xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.34 security updates and fixes (#924)

Browse Source 
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Fabian Greavu <fabiangreavu@gmail.com>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
2023-02-11 01:26:44 +04:00
committed by GitHub
parent 254adfa652
commit d32b339373
31 changed files with 134 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docker/Dockerfile
View File

@ -16,6 +16,10 @@ RUN TZ=Etc/UTC apt install -y tzdata
RUN apt install --no-install-recommends -y gcc git zip curl htop libgl1-mesa-glx libglib2.0-0 libpython3-dev gnupg
# RUN alias python=python3
# Security updates
# https://security.snyk.io/vuln/SNYK-UBUNTU1804-OPENSSL-3314796
RUN apt upgrade --no-install-recommends -y openssl
# Create working directory
RUN mkdir -p /usr/src/ultralytics
WORKDIR /usr/src/ultralytics

1
docs/cfg.md
View File

@ -75,6 +75,7 @@ task.
| batch | 16 | number of images per batch (-1 for AutoBatch) |
| imgsz | 640 | size of input images as integer or w,h |
| save | True | save train checkpoints and predict results |
| save_period | -1 | Save checkpoint every x epochs (disabled if < 1) |
| cache | False | True/ram, disk or False. Use cache for data loading |
| device | null | device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu |
| workers | 8 | number of worker threads for data loading (per RANK if DDP) |

