2021-1-capstone-design1 / HCS_Project2

Go to a project
Toggle navigation Toggle navigation pinning
김연수
a4ed6069 1 parent c8199b6d

YOLOv5 for LP detection

Expand all
Inline Side-by-side
Showing 60 changed files with 3225 additions and 0 deletions
# Repo-specific DockerIgnore -------------------------------------------------------------------------------------------
#.git
.cache
.idea
runs
output
coco
storage.googleapis.com
data/samples/*
**/results*.txt
*.jpg
# Neural Network weights -----------------------------------------------------------------------------------------------
**/*.weights
**/*.pt
**/*.pth
**/*.onnx
**/*.mlmodel
**/*.torchscript
# Below Copied From .gitignore -----------------------------------------------------------------------------------------
# Below Copied From .gitignore -----------------------------------------------------------------------------------------
# GitHub Python GitIgnore ----------------------------------------------------------------------------------------------
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
env/
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
wandb/
.installed.cfg
*.egg
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
.hypothesis/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# pyenv
.python-version
# celery beat schedule file
celerybeat-schedule
# SageMath parsed files
*.sage.py
# dotenv
.env
# virtualenv
.venv*
venv*/
ENV*/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
# https://github.com/github/gitignore/blob/master/Global/macOS.gitignore -----------------------------------------------
# General
.DS_Store
.AppleDouble
.LSOverride
# Icon must end with two \r
Icon
Icon?
# Thumbnails
._*
# Files that might appear in the root of a volume
.DocumentRevisions-V100
.fseventsd
.Spotlight-V100
.TemporaryItems
.Trashes
.VolumeIcon.icns
.com.apple.timemachine.donotpresent
# Directories potentially created on remote AFP share
.AppleDB
.AppleDesktop
Network Trash Folder
Temporary Items
.apdisk
# https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
# User-specific stuff:
.idea/*
.idea/**/workspace.xml
.idea/**/tasks.xml
.idea/dictionaries
.html # Bokeh Plots
.pg # TensorFlow Frozen Graphs
.avi # videos
# Sensitive or high-churn files:
.idea/**/dataSources/
.idea/**/dataSources.ids
.idea/**/dataSources.local.xml
.idea/**/sqlDataSources.xml
.idea/**/dynamic.xml
.idea/**/uiDesigner.xml
# Gradle:
.idea/**/gradle.xml
.idea/**/libraries
# CMake
cmake-build-debug/
cmake-build-release/
# Mongo Explorer plugin:
.idea/**/mongoSettings.xml
## File-based project format:
*.iws
## Plugin-specific files:
# IntelliJ
out/
# mpeltonen/sbt-idea plugin
.idea_modules/
# JIRA plugin
atlassian-ide-plugin.xml
# Cursive Clojure plugin
.idea/replstate.xml
# Crashlytics plugin (for Android Studio and IntelliJ)
com_crashlytics_export_strings.xml
crashlytics.properties
crashlytics-build.properties
fabric.properties
# this drop notebooks from GitHub language stats
*.ipynb linguist-vendored
# Repo-specific GitIgnore ----------------------------------------------------------------------------------------------
*.jpg
*.jpeg
*.png
*.bmp
*.tif
*.tiff
*.heic
*.JPG
*.JPEG
*.PNG
*.BMP
*.TIF
*.TIFF
*.HEIC
*.mp4
*.mov
*.MOV
*.avi
*.data
*.json
*.cfg
!cfg/yolov3*.cfg
storage.googleapis.com
runs/*
data/*
!data/images/zidane.jpg
!data/images/bus.jpg
!data/coco.names
!data/coco_paper.names
!data/coco.data
!data/coco_*.data
!data/coco_*.txt
!data/trainvalno5k.shapes
!data/*.sh
pycocotools/*
results*.txt
gcp_test*.sh
# Datasets -------------------------------------------------------------------------------------------------------------
coco/
coco128/
VOC/
# MATLAB GitIgnore -----------------------------------------------------------------------------------------------------
*.m~
*.mat
!targets*.mat
# Neural Network weights -----------------------------------------------------------------------------------------------
*.weights
*.pt
*.onnx
*.mlmodel
*.torchscript
darknet53.conv.74
yolov3-tiny.conv.15
# GitHub Python GitIgnore ----------------------------------------------------------------------------------------------
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
env/
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
wandb/
.installed.cfg
*.egg
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
.hypothesis/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# pyenv
.python-version
# celery beat schedule file
celerybeat-schedule
# SageMath parsed files
*.sage.py
# dotenv
.env
# virtualenv
.venv*
venv*/
ENV*/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
# https://github.com/github/gitignore/blob/master/Global/macOS.gitignore -----------------------------------------------
# General
.DS_Store
.AppleDouble
.LSOverride
# Icon must end with two \r
Icon
Icon?
# Thumbnails
._*
# Files that might appear in the root of a volume
.DocumentRevisions-V100
.fseventsd
.Spotlight-V100
.TemporaryItems
.Trashes
.VolumeIcon.icns
.com.apple.timemachine.donotpresent
# Directories potentially created on remote AFP share
.AppleDB
.AppleDesktop
Network Trash Folder
Temporary Items
.apdisk
# https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
# User-specific stuff:
.idea/*
.idea/**/workspace.xml
.idea/**/tasks.xml
.idea/dictionaries
.html # Bokeh Plots
.pg # TensorFlow Frozen Graphs
.avi # videos
# Sensitive or high-churn files:
.idea/**/dataSources/
.idea/**/dataSources.ids
.idea/**/dataSources.local.xml
.idea/**/sqlDataSources.xml
.idea/**/dynamic.xml
.idea/**/uiDesigner.xml
# Gradle:
.idea/**/gradle.xml
.idea/**/libraries
# CMake
cmake-build-debug/
cmake-build-release/
# Mongo Explorer plugin:
.idea/**/mongoSettings.xml
## File-based project format:
*.iws
## Plugin-specific files:
# IntelliJ
out/
# mpeltonen/sbt-idea plugin
.idea_modules/
# JIRA plugin
atlassian-ide-plugin.xml
# Cursive Clojure plugin
.idea/replstate.xml
# Crashlytics plugin (for Android Studio and IntelliJ)
com_crashlytics_export_strings.xml
crashlytics.properties
crashlytics-build.properties
fabric.properties
# Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
FROM nvcr.io/nvidia/pytorch:21.03-py3
# Install linux packages
RUN apt update && apt install -y zip htop screen libgl1-mesa-glx
# Install python dependencies
COPY requirements.txt .
RUN python -m pip install --upgrade pip
RUN pip uninstall -y nvidia-tensorboard nvidia-tensorboard-plugin-dlprof
RUN pip install --no-cache -r requirements.txt coremltools onnx gsutil notebook
# Create working directory
RUN mkdir -p /usr/src/app
WORKDIR /usr/src/app
# Copy contents
COPY . /usr/src/app
# Set environment variables
ENV HOME=/usr/src/app
# --------------------------------------------------- Extras Below ---------------------------------------------------
# Build and Push
# t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t
# for v in {300..303}; do t=ultralytics/coco:v$v && sudo docker build -t $t . && sudo docker push $t; done
# Pull and Run
# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t
# Pull and Run with local directory access
# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/coco:/usr/src/coco $t
# Kill all
# sudo docker kill $(sudo docker ps -q)
# Kill all image-based
# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest)
# Bash into running container
# sudo docker exec -it 5a9b5863d93d bash
# Bash into stopped container
# id=$(sudo docker ps -qa) && sudo docker start $id && sudo docker exec -it $id bash
# Send weights to GCP
# python -c "from utils.general import *; strip_optimizer('runs/train/exp0_*/weights/best.pt', 'tmp.pt')" && gsutil cp tmp.pt gs://*.pt
# Clean up
# docker system prune -a --volumes
This diff is collapsed. Click to expand it.
This diff is collapsed. Click to expand it.
