v6.0.5

What's Changed

• coco dataset support, automatic aws weight upload by @fcakyon in #54
• add dataset upload, add neptune dataset tracking by @fcakyon in #59
• add windows support for dataset upload by @fcakyon in #61
• make pycocotools optional by @fcakyon in #56
• remove python 3.6 in tests by @fcakyon in #57
• add missing argument in readme by @fcakyon in #60
• fix omp error in windows by @fcakyon in #62
• fix weight s3 uri for windows by @fcakyon in #63

Full Changelog: 6.0.4...6.0.5

COCO Dataset Support

• Start a training using a COCO formatted dataset:

# data.yml
train_json_path: "train.json"
train_image_dir: "train_image_dir/"
val_json_path: "val.json"
val_image_dir: "val_image_dir/"

$ yolov5 train --data data.yaml --weights yolov5s.pt

New AWS and Neptune.AI Utilities

• Automatically upload weights and datasets to AWS S3 (with Neptune.AI artifact tracking integration):

export AWS_ACCESS_KEY_ID=YOUR_KEY
export AWS_SECRET_ACCESS_KEY=YOUR_KEY

$ yolov5 train --data data.yaml --weights yolov5s.pt --s3_upload_dir YOUR_S3_FOLDER_DIRECTORY --upload_dataset

• Add yolo_s3_data_dir into data.yaml to match Neptune dataset with a present dataset in S3.

# data.yml
train_json_path: "train.json"
train_image_dir: "train_image_dir/"
val_json_path: "val.json"
val_image_dir: "val_image_dir/"
yolo_s3_data_dir: s3://bucket_name/data_dir/

v6.0.4

new features

• export and log results.html at the end of training, log category based metrics (#51)
• handle when neptune installed but not set (#50)

v6.0.3

update v6.0.3

• update to 19.10.21 ultralytics/yolov5: https://github.com/ultralytics/yolov5/tree/a18b0c36cd4df0d3b9c2623c5dda009c5f281ac9
• fix a neptune logging error

v6.0.1

YOLOv5 object detector v6.0 is now in pip !

Use from Python

Basic

import yolov5

# load model
model = yolov5.load('yolov5s')

# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

# perform inference
results = model(img)

# inference with larger input size
results = model(img, size=1280)

# inference with test time augmentation
results = model(img, augment=True)

# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, x2, y1, y2
scores = predictions[:, 4]
categories = predictions[:, 5]

# show detection bounding boxes on image
results.show()

# save results into "results/" folder
results.save(save_dir='results/')

Alternative

from yolov5 import YOLOv5

# set model params
model_path = "yolov5/weights/yolov5s.pt"
device = "cuda:0" # or "cpu"

# init yolov5 model
yolov5 = YOLOv5(model_path, device)

# load images
image1 = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
image2 = 'https://github.com/ultralytics/yolov5/blob/master/data/images/bus.jpg'

# perform inference
results = yolov5.predict(image1)

# perform inference with larger input size
results = yolov5.predict(image1, size=1280)

# perform inference with test time augmentation
results = yolov5.predict(image1, augment=True)

# perform inference on multiple images
results = yolov5.predict([image1, image2], size=1280, augment=True)

# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, x2, y1, y2
scores = predictions[:, 4]
categories = predictions[:, 5]

# show detection bounding boxes on image
results.show()

# save results into "results/" folder
results.save(save_dir='results/')

Train/Detect/Test/Export

• You can directly use these functions by importing them:

from yolov5 import train, val, detect, export

train.run(imgsz=640, data='coco128.yaml')
val.run(imgsz=640, data='coco128.yaml', weights='yolov5s.pt')
detect.run(imgsz=640)
export.run(imgsz=640, weights='yolov5s.pt')

• You can pass any argument as input:

from yolov5 import detect

img_url = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

detect.run(source=img_url, weights="yolov5s6.pt", conf_thres=0.25, imgsz=640)

Use from CLI

You can call yolov5 train, yolov5 detect, yolov5 val and yolov5 export commands after installing the package via pip:

Training

Finetune one of the pretrained YOLOv5 models using your custom data.yaml:

$ yolov5 train --data data.yaml --weights yolov5s.pt --batch-size 16 --img 640
                                          yolov5m.pt              8
                                          yolov5l.pt              4
                                          yolov5x.pt              2

Visualize your experiments via Neptune.AI:

$ yolov5 train --data data.yaml --weights yolov5s.pt --neptune_project NAMESPACE/PROJECT_NAME --neptune_token YOUR_NEPTUNE_TOKEN

Inference

yolov5 detect command runs inference on a variety of sources, downloading models automatically from the latest YOLOv5 release and saving results to runs/detect.