44
docs/reference/ops.md
View File

@ -2,7 +2,7 @@ This module contains optimized deep learning related operations used in the Ultr
## Non-max suppression
:::ultralytics.ops.non_max_suppression
:::ultralytics.yolo.utils.ops.non_max_suppression
handler: python
options:
show_source: false
@ -11,7 +11,7 @@ show_root_toc_entry: false
## Scale boxes
:::ultralytics.ops.scale_boxes
:::ultralytics.yolo.utils.ops.scale_boxes
handler: python
options:
show_source: false
@ -20,7 +20,7 @@ show_root_toc_entry: false
## Scale image
:::ultralytics.ops.scale_image
:::ultralytics.yolo.utils.ops.scale_image
handler: python
options:
show_source: false
@ -29,7 +29,7 @@ show_root_toc_entry: false
## clip boxes
:::ultralytics.ops.clip_boxes
:::ultralytics.yolo.utils.ops.clip_boxes
handler: python
options:
show_source: false
@ -40,7 +40,7 @@ show_root_toc_entry: false
## xyxy2xywh
:::ultralytics.ops.xyxy2xywh
:::ultralytics.yolo.utils.ops.xyxy2xywh
handler: python
options:
show_source: false
@ -49,7 +49,7 @@ show_root_toc_entry: false
## xywh2xyxy
:::ultralytics.ops.xywh2xyxy
:::ultralytics.yolo.utils.ops.xywh2xyxy
handler: python
options:
show_source: false
@ -58,7 +58,7 @@ show_root_toc_entry: false
## xywhn2xyxy
:::ultralytics.ops.xywhn2xyxy
:::ultralytics.yolo.utils.ops.xywhn2xyxy
handler: python
options:
show_source: false
@ -67,7 +67,7 @@ show_root_toc_entry: false
## xyxy2xywhn
:::ultralytics.ops.xyxy2xywhn
:::ultralytics.yolo.utils.ops.xyxy2xywhn
handler: python
options:
show_source: false
@ -76,7 +76,7 @@ show_root_toc_entry: false
## xyn2xy
:::ultralytics.ops.xyn2xy
:::ultralytics.yolo.utils.ops.xyn2xy
handler: python
options:
show_source: false
@ -85,7 +85,7 @@ show_root_toc_entry: false
## xywh2ltwh
:::ultralytics.ops.xywh2ltwh
:::ultralytics.yolo.utils.ops.xywh2ltwh
handler: python
options:
show_source: false
@ -94,7 +94,7 @@ show_root_toc_entry: false
## xyxy2ltwh
:::ultralytics.ops.xyxy2ltwh
:::ultralytics.yolo.utils.ops.xyxy2ltwh
handler: python
options:
show_source: false
@ -103,7 +103,7 @@ show_root_toc_entry: false
## ltwh2xywh
:::ultralytics.ops.ltwh2xywh
:::ultralytics.yolo.utils.ops.ltwh2xywh
handler: python
options:
show_source: false
@ -112,7 +112,7 @@ show_root_toc_entry: false
## ltwh2xyxy
:::ultralytics.ops.ltwh2xyxy
:::ultralytics.yolo.utils.ops.ltwh2xyxy
handler: python
options:
show_source: false
@ -121,7 +121,7 @@ show_root_toc_entry: false
## segment2box
:::ultralytics.ops.segment2box
:::ultralytics.yolo.utils.ops.segment2box
handler: python
options:
show_source: false
@ -132,7 +132,7 @@ show_root_toc_entry: false
## resample_segments
:::ultralytics.ops.resample_segments
:::ultralytics.yolo.utils.ops.resample_segments
handler: python
options:
show_source: false
@ -141,7 +141,7 @@ show_root_toc_entry: false
## crop_mask
:::ultralytics.ops.crop_mask
:::ultralytics.yolo.utils.ops.crop_mask
handler: python
options:
show_source: false
@ -150,7 +150,7 @@ show_root_toc_entry: false
## process_mask_upsample
:::ultralytics.ops.process_mask_upsample
:::ultralytics.yolo.utils.ops.process_mask_upsample
handler: python
options:
show_source: false
@ -159,7 +159,7 @@ show_root_toc_entry: false
## process_mask
:::ultralytics.ops.process_mask
:::ultralytics.yolo.utils.ops.process_mask
handler: python
options:
show_source: false
@ -168,7 +168,7 @@ show_root_toc_entry: false
## process_mask_native
:::ultralytics.ops.process_mask_native
:::ultralytics.yolo.utils.ops.process_mask_native
handler: python
options:
show_source: false
@ -177,7 +177,7 @@ show_root_toc_entry: false
## scale_segments
:::ultralytics.ops.scale_segments
:::ultralytics.yolo.utils.ops.scale_segments
handler: python
options:
show_source: false
@ -186,7 +186,7 @@ show_root_toc_entry: false
## masks2segments
:::ultralytics.ops.masks2segments
:::ultralytics.yolo.utils.ops.masks2segments
handler: python
options:
show_source: false
@ -195,7 +195,7 @@ show_root_toc_entry: false
## clip_segments
:::ultralytics.ops.clip_segments
:::ultralytics.yolo.utils.ops.clip_segments
handler: python
options:
show_source: false

5
mkdocs.yml
View File

@ -1,11 +1,12 @@
site_name: Ultralytics YOLOv8 Docs
site_name: YOLOv8 Docs
repo_url: https://github.com/ultralytics/ultralytics
edit_uri: https://github.com/ultralytics/ultralytics/tree/main/docs
repo_name: ultralytics/ultralytics
remote_name: https://github.com/ultralytics/docs
theme:
name: "material"
logo: https://github.com/ultralytics/assets/raw/main/logo/Ultralytics-logomark-white.png
logo: https://github.com/ultralytics/assets/raw/main/logo/Ultralytics_Logotype_Reverse.svg
favicon: https://github.com/ultralytics/assets/raw/main/logo/favicon-yolo.ico
font:
text: Roboto

2
ultralytics/__init__.py
View File

@ -1,6 +1,6 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
__version__ = "8.0.33"
__version__ = "8.0.34"
from ultralytics.yolo.engine.model import YOLO
from ultralytics.yolo.utils.checks import check_yolo as checks