File mode changed
import argparse
import time
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path, save_one_box
from utils.plots import colors, plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized
@torch.no_grad()
def detect(opt):
# source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, True, opt.img_size
save_img = not opt.nosave and not source.endswith('.txt') # save inference images
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))
# Directories
save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Initialize
set_logging()
device = select_device(opt.device)
half = device.type != 'cpu' # half precision only supported on CUDA
# Load model
model = attempt_load(weights, map_location=device) # load FP32 model
stride = int(model.stride.max()) # model stride
imgsz = check_img_size(imgsz, s=stride) # check img_size
names = model.module.names if hasattr(model, 'module') else model.names # get class names
if half:
model.half() # to FP16
# Second-stage classifier
classify = False
if classify:
modelc = load_classifier(name='resnet101', n=2) # initialize
modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride)
# Run inference
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
t0 = time.time()
for path, img, im0s, vid_cap in dataset:
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
# Inference
t1 = time_synchronized()
pred = model(img, augment=opt.augment)[0]
# Apply NMS
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, opt.classes, opt.agnostic_nms,
max_det=opt.max_det)
t2 = time_synchronized()
# Apply Classifier
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# Process detections
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
else:
p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # img.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
imc = im0.copy() if opt.save_crop else im0 # for opt.save_crop
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
# Write results
for *xyxy, conf, cls in reversed(det):
if save_txt: # Write to file
# print("+++++++++++++++++++++++++++++++++")
# print(torch.tensor(xyxy))
# print("+++++++++++++++++++++++++++++++++")
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
# print("+++++++++++++++++++++++++++++++++")
# print(xywh)
# print("+++++++++++++++++++++++++++++++++")
line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or opt.save_crop or view_img: # Add bbox to image
c = int(cls) # integer class
label = None if opt.hide_labels else (names[c] if opt.hide_conf else f'{names[c]} {conf:.2f}')
plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=opt.line_thickness)
# if opt.save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# Print time (inference + NMS)
print(f'{s}Done. ({t2 - t1:.3f}s)')
# Stream results
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video' or 'stream'
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release() # release previous video writer
if vid_cap: # video
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path += '.mp4'
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer.write(im0)
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
print(f"Results saved to {save_dir}{s}")
print(f'Done. ({time.time() - t0:.3f}s)')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='data/images', help='source') # file/folder, 0 for webcam
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
parser.add_argument('--max-det', type=int, default=1000, help='maximum number of detections per image')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--view-img', action='store_true', help='display results')
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
parser.add_argument('--augment', action='store_true', help='augmented inference')
parser.add_argument('--update', action='store_true', help='update all models')
parser.add_argument('--project', default='runs/detect', help='save results to project/name')
parser.add_argument('--name', default='exp', help='save results to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
opt = parser.parse_args()
print(opt)
check_requirements(exclude=('tensorboard', 'pycocotools', 'thop'))
if opt.update: # update all models (to fix SourceChangeWarning)
for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
detect(opt=opt)
strip_optimizer(opt.weights)
else:
detect(opt=opt)
"""YOLOv5 PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5/
Usage:
import torch
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
"""
import torch
def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
"""Creates a specified YOLOv5 model
Arguments:
name (str): name of model, i.e. 'yolov5s'
pretrained (bool): load pretrained weights into the model
channels (int): number of input channels
classes (int): number of model classes
autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
verbose (bool): print all information to screen
device (str, torch.device, None): device to use for model parameters
Returns:
YOLOv5 pytorch model
"""
from pathlib import Path
from models.yolo import Model, attempt_load
from utils.general import check_requirements, set_logging
from utils.google_utils import attempt_download
from utils.torch_utils import select_device
check_requirements(Path(__file__).parent / 'requirements.txt', exclude=('tensorboard', 'pycocotools', 'thop'))
set_logging(verbose=verbose)
fname = Path(name).with_suffix('.pt') # checkpoint filename
try:
if pretrained and channels == 3 and classes == 80:
model = attempt_load(fname, map_location=torch.device('cpu')) # download/load FP32 model
else:
cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path
model = Model(cfg, channels, classes) # create model
if pretrained:
ckpt = torch.load(attempt_download(fname), map_location=torch.device('cpu')) # load
msd = model.state_dict() # model state_dict
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape} # filter
model.load_state_dict(csd, strict=False) # load
if len(ckpt['model'].names) == classes:
model.names = ckpt['model'].names # set class names attribute
if autoshape:
model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS
device = select_device('0' if torch.cuda.is_available() else 'cpu') if device is None else torch.device(device)
return model.to(device)
except Exception as e:
help_url = 'https://github.com/ultralytics/yolov5/issues/36'
s = 'Cache may be out of date, try `force_reload=True`. See %s for help.' % help_url
raise Exception(s) from e
def custom(path='path/to/model.pt', autoshape=True, verbose=True, device=None):
# YOLOv5 custom or local model
return _create(path, autoshape=autoshape, verbose=verbose, device=device)
def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
# YOLOv5-small model https://github.com/ultralytics/yolov5
return _create('yolov5s', pretrained, channels, classes, autoshape, verbose, device)
def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
# YOLOv5-medium model https://github.com/ultralytics/yolov5
return _create('yolov5m', pretrained, channels, classes, autoshape, verbose, device)
def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
# YOLOv5-large model https://github.com/ultralytics/yolov5
return _create('yolov5l', pretrained, channels, classes, autoshape, verbose, device)
def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
# YOLOv5-xlarge model https://github.com/ultralytics/yolov5
return _create('yolov5x', pretrained, channels, classes, autoshape, verbose, device)
def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
# YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
return _create('yolov5s6', pretrained, channels, classes, autoshape, verbose, device)
def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
# YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
return _create('yolov5m6', pretrained, channels, classes, autoshape, verbose, device)
def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
# YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
return _create('yolov5l6', pretrained, channels, classes, autoshape, verbose, device)
def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
# YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
return _create('yolov5x6', pretrained, channels, classes, autoshape, verbose, device)
if __name__ == '__main__':
model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True) # pretrained
# model = custom(path='path/to/model.pt') # custom
# Verify inference
import cv2
import numpy as np
from PIL import Image
imgs = ['data/images/zidane.jpg', # filename
'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg', # URI
cv2.imread('data/images/bus.jpg')[:, :, ::-1], # OpenCV
Image.open('data/images/bus.jpg'), # PIL
np.zeros((320, 640, 3))] # numpy
results = model(imgs) # batched inference
results.print()
results.save()
File mode changed
This diff is collapsed. Click to expand it.