$ yolov5 detect --source 0  # webcam
                         file.jpg  # image
                         file.mp4  # video
                         path/  # directory
                         path/*.jpg  # glob
                         rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa  # rtsp stream
                         rtmp://192.168.1.105/live/test  # rtmp stream
                         http://112.50.243.8/PLTV/88888888/224/3221225900/1.m3u8  # http stream

Export

You can export your fine-tuned YOLOv5 weights to any format such as torchscript, onnx, coreml, pb, tflite, tfjs:

$ yolov5 export --weights yolov5s.pt --include 'torchscript,onnx,coreml,pb,tfjs'

v5.0.10

• fix https://github.com/fcakyon/yolov5-pip/issues/40

v5.0.9

• minor neptune logger fix 571bd4e

v5.0.8

• update to 24.08.21 ultralytics/yolov5

• cli api changes:

Use from CLI

You can call yolov5 train, yolov5 detect, yolov5 val and yolov5 export commands after installing the package via pip:

Training

Run commands below to reproduce results on COCO dataset (dataset auto-downloads on first use). Training times for YOLOv5s/m/l/x are 2/4/6/8 days on a single V100 (multi-GPU times faster). Use the largest --batch-size your GPU allows (batch sizes shown for 16 GB devices).

$ yolov5 train --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size 64
                                      yolov5m                                40
                                      yolov5l                                24
                                      yolov5x                                16

Inference

yolov5 detect command runs inference on a variety of sources, downloading models automatically from the latest YOLOv5 release and saving results to runs/detect.

$ yolov5 detect --img 1280 --source 0  # webcam
                                    file.jpg  # image
                                    file.mp4  # video
                                    path/  # directory
                                    path/*.jpg  # glob
                                    rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa  # rtsp stream
                                    rtmp://192.168.1.105/live/test  # rtmp stream
                                    http://112.50.243.8/PLTV/88888888/224/3221225900/1.m3u8  # http stream

To run inference on example images in yolov5/data/images:

v5.0.7

• remove check_requirements (#37)

v5.0.6

Install

Install yolov5 using pip (for Python >=3.7)

pip install yolov5

Install yolov5 using pip `(for Python 3.6)`

pip install "numpy>=1.18.5,<1.20" "matplotlib>=3.2.2,<4"
pip install yolov5

Use from Python

Basic

import yolov5

# load model
model = yolov5.load('yolov5s')

# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

# perform inference
results = model(img)

# inference with larger input size
results = model(img, size=1280)

# inference with test time augmentation
results = model(img, augment=True)

# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, x2, y1, y2
scores = predictions[:, 4]
categories = predictions[:, 5]

# show detection bounding boxes on image
results.show()

# save results into "results/" folder
results.save(save_dir='results/')

Alternative

from yolov5 import YOLOv5

# set model params
model_path = "yolov5/weights/yolov5s.pt" # it automatically downloads yolov5s model to given path
device = "cuda" # or "cpu"

# init yolov5 model
yolov5 = YOLOv5(model_path, device)

# load images
image1 = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
image2 = 'https://github.com/ultralytics/yolov5/blob/master/data/images/bus.jpg'

# perform inference
results = yolov5.predict(image1)

# perform inference with larger input size
results = yolov5.predict(image1, size=1280)

# perform inference with test time augmentation
results = yolov5.predict(image1, augment=True)

# perform inference on multiple images
results = yolov5.predict([image1, image2], size=1280, augment=True)

# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, x2, y1, y2
scores = predictions[:, 4]
categories = predictions[:, 5]

# show detection bounding boxes on image
results.show()

# save results into "results/" folder
results.save(save_dir='results/')

Train/Detect/Test/Export

• You can directly use these functions by importing them:

from yolov5 import train, test, detect, export

train.run(imgsz=640, data='coco128.yaml')
test.run(imgsz=640, data='coco128.yaml', weights='yolov5s.pt')
detect.run(imgsz=640)
export.run(imgsz=640, weights='yolov5s.pt')

• You can pass any argument as input:

from yolov5 import detect

img_url = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

detect.run(source=img_url, weights="yolov5s6.pt", conf_thres=0.25, imgsz=640)

Use from CLI

You can call yolo_train, yolo_detect, yolo_test and yolo_export commands after installing the package via pip:

Training

Run commands below to reproduce results on COCO dataset (dataset auto-downloads on first use). Training times for YOLOv5s/m/l/x are 2/4/6/8 days on a single V100 (multi-GPU times faster). Use the largest --batch-size your GPU allows (batch sizes shown for 16 GB devices).

$ yolo_train --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size 64
                                    yolov5m                                40
                                    yolov5l                                24
                                    yolov5x                                16

Inference

yolo_detect command runs inference on a variety of sources, downloading models automatically from the latest YOLOv5 release and saving results to runs/detect.

$ yolo_detect --source 0  # webcam
                       file.jpg  # image
                       file.mp4  # video
                       path/  # directory
                       path/*.jpg  # glob
                       rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa  # rtsp stream
                       rtmp://192.168.1.105/live/test  # rtmp stream
                       http://112.50.243.8/PLTV/88888888/224/3221225900/1.m3u8  # http stream

To run inference on example images in yolov5/data/images:

v5.0.5

• Synchronized with 11.05.21 ultralytics/yolov5 repo.

PLUS:

• neptune ai support:
  yolo_train --data coco.yaml --weights yolov5s.pt --neptune_token YOUR_TOKEN --neptune_project YOUR/PROJECT

• mmdet style metric logging support
  yolo_train --data coco.yaml --weights yolov5s.pt --mmdet_tags