2
ultralytics/hub/__init__.py
View File

@ -7,7 +7,7 @@ from ultralytics.hub.session import HubTrainingSession
from ultralytics.hub.utils import split_key
from ultralytics.yolo.engine.exporter import export_formats
from ultralytics.yolo.engine.model import YOLO
from ultralytics.yolo.utils import LOGGER, emojis, PREFIX
from ultralytics.yolo.utils import LOGGER, PREFIX, emojis
# Define all export formats
EXPORT_FORMATS = list(export_formats()['Argument'][1:]) + ["ultralytics_tflite", "ultralytics_coreml"]

3
ultralytics/hub/session.py
View File

@ -7,9 +7,8 @@ from time import sleep, time
import requests
from ultralytics import __version__
from ultralytics.hub.utils import HUB_API_ROOT, check_dataset_disk_space, smart_request
from ultralytics.yolo.utils import is_colab, threaded, LOGGER, emojis, PREFIX
from ultralytics.yolo.utils import LOGGER, PREFIX, __version__, emojis, is_colab, threaded
from ultralytics.yolo.utils.torch_utils import get_flops, get_num_params
AGENT_NAME = f"python-{__version__}-colab" if is_colab() else f"python-{__version__}-local"

14
ultralytics/hub/utils.py
View File

@ -11,9 +11,10 @@ from random import random
import requests
from ultralytics.yolo.utils import (DEFAULT_CFG_DICT, LOGGER, RANK, SETTINGS, TryExcept, colorstr, emojis,
get_git_origin_url, is_colab, is_docker, is_git_dir, is_github_actions_ci,
is_jupyter, is_kaggle, is_pip_package, is_pytest_running)
from ultralytics.yolo.utils import (DEFAULT_CFG_DICT, ENVIRONMENT, LOGGER, RANK, SETTINGS, TryExcept, __version__,
colorstr, emojis, get_git_origin_url, is_git_dir, is_github_actions_ci,
is_pip_package, is_pytest_running)
from ultralytics.yolo.utils.checks import check_online
PREFIX = colorstr('Ultralytics: ')
HELP_MSG = 'If this issue persists please visit https://github.com/ultralytics/hub/issues for assistance.'
@ -143,9 +144,6 @@ class Traces:
"""
Initialize Traces for error tracking and reporting if tests are not currently running.
"""
from ultralytics import __version__
env = 'Colab' if is_colab() else 'Kaggle' if is_kaggle() else 'Jupyter' if is_jupyter() else \
'Docker' if is_docker() else platform.system()
self.rate_limit = 3.0 # rate limit (seconds)
self.t = 0.0 # rate limit timer (seconds)
self.metadata = {
@ -153,9 +151,10 @@ class Traces:
"install": 'git' if is_git_dir() else 'pip' if is_pip_package() else 'other',
"python": platform.python_version(),
"release": __version__,
"environment": env}
"environment": ENVIRONMENT}
self.enabled = SETTINGS['sync'] and \
RANK in {-1, 0} and \
check_online() and \
not is_pytest_running() and \
not is_github_actions_ci() and \
(is_pip_package() or get_git_origin_url() == "https://github.com/ultralytics/ultralytics.git")
@ -186,6 +185,7 @@ class Traces:
headers=None,
code=3,
retry=0,
timeout=1.0,
verbose=False)

8
ultralytics/models/v8/seg/yolov8l-seg.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [512]] # 23 (P5/32-large)
- [-1, 3, C2f, [512]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/seg/yolov8m-seg.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [768]] # 23 (P5/32-large)
- [-1, 3, C2f, [768]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/seg/yolov8n-seg.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 23 (P5/32-large)
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/seg/yolov8s-seg.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 23 (P5/32-large)
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/seg/yolov8x-seg.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [512]] # 23 (P5/32-large)
- [-1, 3, C2f, [512]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/yolov8l.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [512]] # 23 (P5/32-large)
- [-1, 3, C2f, [512]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/yolov8m.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [768]] # 23 (P5/32-large)
- [-1, 3, C2f, [768]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/yolov8n.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 23 (P5/32-large)
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/yolov8s.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 23 (P5/32-large)
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