# YOLOv5 experimental modules
import numpy as np
import torch
import torch.nn as nn
from models.common import Conv, DWConv
from utils.google_utils import attempt_download
class CrossConv(nn.Module):
# Cross Convolution Downsample
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
# ch_in, ch_out, kernel, stride, groups, expansion, shortcut
super(CrossConv, self).__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, (1, k), (1, s))
self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class Sum(nn.Module):
# Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
def __init__(self, n, weight=False): # n: number of inputs
super(Sum, self).__init__()
self.weight = weight # apply weights boolean
self.iter = range(n - 1) # iter object
if weight:
self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True) # layer weights
def forward(self, x):
y = x[0] # no weight
if self.weight:
w = torch.sigmoid(self.w) * 2
for i in self.iter:
y = y + x[i + 1] * w[i]
else:
for i in self.iter:
y = y + x[i + 1]
return y
class GhostConv(nn.Module):
# Ghost Convolution https://github.com/huawei-noah/ghostnet
def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
super(GhostConv, self).__init__()
c_ = c2 // 2 # hidden channels
self.cv1 = Conv(c1, c_, k, s, None, g, act)
self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
def forward(self, x):
y = self.cv1(x)
return torch.cat([y, self.cv2(y)], 1)
class GhostBottleneck(nn.Module):
# Ghost Bottleneck https://github.com/huawei-noah/ghostnet
def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride
super(GhostBottleneck, self).__init__()
c_ = c2 // 2
self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1), # pw
DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw
GhostConv(c_, c2, 1, 1, act=False)) # pw-linear
self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
def forward(self, x):
return self.conv(x) + self.shortcut(x)
class MixConv2d(nn.Module):
# Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
super(MixConv2d, self).__init__()
groups = len(k)
if equal_ch: # equal c_ per group
i = torch.linspace(0, groups - 1E-6, c2).floor() # c2 indices
c_ = [(i == g).sum() for g in range(groups)] # intermediate channels
else: # equal weight.numel() per group
b = [c2] + [0] * groups
a = np.eye(groups + 1, groups, k=-1)
a -= np.roll(a, 1, axis=1)
a *= np.array(k) ** 2
a[0] = 1
c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
self.bn = nn.BatchNorm2d(c2)
self.act = nn.LeakyReLU(0.1, inplace=True)
def forward(self, x):
return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
class Ensemble(nn.ModuleList):
# Ensemble of models
def __init__(self):
super(Ensemble, self).__init__()
def forward(self, x, augment=False):
y = []
for module in self:
y.append(module(x, augment)[0])
# y = torch.stack(y).max(0)[0] # max ensemble
# y = torch.stack(y).mean(0) # mean ensemble
y = torch.cat(y, 1) # nms ensemble
return y, None # inference, train output
def attempt_load(weights, map_location=None, inplace=True):
from models.yolo import Detect, Model
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
model = Ensemble()
for w in weights if isinstance(weights, list) else [weights]:
ckpt = torch.load(attempt_download(w), map_location=map_location) # load
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
# Compatibility updates
for m in model.modules():
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:
m.inplace = inplace # pytorch 1.7.0 compatibility
elif type(m) is Conv:
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
if len(model) == 1:
return model[-1] # return model
else:
print(f'Ensemble created with {weights}\n')
for k in ['names']:
setattr(model, k, getattr(model[-1], k))
model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride
return model # return ensemble
"""Exports a YOLOv5 *.pt model to TorchScript, ONNX, CoreML formats
Usage:
$ python path/to/models/export.py --weights yolov5s.pt --img 640 --batch 1
"""
import argparse
import sys
import time
from pathlib import Path
sys.path.append(Path(__file__).parent.parent.absolute().__str__()) # to run '$ python *.py' files in subdirectories
import torch
import torch.nn as nn
from torch.utils.mobile_optimizer import optimize_for_mobile
import models
from models.experimental import attempt_load
from utils.activations import Hardswish, SiLU
from utils.general import colorstr, check_img_size, check_requirements, file_size, set_logging
from utils.torch_utils import select_device
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path')
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') # height, width
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--include', nargs='+', default=['torchscript', 'onnx', 'coreml'], help='include formats')
parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
parser.add_argument('--train', action='store_true', help='model.train() mode')
parser.add_argument('--optimize', action='store_true', help='optimize TorchScript for mobile') # TorchScript-only
parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes') # ONNX-only
parser.add_argument('--simplify', action='store_true', help='simplify ONNX model') # ONNX-only
parser.add_argument('--opset-version', type=int, default=12, help='ONNX opset version') # ONNX-only
opt = parser.parse_args()
opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand
opt.include = [x.lower() for x in opt.include]
print(opt)
set_logging()
t = time.time()
# Load PyTorch model
device = select_device(opt.device)
model = attempt_load(opt.weights, map_location=device) # load FP32 model
labels = model.names
# Checks
gs = int(max(model.stride)) # grid size (max stride)
opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples
assert not (opt.device.lower() == 'cpu' and opt.half), '--half only compatible with GPU export, i.e. use --device 0'
# Input
img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device) # image size(1,3,320,192) iDetection
# Update model
if opt.half:
img, model = img.half(), model.half() # to FP16
if opt.train:
model.train() # training mode (no grid construction in Detect layer)
for k, m in model.named_modules():
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
if isinstance(m, models.common.Conv): # assign export-friendly activations
if isinstance(m.act, nn.Hardswish):
m.act = Hardswish()
elif isinstance(m.act, nn.SiLU):
m.act = SiLU()
elif isinstance(m, models.yolo.Detect):
m.inplace = opt.inplace
m.onnx_dynamic = opt.dynamic
# m.forward = m.forward_export # assign forward (optional)
for _ in range(2):
y = model(img) # dry runs
print(f"\n{colorstr('PyTorch:')} starting from {opt.weights} ({file_size(opt.weights):.1f} MB)")
# TorchScript export -----------------------------------------------------------------------------------------------
if 'torchscript' in opt.include or 'coreml' in opt.include:
prefix = colorstr('TorchScript:')
try:
print(f'\n{prefix} starting export with torch {torch.__version__}...')
f = opt.weights.replace('.pt', '.torchscript.pt') # filename
ts = torch.jit.trace(model, img, strict=False)
(optimize_for_mobile(ts) if opt.optimize else ts).save(f)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'{prefix} export failure: {e}')
# ONNX export ------------------------------------------------------------------------------------------------------
if 'onnx' in opt.include:
prefix = colorstr('ONNX:')
try:
import onnx
print(f'{prefix} starting export with onnx {onnx.__version__}...')
f = opt.weights.replace('.pt', '.onnx') # filename
torch.onnx.export(model, img, f, verbose=False, opset_version=opt.opset_version, input_names=['images'],
training=torch.onnx.TrainingMode.TRAINING if opt.train else torch.onnx.TrainingMode.EVAL,
do_constant_folding=not opt.train,
dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # size(1,3,640,640)
'output': {0: 'batch', 2: 'y', 3: 'x'}} if opt.dynamic else None)
# Checks
model_onnx = onnx.load(f) # load onnx model
onnx.checker.check_model(model_onnx) # check onnx model
# print(onnx.helper.printable_graph(model_onnx.graph)) # print
# Simplify
if opt.simplify:
try:
check_requirements(['onnx-simplifier'])
import onnxsim
print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
model_onnx, check = onnxsim.simplify(
model_onnx,
dynamic_input_shape=opt.dynamic,
input_shapes={'images': list(img.shape)} if opt.dynamic else None)
assert check, 'assert check failed'
onnx.save(model_onnx, f)
except Exception as e:
print(f'{prefix} simplifier failure: {e}')
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'{prefix} export failure: {e}')
# CoreML export ----------------------------------------------------------------------------------------------------
if 'coreml' in opt.include:
prefix = colorstr('CoreML:')
try:
import coremltools as ct
print(f'{prefix} starting export with coremltools {ct.__version__}...')
assert opt.train, 'CoreML exports should be placed in model.train() mode with `python export.py --train`'
model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
f = opt.weights.replace('.pt', '.mlmodel') # filename
model.save(f)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'{prefix} export failure: {e}')
# Finish
print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.')
# Default YOLOv5 anchors for COCO data
# P5 -------------------------------------------------------------------------------------------------------------------
# P5-640:
anchors_p5_640:
- [ 10,13, 16,30, 33,23 ] # P3/8
- [ 30,61, 62,45, 59,119 ] # P4/16
- [ 116,90, 156,198, 373,326 ] # P5/32
# P6 -------------------------------------------------------------------------------------------------------------------
# P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387
anchors_p6_640:
- [ 9,11, 21,19, 17,41 ] # P3/8
- [ 43,32, 39,70, 86,64 ] # P4/16
- [ 65,131, 134,130, 120,265 ] # P5/32
- [ 282,180, 247,354, 512,387 ] # P6/64
# P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792
anchors_p6_1280:
- [ 19,27, 44,40, 38,94 ] # P3/8
- [ 96,68, 86,152, 180,137 ] # P4/16
