HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.224 Counting and Heatmaps updates (#6855)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: Muhammad Rizwan Munawar <chr043416@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 2023-12-08 02:34:32 +01:00 • committed by GitHub
parent 0f5406ec21
commit 2b49d71772
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
15 changed files with 225 additions and 145 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/README.md
View file

@ -4,7 +4,7 @@ Ultralytics Docs are deployed to [https://docs.ultralytics.com](https://docs.ult
[![pages-build-deployment](https://github.com/ultralytics/docs/actions/workflows/pages/pages-build-deployment/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/pages/pages-build-deployment) [![Check Broken links](https://github.com/ultralytics/docs/actions/workflows/links.yml/badge.svg)](https://github.com/ultralytics/docs/actions/workflows/links.yml)
### Install Ultralytics package
## Install Ultralytics package
[![PyPI version](https://badge.fury.io/py/ultralytics.svg)](https://badge.fury.io/py/ultralytics) [![Downloads](https://static.pepy.tech/badge/ultralytics)](https://pepy.tech/project/ultralytics)
@ -32,7 +32,7 @@ This will install the ultralytics package and its dependencies in developer mode
Note that you may need to use the pip3 command instead of pip if you have multiple versions of Python installed on your system.
### Building and Serving Locally
## Building and Serving Locally
The `mkdocs serve` command is used to build and serve a local version of the MkDocs documentation site. It is typically used during the development and testing phase of a documentation project.
@ -52,7 +52,7 @@ While the site is being served, you can make changes to the documentation files
To stop the serve command and terminate the local server, you can use the `CTRL+C` keyboard shortcut.
### Building and Serving Multi-Language
## Building and Serving Multi-Language
For multi-language MkDocs sites use the following additional steps:
@ -81,7 +81,7 @@ For multi-language MkDocs sites use the following additional steps:
Note the above steps are combined into the Ultralytics [build_docs.py](https://github.com/ultralytics/ultralytics/blob/main/docs/build_docs.py) script.
### Deploying Your Documentation Site
## Deploying Your Documentation Site
To deploy your MkDocs documentation site, you will need to choose a hosting provider and a deployment method. Some popular options include GitHub Pages, GitLab Pages, and Amazon S3.