8
ultralytics/models/v8/yolov8x.yaml
View File

@ -23,18 +23,18 @@ backbone:
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [512]] # 23 (P5/32-large)
- [-1, 3, C2f, [512]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

33
ultralytics/yolo/cfg/__init__.py
View File

@ -8,9 +8,9 @@ from pathlib import Path
from types import SimpleNamespace
from typing import Dict, List, Union
from ultralytics import __version__
from ultralytics.yolo.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_PATH, LOGGER, PREFIX, ROOT,
USER_CONFIG_DIR, IterableSimpleNamespace, colorstr, emojis, yaml_load, yaml_print)
USER_CONFIG_DIR, IterableSimpleNamespace, __version__, colorstr, emojis, yaml_load,
yaml_print)
from ultralytics.yolo.utils.checks import check_yolo
CLI_HELP_MSG = \
@ -25,13 +25,13 @@ CLI_HELP_MSG = \
See all ARGS at https://docs.ultralytics.com/cfg or with 'yolo cfg'
1. Train a detection model for 10 epochs with an initial learning_rate of 0.01
yolo detect train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01
yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01
2. Predict a YouTube video using a pretrained segmentation model at image size 320:
yolo segment predict model=yolov8n-seg.pt source='https://youtu.be/Zgi9g1ksQHc' imgsz=320
yolo predict model=yolov8n-seg.pt source='https://youtu.be/Zgi9g1ksQHc' imgsz=320
3. Val a pretrained detection model at batch-size 1 and image size 640:
yolo detect val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640
yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640
4. Export a YOLOv8n classification model to ONNX format at image size 224 by 128 (no TASK required)
yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128
@ -56,7 +56,7 @@ CFG_FRACTION_KEYS = {
'mixup', 'copy_paste', 'conf', 'iou'}
CFG_INT_KEYS = {
'epochs', 'patience', 'batch', 'workers', 'seed', 'close_mosaic', 'mask_ratio', 'max_det', 'vid_stride',
'line_thickness', 'workspace', 'nbs'}
'line_thickness', 'workspace', 'nbs', 'save_period'}
CFG_BOOL_KEYS = {
'save', 'exist_ok', 'pretrained', 'verbose', 'deterministic', 'single_cls', 'image_weights', 'rect', 'cos_lr',
'overlap_mask', 'val', 'save_json', 'save_hybrid', 'half', 'dnn', 'plots', 'show', 'save_txt', 'save_conf',
@ -131,7 +131,7 @@ def get_cfg(cfg: Union[str, Path, Dict, SimpleNamespace] = DEFAULT_CFG, override
return IterableSimpleNamespace(**cfg)
def check_cfg_mismatch(base: Dict, custom: Dict):
def check_cfg_mismatch(base: Dict, custom: Dict, e=None):
"""
This function checks for any mismatched keys between a custom configuration list and a base configuration list.
If any mismatched keys are found, the function prints out similar keys from the base list and exits the program.
@ -143,12 +143,12 @@ def check_cfg_mismatch(base: Dict, custom: Dict):
base, custom = (set(x.keys()) for x in (base, custom))
mismatched = [x for x in custom if x not in base]
if mismatched:
string = ''
for x in mismatched:
matches = get_close_matches(x, base, 3, 0.6)
match_str = f"Similar arguments are {matches}." if matches else 'There are no similar arguments.'
LOGGER.warning(f"'{colorstr('red', 'bold', x)}' is not a valid YOLO argument. {match_str}")
LOGGER.warning(CLI_HELP_MSG)
sys.exit()
matches = get_close_matches(x, base)
match_str = f"Similar arguments are {matches}." if matches else ''
string += f"'{colorstr('red', 'bold', x)}' is not a valid YOLO argument. {match_str}\n"
raise SyntaxError(string + CLI_HELP_MSG) from e
def merge_equals_args(args: List[str]) -> List[str]:
@ -178,10 +178,6 @@ def merge_equals_args(args: List[str]) -> List[str]:
return new_args
def argument_error(arg):
return SyntaxError(f"'{arg}' is not a valid YOLO argument.\n{CLI_HELP_MSG}")
def entrypoint(debug=''):
"""
This function is the ultralytics package entrypoint, it's responsible for parsing the command line arguments passed
@ -212,6 +208,7 @@ def entrypoint(debug=''):
'settings': lambda: yaml_print(USER_CONFIG_DIR / 'settings.yaml'),
'cfg': lambda: yaml_print(DEFAULT_CFG_PATH),
'copy-cfg': copy_default_cfg}
FULL_ARGS_DICT = {**DEFAULT_CFG_DICT, **{k: None for k in tasks}, **{k: None for k in modes}, **special}
special = {**special, **{f'-{k}': v for k, v in special.items()}, **{f'--{k}': v for k, v in special.items()}}
overrides = {} # basic overrides, i.e. imgsz=320
@ -236,7 +233,7 @@ def entrypoint(debug=''):
v = eval(v)
overrides[k] = v
except (NameError, SyntaxError, ValueError, AssertionError) as e:
raise argument_error(a) from e
check_cfg_mismatch(FULL_ARGS_DICT, {a: ""}, e)
elif a in tasks:
overrides['task'] = a
@ -251,7 +248,7 @@ def entrypoint(debug=''):
raise SyntaxError(f"'{colorstr('red', 'bold', a)}' is a valid YOLO argument but is missing an '=' sign "
f"to set its value, i.e. try '{a}={DEFAULT_CFG_DICT[a]}'\n{CLI_HELP_MSG}")
else:
raise argument_error(a)
check_cfg_mismatch(FULL_ARGS_DICT, {a: ""})
# Defaults
task2model = dict(detect='yolov8n.pt', segment='yolov8n-seg.pt', classify='yolov8n-cls.pt')