- [ 140,301, 303,264, 238,542 ] # P5/32
- [ 436,615, 739,380, 925,792 ] # P6/64
# P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187
anchors_p6_1920:
- [ 28,41, 67,59, 57,141 ] # P3/8
- [ 144,103, 129,227, 270,205 ] # P4/16
- [ 209,452, 455,396, 358,812 ] # P5/32
- [ 653,922, 1109,570, 1387,1187 ] # P6/64
# P7 -------------------------------------------------------------------------------------------------------------------
# P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372
anchors_p7_640:
- [ 11,11, 13,30, 29,20 ] # P3/8
- [ 30,46, 61,38, 39,92 ] # P4/16
- [ 78,80, 146,66, 79,163 ] # P5/32
- [ 149,150, 321,143, 157,303 ] # P6/64
- [ 257,402, 359,290, 524,372 ] # P7/128
# P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818
anchors_p7_1280:
- [ 19,22, 54,36, 32,77 ] # P3/8
- [ 70,83, 138,71, 75,173 ] # P4/16
- [ 165,159, 148,334, 375,151 ] # P5/32
- [ 334,317, 251,626, 499,474 ] # P6/64
- [ 750,326, 534,814, 1079,818 ] # P7/128
# P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227
anchors_p7_1920:
- [ 29,34, 81,55, 47,115 ] # P3/8
- [ 105,124, 207,107, 113,259 ] # P4/16
- [ 247,238, 222,500, 563,227 ] # P5/32
- [ 501,476, 376,939, 749,711 ] # P6/64
- [ 1126,489, 801,1222, 1618,1227 ] # P7/128
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# darknet53 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [32, 3, 1]], # 0
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
[-1, 1, Bottleneck, [64]],
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
[-1, 2, Bottleneck, [128]],
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
[-1, 8, Bottleneck, [256]],
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
[-1, 8, Bottleneck, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
[-1, 4, Bottleneck, [1024]], # 10
]
# YOLOv3-SPP head
head:
[[-1, 1, Bottleneck, [1024, False]],
[-1, 1, SPP, [512, [5, 9, 13]]],
[-1, 1, Conv, [1024, 3, 1]],
[-1, 1, Conv, [512, 1, 1]],
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 8], 1, Concat, [1]], # cat backbone P4
[-1, 1, Bottleneck, [512, False]],
[-1, 1, Bottleneck, [512, False]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P3
[-1, 1, Bottleneck, [256, False]],
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [10,14, 23,27, 37,58] # P4/16
- [81,82, 135,169, 344,319] # P5/32
# YOLOv3-tiny backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [16, 3, 1]], # 0
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2
[-1, 1, Conv, [32, 3, 1]],
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32
[-1, 1, Conv, [512, 3, 1]],
[-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11
[-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12
]
# YOLOv3-tiny head
head:
[[-1, 1, Conv, [1024, 3, 1]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large)
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 8], 1, Concat, [1]], # cat backbone P4
[-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium)
[[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# darknet53 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [32, 3, 1]], # 0
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
[-1, 1, Bottleneck, [64]],
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
[-1, 2, Bottleneck, [128]],
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
[-1, 8, Bottleneck, [256]],
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
[-1, 8, Bottleneck, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
[-1, 4, Bottleneck, [1024]], # 10
]
# YOLOv3 head
head:
[[-1, 1, Bottleneck, [1024, False]],
[-1, 1, Conv, [512, [1, 1]]],
[-1, 1, Conv, [1024, 3, 1]],
[-1, 1, Conv, [512, 1, 1]],
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 8], 1, Concat, [1]], # cat backbone P4
[-1, 1, Bottleneck, [512, False]],
[-1, 1, Bottleneck, [512, False]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P3
[-1, 1, Bottleneck, [256, False]],
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, Bottleneck, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 6, BottleneckCSP, [1024]], # 9
]
# YOLOv5 FPN head
head:
[[-1, 3, BottleneckCSP, [1024, False]], # 10 (P5/32-large)
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 1, Conv, [512, 1, 1]],
[-1, 3, BottleneckCSP, [512, False]], # 14 (P4/16-medium)
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 1, Conv, [256, 1, 1]],
[-1, 3, BottleneckCSP, [256, False]], # 18 (P3/8-small)
[[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors: 3
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
[ -1, 3, C3, [ 128 ] ],
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
[ -1, 9, C3, [ 256 ] ],
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
[ -1, 9, C3, [ 512 ] ],
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 7-P5/32
[ -1, 1, SPP, [ 1024, [ 5, 9, 13 ] ] ],
[ -1, 3, C3, [ 1024, False ] ], # 9
]
# YOLOv5 head
head:
[ [ -1, 1, Conv, [ 512, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
[ -1, 3, C3, [ 512, False ] ], # 13
[ -1, 1, Conv, [ 256, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
[ -1, 3, C3, [ 256, False ] ], # 17 (P3/8-small)
[ -1, 1, Conv, [ 128, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 2 ], 1, Concat, [ 1 ] ], # cat backbone P2
[ -1, 1, C3, [ 128, False ] ], # 21 (P2/4-xsmall)
[ -1, 1, Conv, [ 128, 3, 2 ] ],
[ [ -1, 18 ], 1, Concat, [ 1 ] ], # cat head P3
[ -1, 3, C3, [ 256, False ] ], # 24 (P3/8-small)
[ -1, 1, Conv, [ 256, 3, 2 ] ],
[ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P4
[ -1, 3, C3, [ 512, False ] ], # 27 (P4/16-medium)
[ -1, 1, Conv, [ 512, 3, 2 ] ],
[ [ -1, 10 ], 1, Concat, [ 1 ] ], # cat head P5
[ -1, 3, C3, [ 1024, False ] ], # 30 (P5/32-large)
[ [ 24, 27, 30 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors: 3
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
[ -1, 3, C3, [ 128 ] ],
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
[ -1, 9, C3, [ 256 ] ],
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
[ -1, 9, C3, [ 512 ] ],
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
[ -1, 3, C3, [ 768 ] ],
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
[ -1, 3, C3, [ 1024, False ] ], # 11
]
# YOLOv5 head
head:
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
[ -1, 3, C3, [ 768, False ] ], # 15
[ -1, 1, Conv, [ 512, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
[ -1, 3, C3, [ 512, False ] ], # 19
[ -1, 1, Conv, [ 256, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
[ -1, 1, Conv, [ 256, 3, 2 ] ],
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
[ -1, 1, Conv, [ 512, 3, 2 ] ],
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
[ -1, 1, Conv, [ 768, 3, 2 ] ],
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
[ -1, 3, C3, [ 1024, False ] ], # 32 (P5/64-xlarge)
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors: 3
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
[ -1, 3, C3, [ 128 ] ],
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
[ -1, 9, C3, [ 256 ] ],
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
[ -1, 9, C3, [ 512 ] ],
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
[ -1, 3, C3, [ 768 ] ],
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
[ -1, 3, C3, [ 1024 ] ],
[ -1, 1, Conv, [ 1280, 3, 2 ] ], # 11-P7/128
[ -1, 1, SPP, [ 1280, [ 3, 5 ] ] ],
[ -1, 3, C3, [ 1280, False ] ], # 13
]
# YOLOv5 head
head:
[ [ -1, 1, Conv, [ 1024, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 10 ], 1, Concat, [ 1 ] ], # cat backbone P6
[ -1, 3, C3, [ 1024, False ] ], # 17
[ -1, 1, Conv, [ 768, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
[ -1, 3, C3, [ 768, False ] ], # 21
[ -1, 1, Conv, [ 512, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
[ -1, 3, C3, [ 512, False ] ], # 25
[ -1, 1, Conv, [ 256, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
[ -1, 3, C3, [ 256, False ] ], # 29 (P3/8-small)
[ -1, 1, Conv, [ 256, 3, 2 ] ],
[ [ -1, 26 ], 1, Concat, [ 1 ] ], # cat head P4
[ -1, 3, C3, [ 512, False ] ], # 32 (P4/16-medium)
[ -1, 1, Conv, [ 512, 3, 2 ] ],
[ [ -1, 22 ], 1, Concat, [ 1 ] ], # cat head P5
[ -1, 3, C3, [ 768, False ] ], # 35 (P5/32-large)
[ -1, 1, Conv, [ 768, 3, 2 ] ],
[ [ -1, 18 ], 1, Concat, [ 1 ] ], # cat head P6
[ -1, 3, C3, [ 1024, False ] ], # 38 (P6/64-xlarge)
[ -1, 1, Conv, [ 1024, 3, 2 ] ],
[ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P7
[ -1, 3, C3, [ 1280, False ] ], # 41 (P7/128-xxlarge)
[ [ 29, 32, 35, 38, 41 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6, P7)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, BottleneckCSP, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, BottleneckCSP, [1024, False]], # 9
]
# YOLOv5 PANet head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, BottleneckCSP, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, BottleneckCSP, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [ 19,27, 44,40, 38,94 ] # P3/8
- [ 96,68, 86,152, 180,137 ] # P4/16
- [ 140,301, 303,264, 238,542 ] # P5/32
- [ 436,615, 739,380, 925,792 ] # P6/64
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
[ -1, 3, C3, [ 128 ] ],
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
[ -1, 9, C3, [ 256 ] ],
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
[ -1, 9, C3, [ 512 ] ],
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
[ -1, 3, C3, [ 768 ] ],
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
[ -1, 3, C3, [ 1024, False ] ], # 11
]
# YOLOv5 head
head:
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
[ -1, 3, C3, [ 768, False ] ], # 15
[ -1, 1, Conv, [ 512, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
[ -1, 3, C3, [ 512, False ] ], # 19
[ -1, 1, Conv, [ 256, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
[ -1, 1, Conv, [ 256, 3, 2 ] ],
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
[ -1, 1, Conv, [ 512, 3, 2 ] ],
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
[ -1, 1, Conv, [ 768, 3, 2 ] ],
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
[ -1, 3, C3, [ 1024, False ] ], # 32 (P6/64-xlarge)
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
