
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/how-to-train-yolov5-on-a-custom-dataset/
- Custom Training Notebook:
In [ ]:
# Tensorboard (optional)
%load_ext tensorboard
%tensorboard --logdir runs/trainIn [ ]:
# Weights & Biases (optional)
%pip install -q wandb
import wandb
wandb.login()In [ ]:
# Train YOLOv5s on COCO128 for 3 epochs
!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache[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, 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 🚀 v6.1-257-g669f707 Python-3.7.13 torch-1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)
[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[1mWeights & Biases: [0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)
[34m[1mTensorBoard: [0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/
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: 270 layers, 7235389 parameters, 7235389 gradients
Transferred 349/349 items from yolov5s.pt
[34m[1mAMP: [0mchecks passed ✅
Scaled weight_decay = 0.0005
[34m[1moptimizer:[0m SGD with parameter groups 57 weight (no decay), 60 weight, 60 bias
[34m[1malbumentations: [0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed
[34m[1mtrain: [0mScanning '/content/datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]
[34m[1mtrain: [0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 978.19it/s]
[34m[1mval: [0mScanning '/content/datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]
[34m[1mval: [0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 207.08it/s]
Plotting labels to runs/train/exp/labels.jpg...
[34m[1mAutoAnchor: [0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅
Image sizes 640 train, 640 val
Using 8 dataloader workers
Logging results to [1mruns/train/exp[0m
Starting training for 3 epochs...
Epoch gpu_mem box obj cls labels img_size
0/2 3.72G 0.04609 0.06258 0.01898 260 640: 100% 8/8 [00:03<00:00, 2.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.45it/s]
all 128 929 0.724 0.638 0.718 0.477
Epoch gpu_mem box obj cls labels img_size
1/2 4.57G 0.04466 0.06904 0.01721 210 640: 100% 8/8 [00:00<00:00, 8.21it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.62it/s]
all 128 929 0.732 0.658 0.746 0.488
Epoch gpu_mem box obj cls labels img_size
2/2 4.57G 0.04489 0.06445 0.01634 269 640: 100% 8/8 [00:00<00:00, 9.12it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.59it/s]
all 128 929 0.783 0.652 0.758 0.502
3 epochs completed in 0.003 hours.
Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB
Optimizer stripped from runs/train/exp/weights/best.pt, 14.9MB
Validating runs/train/exp/weights/best.pt...
Fusing layers...
Model summary: 213 layers, 7225885 parameters, 0 gradients
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.27it/s]
all 128 929 0.785 0.653 0.761 0.503
person 128 254 0.866 0.71 0.82 0.531
bicycle 128 6 0.764 0.546 0.62 0.375
car 128 46 0.615 0.556 0.565 0.211
motorcycle 128 5 1 0.952 0.995 0.761
airplane 128 6 0.937 1 0.995 0.751
bus 128 7 0.816 0.714 0.723 0.642
train 128 3 0.985 0.667 0.863 0.561
truck 128 12 0.553 0.417 0.481 0.258
boat 128 6 1 0.317 0.418 0.132
traffic light 128 14 0.668 0.287 0.372 0.227
stop sign 128 2 0.789 1 0.995 0.796
bench 128 9 0.691 0.444 0.614 0.265
bird 128 16 0.955 1 0.995 0.666
cat 128 4 0.811 1 0.995 0.797
dog 128 9 1 0.657 0.886 0.637
horse 128 2 0.806 1 0.995 0.647
elephant 128 17 0.955 0.882 0.932 0.691
bear 128 1 0.681 1 0.995 0.895
zebra 128 4 0.87 1 0.995 0.947
giraffe 128 9 0.881 1 0.995 0.734
backpack 128 6 0.926 0.667 0.808 0.359
umbrella 128 18 0.811 0.667 0.864 0.507
handbag 128 19 0.768 0.211 0.352 0.183
tie 128 7 0.778 0.714 0.822 0.495
suitcase 128 4 0.805 1 0.995 0.534
frisbee 128 5 0.697 0.8 0.8 0.74
skis 128 1 0.734 1 0.995 0.4
snowboard 128 7 0.859 0.714 0.852 0.563
sports ball 128 6 0.612 0.667 0.603 0.328
kite 128 10 0.855 0.592 0.624 0.249
baseball bat 128 4 0.403 0.25 0.401 0.171
baseball glove 128 7 0.7 0.429 0.467 0.323
skateboard 128 5 1 0.57 0.862 0.512
tennis racket 128 7 0.753 0.429 0.635 0.327
bottle 128 18 0.59 0.4 0.578 0.293
wine glass 128 16 0.654 1 0.925 0.503
cup 128 36 0.77 0.806 0.845 0.521
fork 128 6 0.988 0.333 0.44 0.312
knife 128 16 0.755 0.579 0.684 0.404
spoon 128 22 0.827 0.436 0.629 0.354
bowl 128 28 0.784 0.648 0.753 0.528
banana 128 1 0.802 1 0.995 0.108
sandwich 128 2 1 0 0.606 0.545
orange 128 4 0.921 1 0.995 0.691
broccoli 128 11 0.379 0.455 0.468 0.338
carrot 128 24 0.777 0.542 0.73 0.503
hot dog 128 2 0.562 1 0.828 0.712
pizza 128 5 0.802 0.814 0.962 0.694