1
ultralytics/yolo/cfg/default.yaml
View File

@ -12,6 +12,7 @@ patience: 50 # epochs to wait for no observable improvement for early stopping
batch: 16 # number of images per batch (-1 for AutoBatch)
imgsz: 640 # size of input images as integer or w,h
save: True # save train checkpoints and predict results
save_period: -1 # Save checkpoint every x epochs (disabled if < 1)
cache: False # True/ram, disk or False. Use cache for data loading
device: # device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu
workers: 8 # number of worker threads for data loading (per RANK if DDP)

2
ultralytics/yolo/data/dataloaders/stream_loaders.py
View File

@ -291,7 +291,7 @@ class LoadPilAndNumpy:
self.mode = 'image'
# generate fake paths
self.paths = [f"image{i}.jpg" for i in range(len(self.im0))]
self.bs = 1
self.bs = len(self.im0)
@staticmethod
def _single_check(im):

1
ultralytics/yolo/data/dataloaders/v5loader.py
View File

@ -34,6 +34,7 @@ from ultralytics.yolo.utils.checks import check_requirements, check_yaml
from ultralytics.yolo.utils.downloads import unzip_file
from ultralytics.yolo.utils.ops import clean_str, segments2boxes, xyn2xy, xywh2xyxy, xywhn2xyxy, xyxy2xywhn
from ultralytics.yolo.utils.torch_utils import torch_distributed_zero_first
from .v5augmentations import (Albumentations, augment_hsv, classify_albumentations, classify_transforms, copy_paste,
letterbox, mixup, random_perspective)