]
# parameters
nc: 80 # number of classes
depth_multiple: 0.67 # model depth multiple
width_multiple: 0.75 # layer channel multiple
# anchors
anchors:
- [ 19,27, 44,40, 38,94 ] # P3/8
- [ 96,68, 86,152, 180,137 ] # P4/16
- [ 140,301, 303,264, 238,542 ] # P5/32
- [ 436,615, 739,380, 925,792 ] # P6/64
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
[ -1, 3, C3, [ 128 ] ],
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
[ -1, 9, C3, [ 256 ] ],
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
[ -1, 9, C3, [ 512 ] ],
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
[ -1, 3, C3, [ 768 ] ],
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
[ -1, 3, C3, [ 1024, False ] ], # 11
]
# YOLOv5 head
head:
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
[ -1, 3, C3, [ 768, False ] ], # 15
[ -1, 1, Conv, [ 512, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
[ -1, 3, C3, [ 512, False ] ], # 19
[ -1, 1, Conv, [ 256, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
[ -1, 1, Conv, [ 256, 3, 2 ] ],
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
[ -1, 1, Conv, [ 512, 3, 2 ] ],
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
[ -1, 1, Conv, [ 768, 3, 2 ] ],
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
[ -1, 3, C3, [ 1024, False ] ], # 32 (P6/64-xlarge)
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
]
# parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, C3TR, [1024, False]], # 9 <-------- C3TR() Transformer module
]
# YOLOv5 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
# anchors
anchors:
- [ 19,27, 44,40, 38,94 ] # P3/8
- [ 96,68, 86,152, 180,137 ] # P4/16
- [ 140,301, 303,264, 238,542 ] # P5/32
- [ 436,615, 739,380, 925,792 ] # P6/64
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
[ -1, 3, C3, [ 128 ] ],
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
[ -1, 9, C3, [ 256 ] ],
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
[ -1, 9, C3, [ 512 ] ],
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
[ -1, 3, C3, [ 768 ] ],
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
[ -1, 3, C3, [ 1024, False ] ], # 11
]
# YOLOv5 head
head:
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
[ -1, 3, C3, [ 768, False ] ], # 15
[ -1, 1, Conv, [ 512, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
[ -1, 3, C3, [ 512, False ] ], # 19
[ -1, 1, Conv, [ 256, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
[ -1, 1, Conv, [ 256, 3, 2 ] ],
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
[ -1, 1, Conv, [ 512, 3, 2 ] ],
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
[ -1, 1, Conv, [ 768, 3, 2 ] ],
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
[ -1, 3, C3, [ 1024, False ] ], # 32 (P6/64-xlarge)
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.33 # model depth multiple
width_multiple: 1.25 # layer channel multiple
# anchors
anchors:
- [ 19,27, 44,40, 38,94 ] # P3/8
- [ 96,68, 86,152, 180,137 ] # P4/16
- [ 140,301, 303,264, 238,542 ] # P5/32
- [ 436,615, 739,380, 925,792 ] # P6/64
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
[ -1, 3, C3, [ 128 ] ],
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
[ -1, 9, C3, [ 256 ] ],
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
[ -1, 9, C3, [ 512 ] ],
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
[ -1, 3, C3, [ 768 ] ],
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
[ -1, 3, C3, [ 1024, False ] ], # 11
]
# YOLOv5 head
head:
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
[ -1, 3, C3, [ 768, False ] ], # 15
[ -1, 1, Conv, [ 512, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
[ -1, 3, C3, [ 512, False ] ], # 19
[ -1, 1, Conv, [ 256, 1, 1 ] ],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
[ -1, 1, Conv, [ 256, 3, 2 ] ],
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
[ -1, 1, Conv, [ 512, 3, 2 ] ],
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
[ -1, 1, Conv, [ 768, 3, 2 ] ],
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
[ -1, 3, C3, [ 1024, False ] ], # 32 (P6/64-xlarge)
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
]
This diff is collapsed. Click to expand it.
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, C3, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 0.67 # model depth multiple
width_multiple: 0.75 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, C3, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# parameters
nc: 1 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, C3, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# parameters
nc: 80 # number of classes
depth_multiple: 1.33 # model depth multiple
width_multiple: 1.25 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, C3, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
# pip install -r requirements.txt
# base ----------------------------------------
matplotlib>=3.2.2
numpy>=1.18.5
opencv-python>=4.1.2
Pillow
PyYAML>=5.3.1
scipy>=1.4.1
torch>=1.7.0
torchvision>=0.8.1
tqdm>=4.41.0
# logging -------------------------------------
tensorboard>=2.4.1
# wandb
# plotting ------------------------------------
seaborn>=0.11.0
pandas
# export --------------------------------------
# coremltools>=4.1
# onnx>=1.9.0
# scikit-learn==0.19.2 # for coreml quantization
# extras --------------------------------------
# Cython # for pycocotools https://github.com/cocodataset/cocoapi/issues/172
pycocotools>=2.0 # COCO mAP
thop # FLOPS computation
This diff is collapsed. Click to expand it.
This diff is collapsed. Click to expand it.
This diff could not be displayed because it is too large.
File mode changed
# Activation functions
import torch
import torch.nn as nn
import torch.nn.functional as F
# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
class SiLU(nn.Module): # export-friendly version of nn.SiLU()
@staticmethod
def forward(x):
return x * torch.sigmoid(x)
class Hardswish(nn.Module): # export-friendly version of nn.Hardswish()
@staticmethod
def forward(x):
# return x * F.hardsigmoid(x) # for torchscript and CoreML
return x * F.hardtanh(x + 3, 0., 6.) / 6. # for torchscript, CoreML and ONNX
# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
class Mish(nn.Module):
@staticmethod
def forward(x):
return x * F.softplus(x).tanh()
class MemoryEfficientMish(nn.Module):
class F(torch.autograd.Function):
@staticmethod
def forward(ctx, x):
ctx.save_for_backward(x)
return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x)))
@staticmethod
def backward(ctx, grad_output):
x = ctx.saved_tensors[0]
sx = torch.sigmoid(x)
fx = F.softplus(x).tanh()
return grad_output * (fx + x * sx * (1 - fx * fx))
def forward(self, x):
return self.F.apply(x)
# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
class FReLU(nn.Module):
def __init__(self, c1, k=3): # ch_in, kernel
super().__init__()
self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
self.bn = nn.BatchNorm2d(c1)
def forward(self, x):
return torch.max(x, self.bn(self.conv(x)))
# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
class AconC(nn.Module):
r""" ACON activation (activate or not).
AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
"""
def __init__(self, c1):
super().__init__()
self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))
def forward(self, x):
dpx = (self.p1 - self.p2) * x
return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x
class MetaAconC(nn.Module):
r""" ACON activation (activate or not).
MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
"""
def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r
super().__init__()
c2 = max(r, c1 // r)
self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
# self.bn1 = nn.BatchNorm2d(c2)
# self.bn2 = nn.BatchNorm2d(c1)
def forward(self, x):
y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
# batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
# beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable
beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed
dpx = (self.p1 - self.p2) * x
return dpx * torch.sigmoid(beta * dpx) + self.p2 * x
# Auto-anchor utils
import numpy as np
import torch
import yaml
from tqdm import tqdm
from utils.general import colorstr
def check_anchor_order(m):
# Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
a = m.anchor_grid.prod(-1).view(-1) # anchor area
da = a[-1] - a[0] # delta a
ds = m.stride[-1] - m.stride[0] # delta s
if da.sign() != ds.sign(): # same order
print('Reversing anchor order')
m.anchors[:] = m.anchors.flip(0)
m.anchor_grid[:] = m.anchor_grid.flip(0)
def check_anchors(dataset, model, thr=4.0, imgsz=640):
# Check anchor fit to data, recompute if necessary
prefix = colorstr('autoanchor: ')
print(f'\n{prefix}Analyzing anchors... ', end='')
m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect()
shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale
wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh
def metric(k): # compute metric
r = wh[:, None] / k[None]
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
best = x.max(1)[0] # best_x
aat = (x > 1. / thr).float().sum(1).mean() # anchors above threshold
bpr = (best > 1. / thr).float().mean() # best possible recall
return bpr, aat
anchors = m.anchor_grid.clone().cpu().view(-1, 2) # current anchors
bpr, aat = metric(anchors)
print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='')
if bpr < 0.98: # threshold to recompute
print('. Attempting to improve anchors, please wait...')
na = m.anchor_grid.numel() // 2 # number of anchors
try:
anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
except Exception as e:
print(f'{prefix}ERROR: {e}')
new_bpr = metric(anchors)[0]
if new_bpr > bpr: # replace anchors
anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
m.anchor_grid[:] = anchors.clone().view_as(m.anchor_grid) # for inference
m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss
check_anchor_order(m)
print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
else:
print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.')