donut 128 14 0.694 1 0.981 0.848
cake 128 4 0.864 1 0.995 0.858
chair 128 35 0.636 0.648 0.628 0.319
couch 128 6 1 0.606 0.857 0.555
potted plant 128 14 0.739 0.786 0.837 0.476
bed 128 3 1 0 0.806 0.568
dining table 128 13 0.862 0.483 0.602 0.405
toilet 128 2 0.941 1 0.995 0.846
tv 128 2 0.677 1 0.995 0.796
laptop 128 3 1 0 0.83 0.532
mouse 128 2 1 0 0.0931 0.0466
remote 128 8 1 0.612 0.659 0.534
cell phone 128 8 0.645 0.25 0.437 0.227
microwave 128 3 0.797 1 0.995 0.734
oven 128 5 0.435 0.4 0.44 0.29
sink 128 6 0.345 0.167 0.301 0.211
refrigerator 128 5 0.645 0.8 0.804 0.545
book 128 29 0.603 0.207 0.301 0.171
clock 128 9 0.785 0.889 0.888 0.734
vase 128 2 0.477 1 0.995 0.92
scissors 128 1 1 0 0.995 0.199
teddy bear 128 21 0.862 0.667 0.823 0.549
toothbrush 128 5 0.809 1 0.995 0.65
Results saved to [1mruns/train/exp[0m
Weights & Biases Logging 🌟 NEW
Weights & Biases (W&B) is now integrated with YOLOv5 for real-time visualization and cloud logging of training runs. This allows for better run comparison and introspection, as well improved visibility and collaboration for teams. To enable W&B pip install wandb, and then train normally (you will be guided through setup on first use).
During training you will see live updates at https://wandb.ai/home, and you can create and share detailed Reports of your results. For more information see the YOLOv5 Weights & Biases Tutorial.
Local Logging
All results are logged by default to runs/train, with a new experiment directory created for each new training as runs/train/exp2, runs/train/exp3, etc. View train and val jpgs to see mosaics, labels, predictions and augmentation effects. Note an Ultralytics Mosaic Dataloader is used for training (shown below), which combines 4 images into 1 mosaic during training.
train_batch0.jpg shows train batch 0 mosaics and labels
test_batch0_labels.jpg shows val batch 0 labels
test_batch0_pred.jpg shows val batch 0 predictions
Training results are automatically logged to Tensorboard and CSV as results.csv, which is plotted as results.png (below) after training completes. You can also plot any results.csv file manually:
from utils.plots import plot_results
plot_results('path/to/results.csv') # plot 'results.csv' as 'results.png'
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):
- Google Colab and Kaggle 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.
In [ ]:
# Reproduce
for x in 'yolov5n', 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':
!python val.py --weights {x}.pt --data coco.yaml --img 640 --task speed # speed
!python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65 # mAPIn [ ]:
# PyTorch Hub
import torch
# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
# Images
dir = 'https://ultralytics.com/images/'
imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')] # batch of images
# Inference
results = model(imgs)
results.print() # or .show(), .save()In [ ]:
# YOLOv5 CI
%%shell
rm -rf runs # remove runs/
m=yolov5n # official weights
b=runs/train/exp/weights/best # best.pt checkpoint
python train.py --imgsz 64 --batch 32 --weights $m.pt --cfg $m.yaml --epochs 1 --device 0 # train
for d in 0 cpu; do # devices
for w in $m $b; do # weights
python val.py --imgsz 64 --batch 32 --weights $w.pt --device $d # val
python detect.py --imgsz 64 --weights $w.pt --device $d # detect
done
done
python hubconf.py --model $m # hub
python models/tf.py --weights $m.pt # build TF model
python models/yolo.py --cfg $m.yaml # build PyTorch model
python export.py --weights $m.pt --img 64 --include torchscript # exportIn [ ]:
# Profile
from utils.torch_utils import profile
m1 = lambda x: x * torch.sigmoid(x)
m2 = torch.nn.SiLU()
results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)In [ ]:
# Evolve
!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov5s.pt --cache --noautoanchor --evolve
!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket # upload results (optional)In [ ]:
# VOC
for b, m in zip([64, 64, 64, 32, 16], ['yolov5n', 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']): # batch, model
!python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --img 512 --hyp hyp.VOC.yaml --project VOC --name {m} --cacheIn [ ]:
# TensorRT
# https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-pip
!pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com # install
!python export.py --weights yolov5s.pt --include engine --imgsz 640 --device 0 # export
!python detect.py --weights yolov5s.engine --imgsz 640 --device 0 # inference