2
ultralytics/yolo/data/dataset.py
View File

@ -85,7 +85,6 @@ class YOLODataset(BaseDataset):
x["results"] = nf, nm, ne, nc, len(self.im_files)
x["msgs"] = msgs # warnings
x["version"] = self.cache_version # cache version
self.im_files = [lb["im_file"] for lb in x["labels"]] # update im_files
if is_dir_writeable(path.parent):
np.save(str(path), x) # save cache for next time
path.with_suffix(".cache.npy").rename(path) # remove .npy suffix
@ -117,6 +116,7 @@ class YOLODataset(BaseDataset):
# Read cache
[cache.pop(k) for k in ("hash", "version", "msgs")] # remove items
labels = cache["labels"]
self.im_files = [lb["im_file"] for lb in labels] # update im_files
# Check if the dataset is all boxes or all segments
len_cls = sum(len(lb["cls"]) for lb in labels)

7
ultralytics/yolo/engine/exporter.py
View File

@ -64,14 +64,13 @@ import numpy as np
import pandas as pd
import torch
import ultralytics
from ultralytics.nn.autobackend import check_class_names
from ultralytics.nn.modules import Detect, Segment
from ultralytics.nn.tasks import DetectionModel, SegmentationModel
from ultralytics.yolo.cfg import get_cfg
from ultralytics.yolo.data.dataloaders.stream_loaders import LoadImages
from ultralytics.yolo.data.utils import check_det_dataset, IMAGENET_MEAN, IMAGENET_STD
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, callbacks, colorstr, get_default_args, yaml_save
from ultralytics.yolo.data.utils import IMAGENET_MEAN, IMAGENET_STD, check_det_dataset
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, __version__, callbacks, colorstr, get_default_args, yaml_save
from ultralytics.yolo.utils.checks import check_imgsz, check_requirements, check_version, check_yaml
from ultralytics.yolo.utils.files import file_size
from ultralytics.yolo.utils.ops import Profile
@ -209,7 +208,7 @@ class Exporter:
'description': f"Ultralytics {self.pretty_name} model trained on {self.model.args['data']}",
'author': 'Ultralytics',
'license': 'GPL-3.0 https://ultralytics.com/license',
'version': ultralytics.__version__,
'version': __version__,
'stride': int(max(model.stride)),
'names': model.names} # model metadata

10
ultralytics/yolo/engine/model.py
View File

@ -1,16 +1,17 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
import sys
from pathlib import Path
from typing import List
import sys
from ultralytics import yolo # noqa
from ultralytics.nn.tasks import (ClassificationModel, DetectionModel, SegmentationModel, attempt_load_one_weight,
guess_model_task)
from ultralytics.yolo.cfg import get_cfg
from ultralytics.yolo.engine.exporter import Exporter
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, RANK, callbacks, yaml_load
from ultralytics.yolo.utils.checks import check_yaml, check_imgsz
from ultralytics.yolo.utils.checks import check_imgsz, check_yaml
from ultralytics.yolo.utils.downloads import GITHUB_ASSET_STEMS
from ultralytics.yolo.utils.torch_utils import smart_inference_mode
# Map head to model, trainer, validator, and predictor classes
@ -58,10 +59,13 @@ class YOLO:
# Load or create new YOLO model
load_methods = {'.pt': self._load, '.yaml': self._new}
suffix = Path(model).suffix
if not suffix and Path(model).stem in GITHUB_ASSET_STEMS:
model, suffix = Path(model).with_suffix('.pt'), '.pt' # add suffix, i.e. yolov8n -> yolov8n.pt
if suffix in load_methods:
{'.pt': self._load, '.yaml': self._new}[suffix](model)
else:
raise NotImplementedError(f"'{suffix}' model loading not implemented")
raise NotImplementedError(f"'{suffix}' models not supported. Try a *.pt and *.yaml model, "
"i.e. model='yolov8n.pt' or model='yolov8n.yaml'")
def __call__(self, source=None, stream=False, **kwargs):
return self.predict(source, stream, **kwargs)