print('') # newline
def kmean_anchors(path='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
""" Creates kmeans-evolved anchors from training dataset
Arguments:
path: path to dataset *.yaml, or a loaded dataset
n: number of anchors
img_size: image size used for training
thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
gen: generations to evolve anchors using genetic algorithm
verbose: print all results
Return:
k: kmeans evolved anchors
Usage:
from utils.autoanchor import *; _ = kmean_anchors()
"""
from scipy.cluster.vq import kmeans
thr = 1. / thr
prefix = colorstr('autoanchor: ')
def metric(k, wh): # compute metrics
r = wh[:, None] / k[None]
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
# x = wh_iou(wh, torch.tensor(k)) # iou metric
return x, x.max(1)[0] # x, best_x
def anchor_fitness(k): # mutation fitness
_, best = metric(torch.tensor(k, dtype=torch.float32), wh)
return (best * (best > thr).float()).mean() # fitness
def print_results(k):
k = k[np.argsort(k.prod(1))] # sort small to large
x, best = metric(k, wh0)
bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr
print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
f'past_thr={x[x > thr].mean():.3f}-mean: ', end='')
for i, x in enumerate(k):
print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg
return k
if isinstance(path, str): # *.yaml file
with open(path) as f:
data_dict = yaml.safe_load(f) # model dict
from utils.datasets import LoadImagesAndLabels
dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
else:
dataset = path # dataset
# Get label wh
shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh
# Filter
i = (wh0 < 3.0).any(1).sum()
if i:
print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels
# wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1
# Kmeans calculation
print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
s = wh.std(0) # sigmas for whitening
k, dist = kmeans(wh / s, n, iter=30) # points, mean distance
assert len(k) == n, print(f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}')
k *= s
wh = torch.tensor(wh, dtype=torch.float32) # filtered
wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered
k = print_results(k)
# Plot
# k, d = [None] * 20, [None] * 20
# for i in tqdm(range(1, 21)):
# k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance
# fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
# ax = ax.ravel()
# ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
# fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh
# ax[0].hist(wh[wh[:, 0]<100, 0],400)
# ax[1].hist(wh[wh[:, 1]<100, 1],400)
# fig.savefig('wh.png', dpi=200)
# Evolve
npr = np.random
f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma
pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:') # progress bar
for _ in pbar:
v = np.ones(sh)
while (v == 1).all(): # mutate until a change occurs (prevent duplicates)
v = ((npr.random(sh) < mp) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
kg = (k.copy() * v).clip(min=2.0)
fg = anchor_fitness(kg)
if fg > f:
f, k = fg, kg.copy()
pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
if verbose:
print_results(k)
return print_results(k)
# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
# This script will run on every instance restart, not only on first start
# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
Content-Type: multipart/mixed; boundary="//"
MIME-Version: 1.0
--//
Content-Type: text/cloud-config; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment; filename="cloud-config.txt"
#cloud-config
cloud_final_modules:
- [scripts-user, always]
--//
Content-Type: text/x-shellscript; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment; filename="userdata.txt"
#!/bin/bash
# --- paste contents of userdata.sh here ---
--//
# Resume all interrupted trainings in yolov5/ dir including DDP trainings
# Usage: $ python utils/aws/resume.py
import os
import sys
from pathlib import Path
import torch
import yaml
sys.path.append('./') # to run '$ python *.py' files in subdirectories
port = 0 # --master_port
path = Path('').resolve()
for last in path.rglob('*/**/last.pt'):
ckpt = torch.load(last)
if ckpt['optimizer'] is None:
continue
# Load opt.yaml
with open(last.parent.parent / 'opt.yaml') as f:
opt = yaml.safe_load(f)
# Get device count
d = opt['device'].split(',') # devices
nd = len(d) # number of devices
ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel
if ddp: # multi-GPU
port += 1
cmd = f'python -m torch.distributed.launch --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
else: # single-GPU
cmd = f'python train.py --resume {last}'
cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread
print(cmd)
os.system(cmd)
#!/bin/bash
# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
# This script will run only once on first instance start (for a re-start script see mime.sh)
# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
# Use >300 GB SSD
cd home/ubuntu
if [ ! -d yolov5 ]; then
echo "Running first-time script." # install dependencies, download COCO, pull Docker
git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5
cd yolov5
bash data/scripts/get_coco.sh && echo "Data done." &
sudo docker pull ultralytics/yolov5:latest && echo "Docker done." &
python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
wait && echo "All tasks done." # finish background tasks
else
echo "Running re-start script." # resume interrupted runs
i=0
list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
while IFS= read -r id; do
((i++))
echo "restarting container $i: $id"
sudo docker start $id
# sudo docker exec -it $id python train.py --resume # single-GPU
sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
done <<<"$list"
fi
This diff is collapsed. Click to expand it.
# Flask REST API
[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/).
## Requirements
[Flask](https://palletsprojects.com/p/flask/) is required. Install with:
```shell
$ pip install Flask
```
## Run
After Flask installation run:
```shell
$ python3 restapi.py --port 5000
```
Then use [curl](https://curl.se/) to perform a request:
```shell
$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s'`
```
The model inference results are returned as a JSON response:
```json
[
{
"class": 0,
"confidence": 0.8900438547,
"height": 0.9318675399,
"name": "person",
"width": 0.3264600933,
"xcenter": 0.7438579798,
"ycenter": 0.5207948685
},
{
"class": 0,
"confidence": 0.8440024257,
"height": 0.7155083418,
"name": "person",
"width": 0.6546785235,
"xcenter": 0.427829951,
"ycenter": 0.6334488392
},
{
"class": 27,
"confidence": 0.3771208823,
"height": 0.3902671337,
"name": "tie",
"width": 0.0696444362,
"xcenter": 0.3675483763,
"ycenter": 0.7991207838
},
{
"class": 27,
"confidence": 0.3527112305,
"height": 0.1540903747,
"name": "tie",
"width": 0.0336618312,
"xcenter": 0.7814827561,
"ycenter": 0.5065554976
}
]
```
An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given in `example_request.py`
"""Perform test request"""
import pprint
import requests
DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s"
TEST_IMAGE = "zidane.jpg"
image_data = open(TEST_IMAGE, "rb").read()
response = requests.post(DETECTION_URL, files={"image": image_data}).json()
pprint.pprint(response)
"""
Run a rest API exposing the yolov5s object detection model
"""
import argparse
import io
import torch
from PIL import Image
from flask import Flask, request
app = Flask(__name__)
DETECTION_URL = "/v1/object-detection/yolov5s"
@app.route(DETECTION_URL, methods=["POST"])
def predict():
if not request.method == "POST":
return
if request.files.get("image"):
image_file = request.files["image"]
image_bytes = image_file.read()
img = Image.open(io.BytesIO(image_bytes))
results = model(img, size=640) # reduce size=320 for faster inference
return results.pandas().xyxy[0].to_json(orient="records")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model")
parser.add_argument("--port", default=5000, type=int, help="port number")
args = parser.parse_args()
model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True) # force_reload to recache
app.run(host="0.0.0.0", port=args.port) # debug=True causes Restarting with stat
This diff is collapsed. Click to expand it.