9
ultralytics/yolo/engine/trainer.py
View File

@ -20,12 +20,11 @@ from torch.nn.parallel import DistributedDataParallel as DDP
from torch.optim import lr_scheduler
from tqdm import tqdm
from ultralytics import __version__
from ultralytics.nn.tasks import attempt_load_one_weight, attempt_load_weights
from ultralytics.yolo.cfg import get_cfg
from ultralytics.yolo.data.utils import check_cls_dataset, check_det_dataset
from ultralytics.yolo.utils import (DEFAULT_CFG, LOGGER, RANK, SETTINGS, TQDM_BAR_FORMAT, callbacks, colorstr, emojis,
yaml_save)
from ultralytics.yolo.utils import (DEFAULT_CFG, LOGGER, RANK, SETTINGS, TQDM_BAR_FORMAT, __version__, callbacks,
colorstr, emojis, yaml_save)
from ultralytics.yolo.utils.autobatch import check_train_batch_size
from ultralytics.yolo.utils.checks import check_file, check_imgsz, print_args
from ultralytics.yolo.utils.dist import ddp_cleanup, generate_ddp_command
@ -51,6 +50,7 @@ class BaseTrainer:
wdir (Path): Directory to save weights.
last (Path): Path to last checkpoint.
best (Path): Path to best checkpoint.
save_period (int): Save checkpoint every x epochs (disabled if < 1).
batch_size (int): Batch size for training.
epochs (int): Number of epochs to train for.
start_epoch (int): Starting epoch for training.
@ -101,6 +101,7 @@ class BaseTrainer:
self.args.save_dir = str(self.save_dir)
yaml_save(self.save_dir / 'args.yaml', vars(self.args)) # save run args
self.last, self.best = self.wdir / 'last.pt', self.wdir / 'best.pt' # checkpoint paths
self.save_period = self.args.save_period
self.batch_size = self.args.batch
self.epochs = self.args.epochs
@ -392,6 +393,8 @@ class BaseTrainer:
torch.save(ckpt, self.last)
if self.best_fitness == self.fitness:
torch.save(ckpt, self.best)
if (self.epoch > 0) and (self.save_period > 0) and (self.epoch % self.save_period == 0):
torch.save(ckpt, self.wdir / f'epoch{self.epoch}.pt')
del ckpt
def get_dataset(self, data):

16
ultralytics/yolo/utils/__init__.py
View File

@ -22,6 +22,8 @@ import requests
import torch
import yaml
from ultralytics import __version__
# Constants
FILE = Path(__file__).resolve()
ROOT = FILE.parents[2] # YOLO
@ -520,30 +522,27 @@ def set_sentry():
if 'exc_info' in hint:
exc_type, exc_value, tb = hint['exc_info']
if exc_type in (KeyboardInterrupt, FileNotFoundError) \
or 'out of memory' in str(exc_value) \
or not sys.argv[0].endswith('yolo'):
or 'out of memory' in str(exc_value):
return None # do not send event
env = 'Colab' if is_colab() else 'Kaggle' if is_kaggle() else 'Jupyter' if is_jupyter() else \
'Docker' if is_docker() else platform.system()
event['tags'] = {
"sys_argv": sys.argv[0],
"sys_argv_name": Path(sys.argv[0]).name,
"install": 'git' if is_git_dir() else 'pip' if is_pip_package() else 'other',
"os": env}
"os": ENVIRONMENT}
return event
if SETTINGS['sync'] and \
RANK in {-1, 0} and \
sys.argv[0].endswith('yolo') and \
Path(sys.argv[0]).name == 'yolo' and \
not is_pytest_running() and \
not is_github_actions_ci() and \
((is_pip_package() and not is_git_dir()) or
(get_git_origin_url() == "https://github.com/ultralytics/ultralytics.git" and get_git_branch() == "main")):
import hashlib
import sentry_sdk # noqa
from ultralytics import __version__
sentry_sdk.init(
dsn="https://f805855f03bb4363bc1e16cb7d87b654@o4504521589325824.ingest.sentry.io/4504521592406016",
@ -572,6 +571,7 @@ def get_settings(file=USER_CONFIG_DIR / 'settings.yaml', version='0.0.2'):
dict: Dictionary of settings key-value pairs.
"""
import hashlib
from ultralytics.yolo.utils.checks import check_version
from ultralytics.yolo.utils.torch_utils import torch_distributed_zero_first
@ -628,4 +628,6 @@ if platform.system() == 'Windows':
PREFIX = colorstr("Ultralytics: ")
SETTINGS = get_settings()
DATASETS_DIR = Path(SETTINGS['datasets_dir']) # global datasets directory
ENVIRONMENT = 'Colab' if is_colab() else 'Kaggle' if is_kaggle() else 'Jupyter' if is_jupyter() else \
'Docker' if is_docker() else platform.system()
set_sentry()

2
ultralytics/yolo/utils/checks.py
View File

@ -155,7 +155,7 @@ def check_online() -> bool:
bool: True if connection is successful, False otherwise.
"""
import socket
with contextlib.suppress(subprocess.CalledProcessError):
with contextlib.suppress(Exception):
host = socket.gethostbyname("www.github.com")
socket.create_connection((host, 80), timeout=2)
return True

11
ultralytics/yolo/utils/downloads.py
View File

@ -6,7 +6,7 @@ from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
from urllib import parse, request
from zipfile import ZipFile, is_zipfile, BadZipFile
from zipfile import BadZipFile, ZipFile, is_zipfile
import requests
import torch
@ -14,6 +14,11 @@ from tqdm import tqdm
from ultralytics.yolo.utils import LOGGER
GITHUB_ASSET_NAMES = [f'yolov8{size}{suffix}.pt' for size in 'nsmlx' for suffix in ('', '6', '-cls', '-seg')] + \
[f'yolov5{size}u.pt' for size in 'nsmlx'] + \
[f'yolov3{size}u.pt' for size in ('', '-spp', '-tiny')]
GITHUB_ASSET_STEMS = [Path(k).stem for k in GITHUB_ASSET_NAMES]
def is_url(url, check=True):
# Check if string is URL and check if URL exists
@ -158,9 +163,7 @@ def attempt_download_asset(file, repo='ultralytics/assets', release='v0.0.0'):
return file
# GitHub assets
assets = [f'yolov8{size}{suffix}.pt' for size in 'nsmlx' for suffix in ('', '6', '-cls', '-seg')] + \
[f'yolov5{size}u.pt' for size in 'nsmlx'] + \
[f'yolov3{size}u.pt' for size in ('', '-spp', '-tiny')]
assets = GITHUB_ASSET_NAMES
try:
tag, assets = github_assets(repo, release)
except Exception:

3
ultralytics/yolo/utils/torch_utils.py
View File

@ -17,7 +17,7 @@ import torch.nn as nn
import torch.nn.functional as F
from torch.nn.parallel import DistributedDataParallel as DDP
from ultralytics.yolo.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER
from ultralytics.yolo.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, __version__
from ultralytics.yolo.utils.checks import check_version
LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html
@ -61,7 +61,6 @@ def DDP_model(model):
def select_device(device='', batch=0, newline=False):
# device = None or 'cpu' or 0 or '0' or '0,1,2,3'
from ultralytics import __version__
s = f"Ultralytics YOLOv{__version__} 🚀 Python-{platform.python_version()} torch-{torch.__version__} "
device = str(device).lower()
for remove in 'cuda:', 'none', '(', ')', '[', ']', "'", ' ':

2
ultralytics/yolo/v8/classify/train.py
View File

@ -8,7 +8,7 @@ from ultralytics.yolo import v8
from ultralytics.yolo.data import build_classification_dataloader
from ultralytics.yolo.engine.trainer import BaseTrainer
from ultralytics.yolo.utils import DEFAULT_CFG
from ultralytics.yolo.utils.torch_utils import strip_optimizer, is_parallel
from ultralytics.yolo.utils.torch_utils import is_parallel, strip_optimizer
class ClassificationTrainer(BaseTrainer):