FROM gcr.io/google-appengine/python
# Create a virtualenv for dependencies. This isolates these packages from
# system-level packages.
# Use -p python3 or -p python3.7 to select python version. Default is version 2.
RUN virtualenv /env -p python3
# Setting these environment variables are the same as running
# source /env/bin/activate.
ENV VIRTUAL_ENV /env
ENV PATH /env/bin:$PATH
RUN apt-get update && apt-get install -y python-opencv
# Copy the application's requirements.txt and run pip to install all
# dependencies into the virtualenv.
ADD requirements.txt /app/requirements.txt
RUN pip install -r /app/requirements.txt
# Add the application source code.
ADD . /app
# Run a WSGI server to serve the application. gunicorn must be declared as
# a dependency in requirements.txt.
CMD gunicorn -b :$PORT main:app
# add these requirements in your app on top of the existing ones
pip==18.1
Flask==1.0.2
gunicorn==19.9.0
runtime: custom
env: flex
service: yolov5app
liveness_check:
initial_delay_sec: 600
manual_scaling:
instances: 1
resources:
cpu: 1
memory_gb: 4
disk_size_gb: 20
\ No newline at end of file
# Google utils: https://cloud.google.com/storage/docs/reference/libraries
import os
import platform
import subprocess
import time
from pathlib import Path
import requests
import torch
def gsutil_getsize(url=''):
# gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du
s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8')
return eval(s.split(' ')[0]) if len(s) else 0 # bytes
def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''):
# Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes
file = Path(file)
try: # GitHub
print(f'Downloading {url} to {file}...')
torch.hub.download_url_to_file(url, str(file))
assert file.exists() and file.stat().st_size > min_bytes # check
except Exception as e: # GCP
file.unlink(missing_ok=True) # remove partial downloads
print(f'Download error: {e}\nRe-attempting {url2 or url} to {file}...')
os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail
finally:
if not file.exists() or file.stat().st_size < min_bytes: # check
file.unlink(missing_ok=True) # remove partial downloads
print(f'ERROR: Download failure: {error_msg or url}')
print('')
def attempt_download(file, repo='ultralytics/yolov5'):
# Attempt file download if does not exist
file = Path(str(file).strip().replace("'", ''))
if not file.exists():
# URL specified
name = file.name
if str(file).startswith(('http:/', 'https:/')): # download
url = str(file).replace(':/', '://') # Pathlib turns :// -> :/
safe_download(file=name, url=url, min_bytes=1E5)
return name
# GitHub assets
file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required)
try:
response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api
assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...]
tag = response['tag_name'] # i.e. 'v1.0'
except: # fallback plan
assets = ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt',
'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
try:
tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
except:
tag = 'v5.0' # current release
if name in assets:
safe_download(file,
url=f'https://github.com/{repo}/releases/download/{tag}/{name}',
# url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}', # backup url (optional)
min_bytes=1E5,
error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/')
return str(file)
def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
# Downloads a file from Google Drive. from yolov5.utils.google_utils import *; gdrive_download()
t = time.time()
file = Path(file)
cookie = Path('cookie') # gdrive cookie
print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
file.unlink(missing_ok=True) # remove existing file
cookie.unlink(missing_ok=True) # remove existing cookie
# Attempt file download
out = "NUL" if platform.system() == "Windows" else "/dev/null"
os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
if os.path.exists('cookie'): # large file
s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
else: # small file
s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
r = os.system(s) # execute, capture return
cookie.unlink(missing_ok=True) # remove existing cookie
# Error check
if r != 0:
file.unlink(missing_ok=True) # remove partial
print('Download error ') # raise Exception('Download error')
return r
# Unzip if archive
if file.suffix == '.zip':
print('unzipping... ', end='')
os.system(f'unzip -q {file}') # unzip
file.unlink() # remove zip to free space
print(f'Done ({time.time() - t:.1f}s)')
return r
def get_token(cookie="./cookie"):
with open(cookie) as f:
for line in f:
if "download" in line:
return line.split()[-1]
return ""
# def upload_blob(bucket_name, source_file_name, destination_blob_name):
# # Uploads a file to a bucket
# # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
#
# storage_client = storage.Client()
# bucket = storage_client.get_bucket(bucket_name)
# blob = bucket.blob(destination_blob_name)
#
# blob.upload_from_filename(source_file_name)
#
# print('File {} uploaded to {}.'.format(
# source_file_name,
# destination_blob_name))
#
#
# def download_blob(bucket_name, source_blob_name, destination_file_name):
# # Uploads a blob from a bucket
# storage_client = storage.Client()
# bucket = storage_client.get_bucket(bucket_name)
# blob = bucket.blob(source_blob_name)
#
# blob.download_to_filename(destination_file_name)
#
# print('Blob {} downloaded to {}.'.format(
# source_blob_name,
# destination_file_name))
# Loss functions
import torch
import torch.nn as nn
from utils.general import bbox_iou
from utils.torch_utils import is_parallel
def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
# return positive, negative label smoothing BCE targets
return 1.0 - 0.5 * eps, 0.5 * eps
class BCEBlurWithLogitsLoss(nn.Module):
# BCEwithLogitLoss() with reduced missing label effects.
def __init__(self, alpha=0.05):
super(BCEBlurWithLogitsLoss, self).__init__()
self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss()
self.alpha = alpha
def forward(self, pred, true):
loss = self.loss_fcn(pred, true)
pred = torch.sigmoid(pred) # prob from logits
dx = pred - true # reduce only missing label effects
# dx = (pred - true).abs() # reduce missing label and false label effects
alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4))
loss *= alpha_factor
return loss.mean()
class FocalLoss(nn.Module):
# Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
super(FocalLoss, self).__init__()
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
self.gamma = gamma
self.alpha = alpha
self.reduction = loss_fcn.reduction
self.loss_fcn.reduction = 'none' # required to apply FL to each element
def forward(self, pred, true):
loss = self.loss_fcn(pred, true)
# p_t = torch.exp(-loss)
# loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability
# TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
pred_prob = torch.sigmoid(pred) # prob from logits
p_t = true * pred_prob + (1 - true) * (1 - pred_prob)
alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
modulating_factor = (1.0 - p_t) ** self.gamma
loss *= alpha_factor * modulating_factor
if self.reduction == 'mean':
return loss.mean()
elif self.reduction == 'sum':
return loss.sum()
else: # 'none'
return loss
class QFocalLoss(nn.Module):
# Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
super(QFocalLoss, self).__init__()
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
self.gamma = gamma
self.alpha = alpha
self.reduction = loss_fcn.reduction
self.loss_fcn.reduction = 'none' # required to apply FL to each element
def forward(self, pred, true):
loss = self.loss_fcn(pred, true)
pred_prob = torch.sigmoid(pred) # prob from logits
alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
modulating_factor = torch.abs(true - pred_prob) ** self.gamma
loss *= alpha_factor * modulating_factor
if self.reduction == 'mean':
return loss.mean()
elif self.reduction == 'sum':
return loss.sum()
else: # 'none'
return loss
class ComputeLoss:
# Compute losses
def __init__(self, model, autobalance=False):
super(ComputeLoss, self).__init__()
device = next(model.parameters()).device # get model device
h = model.hyp # hyperparameters
# Define criteria
BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))
BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))
# Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets
# Focal loss
g = h['fl_gamma'] # focal loss gamma
if g > 0:
BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
det = model.module.model[-1] if is_parallel(model) else model.model[-1] # Detect() module
self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, .02]) # P3-P7
self.ssi = list(det.stride).index(16) if autobalance else 0 # stride 16 index
self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, model.gr, h, autobalance
for k in 'na', 'nc', 'nl', 'anchors':
setattr(self, k, getattr(det, k))
def __call__(self, p, targets): # predictions, targets, model
device = targets.device
lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets
# Losses
for i, pi in enumerate(p): # layer index, layer predictions
b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
tobj = torch.zeros_like(pi[..., 0], device=device) # target obj
n = b.shape[0] # number of targets
if n:
ps = pi[b, a, gj, gi] # prediction subset corresponding to targets
# Regression
pxy = ps[:, :2].sigmoid() * 2. - 0.5
pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
pbox = torch.cat((pxy, pwh), 1) # predicted box
iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target)
lbox += (1.0 - iou).mean() # iou loss
# Objectness
tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * iou.detach().clamp(0).type(tobj.dtype) # iou ratio
# Classification
if self.nc > 1: # cls loss (only if multiple classes)
t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets
t[range(n), tcls[i]] = self.cp
lcls += self.BCEcls(ps[:, 5:], t) # BCE
# Append targets to text file
# with open('targets.txt', 'a') as file:
# [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]
obji = self.BCEobj(pi[..., 4], tobj)
lobj += obji * self.balance[i] # obj loss
if self.autobalance:
self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()
if self.autobalance:
self.balance = [x / self.balance[self.ssi] for x in self.balance]
lbox *= self.hyp['box']
lobj *= self.hyp['obj']
lcls *= self.hyp['cls']
bs = tobj.shape[0] # batch size
loss = lbox + lobj + lcls
return loss * bs, torch.cat((lbox, lobj, lcls, loss)).detach()
def build_targets(self, p, targets):
# Build targets for compute_loss(), input targets(image,class,x,y,w,h)
na, nt = self.na, targets.shape[0] # number of anchors, targets
tcls, tbox, indices, anch = [], [], [], []
gain = torch.ones(7, device=targets.device) # normalized to gridspace gain
ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices
g = 0.5 # bias
off = torch.tensor([[0, 0],
[1, 0], [0, 1], [-1, 0], [0, -1], # j,k,l,m
# [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm
], device=targets.device).float() * g # offsets
for i in range(self.nl):
anchors = self.anchors[i]
gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain
# Match targets to anchors
t = targets * gain
if nt:
# Matches
r = t[:, :, 4:6] / anchors[:, None] # wh ratio
j = torch.max(r, 1. / r).max(2)[0] < self.hyp['anchor_t'] # compare
# j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
t = t[j] # filter
# Offsets
gxy = t[:, 2:4] # grid xy
gxi = gain[[2, 3]] - gxy # inverse
j, k = ((gxy % 1. < g) & (gxy > 1.)).T
l, m = ((gxi % 1. < g) & (gxi > 1.)).T
j = torch.stack((torch.ones_like(j), j, k, l, m))
t = t.repeat((5, 1, 1))[j]
offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
else:
t = targets[0]
offsets = 0
# Define
b, c = t[:, :2].long().T # image, class
gxy = t[:, 2:4] # grid xy
gwh = t[:, 4:6] # grid wh
gij = (gxy - offsets).long()
gi, gj = gij.T # grid xy indices
# Append
a = t[:, 6].long() # anchor indices
indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices
tbox.append(torch.cat((gxy - gij, gwh), 1)) # box
anch.append(anchors[a]) # anchors
tcls.append(c) # class
return tcls, tbox, indices, anch
# Model validation metrics
from pathlib import Path
import matplotlib.pyplot as plt
import numpy as np
import torch
from . import general
def fitness(x):
# Model fitness as a weighted combination of metrics
w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
return (x[:, :4] * w).sum(1)
def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=()):
""" Compute the average precision, given the recall and precision curves.
Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
# Arguments
tp: True positives (nparray, nx1 or nx10).
conf: Objectness value from 0-1 (nparray).
pred_cls: Predicted object classes (nparray).
target_cls: True object classes (nparray).
plot: Plot precision-recall curve at mAP@0.5
save_dir: Plot save directory
# Returns
The average precision as computed in py-faster-rcnn.
"""
# Sort by objectness
i = np.argsort(-conf)
tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
# Find unique classes
unique_classes = np.unique(target_cls)
nc = unique_classes.shape[0] # number of classes, number of detections
# Create Precision-Recall curve and compute AP for each class
px, py = np.linspace(0, 1, 1000), [] # for plotting
ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000))
for ci, c in enumerate(unique_classes):
i = pred_cls == c
n_l = (target_cls == c).sum() # number of labels
n_p = i.sum() # number of predictions
if n_p == 0 or n_l == 0:
continue
else:
# Accumulate FPs and TPs
fpc = (1 - tp[i]).cumsum(0)
tpc = tp[i].cumsum(0)
# Recall
recall = tpc / (n_l + 1e-16) # recall curve
r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases
# Precision
precision = tpc / (tpc + fpc) # precision curve
p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score
# AP from recall-precision curve
for j in range(tp.shape[1]):
ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
if plot and j == 0:
py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5
# Compute F1 (harmonic mean of precision and recall)
f1 = 2 * p * r / (p + r + 1e-16)
if plot:
plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision')
plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')
i = f1.mean(0).argmax() # max F1 index
return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')
def compute_ap(recall, precision):
""" Compute the average precision, given the recall and precision curves
# Arguments
recall: The recall curve (list)
precision: The precision curve (list)
# Returns
Average precision, precision curve, recall curve
"""
# Append sentinel values to beginning and end
mrec = np.concatenate(([0.], recall, [recall[-1] + 0.01]))
mpre = np.concatenate(([1.], precision, [0.]))
# Compute the precision envelope
mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))
# Integrate area under curve
method = 'interp' # methods: 'continuous', 'interp'
if method == 'interp':
x = np.linspace(0, 1, 101) # 101-point interp (COCO)
ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate
else: # 'continuous'
i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes
ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve
return ap, mpre, mrec
class ConfusionMatrix:
# Updated version of https://github.com/kaanakan/object_detection_confusion_matrix
def __init__(self, nc, conf=0.25, iou_thres=0.45):
self.matrix = np.zeros((nc + 1, nc + 1))
self.nc = nc # number of classes
self.conf = conf
self.iou_thres = iou_thres
def process_batch(self, detections, labels):
"""
Return intersection-over-union (Jaccard index) of boxes.
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
Arguments:
detections (Array[N, 6]), x1, y1, x2, y2, conf, class
labels (Array[M, 5]), class, x1, y1, x2, y2
Returns:
None, updates confusion matrix accordingly
"""
detections = detections[detections[:, 4] > self.conf]
gt_classes = labels[:, 0].int()
detection_classes = detections[:, 5].int()
iou = general.box_iou(labels[:, 1:], detections[:, :4])
x = torch.where(iou > self.iou_thres)
if x[0].shape[0]:
matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()
if x[0].shape[0] > 1:
matches = matches[matches[:, 2].argsort()[::-1]]
matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
matches = matches[matches[:, 2].argsort()[::-1]]
matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
else:
matches = np.zeros((0, 3))
n = matches.shape[0] > 0
m0, m1, _ = matches.transpose().astype(np.int16)
for i, gc in enumerate(gt_classes):
j = m0 == i
if n and sum(j) == 1:
self.matrix[detection_classes[m1[j]], gc] += 1 # correct
else:
self.matrix[self.nc, gc] += 1 # background FP
if n:
for i, dc in enumerate(detection_classes):
if not any(m1 == i):
self.matrix[dc, self.nc] += 1 # background FN
def matrix(self):
return self.matrix
def plot(self, save_dir='', names=()):
try:
import seaborn as sn
array = self.matrix / (self.matrix.sum(0).reshape(1, self.nc + 1) + 1E-6) # normalize
array[array < 0.005] = np.nan # don't annotate (would appear as 0.00)
fig = plt.figure(figsize=(12, 9), tight_layout=True)
sn.set(font_scale=1.0 if self.nc < 50 else 0.8) # for label size
labels = (0 < len(names) < 99) and len(names) == self.nc # apply names to ticklabels
sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
xticklabels=names + ['background FP'] if labels else "auto",
yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1))
fig.axes[0].set_xlabel('True')
fig.axes[0].set_ylabel('Predicted')
fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250)
except Exception as e:
pass
def print(self):
for i in range(self.nc + 1):
print(' '.join(map(str, self.matrix[i])))
# Plots ----------------------------------------------------------------------------------------------------------------
def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
# Precision-recall curve
fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
py = np.stack(py, axis=1)
if 0 < len(names) < 21: # display per-class legend if < 21 classes
for i, y in enumerate(py.T):
ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}') # plot(recall, precision)
else:
ax.plot(px, py, linewidth=1, color='grey') # plot(recall, precision)
ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean())
ax.set_xlabel('Recall')
ax.set_ylabel('Precision')
ax.set_xlim(0, 1)
ax.set_ylim(0, 1)
plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
fig.savefig(Path(save_dir), dpi=250)
def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'):
# Metric-confidence curve
fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
if 0 < len(names) < 21: # display per-class legend if < 21 classes
for i, y in enumerate(py):
ax.plot(px, y, linewidth=1, label=f'{names[i]}') # plot(confidence, metric)
else:
ax.plot(px, py.T, linewidth=1, color='grey') # plot(confidence, metric)
y = py.mean(0)
ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}')
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
ax.set_xlim(0, 1)
ax.set_ylim(0, 1)
plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
fig.savefig(Path(save_dir), dpi=250)
This diff is collapsed. Click to expand it.
This diff is collapsed. Click to expand it.
import argparse
import yaml
from wandb_utils import WandbLogger
WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
def create_dataset_artifact(opt):
with open(opt.data) as f:
data = yaml.safe_load(f) # data dict
logger = WandbLogger(opt, '', None, data, job_type='Dataset Creation')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path')
parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset')
parser.add_argument('--project', type=str, default='YOLOv5', help='name of W&B Project')
opt = parser.parse_args()
opt.resume = False # Explicitly disallow resume check for dataset upload job
create_dataset_artifact(opt)
This diff is collapsed. Click to expand it.
#!/bin/bash
# Download latest models from https://github.com/ultralytics/yolov5/releases
# Usage:
# $ bash weights/download_weights.sh
python - <<EOF
from utils.google_utils import attempt_download
for x in ['s', 'm', 'l', 'x']:
attempt_download(f'yolov5{x}.pt')
EOF