113
docs/en/guides/heatmaps.md
View file

@ -35,12 +35,11 @@ A heatmap generated with [Ultralytics YOLOv8](https://github.com/ultralytics/ult
from ultralytics.solutions import heatmap
import cv2
model = YOLO("yolov8s.pt")
model = YOLO("yolov8s.pt") # YOLOv8 custom/pretrained model
cap = cv2.VideoCapture("path/to/video/file.mp4")
if not cap.isOpened():
print("Error reading video file")
exit(0)
assert cap.isOpened(), "Error reading video file"
# Heatmap Init
heatmap_obj = heatmap.Heatmap()
heatmap_obj.set_args(colormap=cv2.COLORMAP_CIVIDIS,
imw=cap.get(4), # should same as im0 width
@ -52,7 +51,7 @@ A heatmap generated with [Ultralytics YOLOv8](https://github.com/ultralytics/ult
if not success:
exit(0)
results = model.track(im0, persist=True)
frame = heatmap_obj.generate_heatmap(im0, tracks=results)
im0 = heatmap_obj.generate_heatmap(im0, tracks=results)
```
@ -62,14 +61,13 @@ A heatmap generated with [Ultralytics YOLOv8](https://github.com/ultralytics/ult
from ultralytics.solutions import heatmap
import cv2
model = YOLO("yolov8s.pt")
model = YOLO("yolov8s.pt") # YOLOv8 custom/pretrained model
cap = cv2.VideoCapture("path/to/video/file.mp4")
if not cap.isOpened():
print("Error reading video file")
exit(0)
assert cap.isOpened(), "Error reading video file"
classes_for_heatmap = [0, 2]
# Heatmap init
heatmap_obj = heatmap.Heatmap()
heatmap_obj.set_args(colormap=cv2.COLORMAP_CIVIDIS,
imw=cap.get(4), # should same as im0 width
@ -80,29 +78,28 @@ A heatmap generated with [Ultralytics YOLOv8](https://github.com/ultralytics/ult
success, im0 = cap.read()
if not success:
exit(0)
results = model.track(im0, persist=True,
classes=classes_for_heatmap)
frame = heatmap_obj.generate_heatmap(im0, tracks=results)
results = model.track(im0, persist=True, classes=classes_for_heatmap)
im0 = heatmap_obj.generate_heatmap(im0, tracks=results)
```
=== "Heatmap with Save Output"
```python
from ultralytics import YOLO
import heatmap
from ultralytics.solutions import heatmap
import cv2
model = YOLO("yolov8n.pt")
model = YOLO("yolov8s.pt") # YOLOv8 custom/pretrained model
cap = cv2.VideoCapture("path/to/video/file.mp4")
if not cap.isOpened():
print("Error reading video file")
exit(0)
assert cap.isOpened(), "Error reading video file"
# Video writer
video_writer = cv2.VideoWriter("heatmap_output.avi",
cv2.VideoWriter_fourcc(*'mp4v'),
int(cap.get(5)),
(int(cap.get(3)), int(cap.get(4))))
# Heatmap init
heatmap_obj = heatmap.Heatmap()
heatmap_obj.set_args(colormap=cv2.COLORMAP_CIVIDIS,
imw=cap.get(4), # should same as im0 width
@ -113,22 +110,55 @@ A heatmap generated with [Ultralytics YOLOv8](https://github.com/ultralytics/ult
success, im0 = cap.read()
if not success:
exit(0)
results = model.track(im0, persist=True)
frame = heatmap_obj.generate_heatmap(im0, tracks=results)
results = model.track(im0, persist=True, classes=classes_for_heatmap)
im0 = heatmap_obj.generate_heatmap(im0, tracks=results)
video_writer.write(im0)
video_writer.release()
```
=== "Heatmap with Object Counting"
```python
from ultralytics import YOLO
from ultralytics.solutions import heatmap
import cv2
model = YOLO("yolov8s.pt") # YOLOv8 custom/pretrained model
cap = cv2.VideoCapture("path/to/video/file.mp4") # Video file Path, webcam 0
assert cap.isOpened(), "Error reading video file"
# Region for object counting
count_reg_pts = [(20, 400), (1080, 404), (1080, 360), (20, 360)]
# Heatmap Init
heatmap_obj = heatmap.Heatmap()
heatmap_obj.set_args(colormap=cv2.COLORMAP_JET,
imw=cap.get(4), # should same as im0 width
imh=cap.get(3), # should same as im0 height
view_img=True,
count_reg_pts=count_reg_pts)
while cap.isOpened():
success, im0 = cap.read()
if not success:
exit(0)
results = model.track(im0, persist=True)
im0 = heatmap_obj.generate_heatmap(im0, tracks=results)
```
### Arguments `set_args`
| Name | Type | Default | Description |
|---------------|----------------|---------|--------------------------------|
| view_img | `bool` | `False` | Display the frame with heatmap |
| colormap | `cv2.COLORMAP` | `None` | cv2.COLORMAP for heatmap |
| imw | `int` | `None` | Width of Heatmap |
| imh | `int` | `None` | Height of Heatmap |
| heatmap_alpha | `float` | `0.5` | Heatmap alpha value |
| Name | Type | Default | Description |
|---------------------|----------------|-----------------|---------------------------------|
| view_img | `bool` | `False` | Display the frame with heatmap |
| colormap | `cv2.COLORMAP` | `None` | cv2.COLORMAP for heatmap |
| imw | `int` | `None` | Width of Heatmap |
| imh | `int` | `None` | Height of Heatmap |
| heatmap_alpha | `float` | `0.5` | Heatmap alpha value |
| count_reg_pts | `list` | `None` | Object counting region points |
| count_txt_thickness | `int` | `2` | Count values text size |
| count_reg_color | `tuple` | `(255, 0, 255)` | Counting region color |
| region_thickness | `int` | `5` | Counting region thickness value |
### Arguments `model.track`
@ -140,3 +170,32 @@ A heatmap generated with [Ultralytics YOLOv8](https://github.com/ultralytics/ult
| `conf` | `float` | `0.3` | Confidence Threshold |
| `iou` | `float` | `0.5` | IOU Threshold |
| `classes` | `list` | `None` | filter results by class, i.e. classes=0, or classes=[0,2,3] |
### Heatmap COLORMAPs
| Colormap Name | Description |
|---------------------------------|----------------------------------------|
| `cv::COLORMAP_AUTUMN` | Autumn color map |
| `cv::COLORMAP_BONE` | Bone color map |
| `cv::COLORMAP_JET` | Jet color map |
| `cv::COLORMAP_WINTER` | Winter color map |
| `cv::COLORMAP_RAINBOW` | Rainbow color map |
| `cv::COLORMAP_OCEAN` | Ocean color map |
| `cv::COLORMAP_SUMMER` | Summer color map |
| `cv::COLORMAP_SPRING` | Spring color map |
| `cv::COLORMAP_COOL` | Cool color map |
| `cv::COLORMAP_HSV` | HSV (Hue, Saturation, Value) color map |
| `cv::COLORMAP_PINK` | Pink color map |
| `cv::COLORMAP_HOT` | Hot color map |
| `cv::COLORMAP_PARULA` | Parula color map |
| `cv::COLORMAP_MAGMA` | Magma color map |
| `cv::COLORMAP_INFERNO` | Inferno color map |
| `cv::COLORMAP_PLASMA` | Plasma color map |
| `cv::COLORMAP_VIRIDIS` | Viridis color map |
| `cv::COLORMAP_CIVIDIS` | Cividis color map |
| `cv::COLORMAP_TWILIGHT` | Twilight color map |
| `cv::COLORMAP_TWILIGHT_SHIFTED` | Shifted Twilight color map |
| `cv::COLORMAP_TURBO` | Turbo color map |
| `cv::COLORMAP_DEEPGREEN` | Deep Green color map |
These colormaps are commonly used for visualizing data with different color representations.

14
docs/en/guides/object-counting.md
View file

@ -23,7 +23,6 @@ Object counting with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly
| ![Conveyor Belt Packets Counting Using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/70e2d106-510c-4c6c-a57a-d34a765aa757) | ![Fish Counting in Sea using Ultralytics YOLOv8](https://github.com/RizwanMunawar/ultralytics/assets/62513924/c60d047b-3837-435f-8d29-bb9fc95d2191) |
| Conveyor Belt Packets Counting Using Ultralytics YOLOv8 | Fish Counting in Sea using Ultralytics YOLOv8 |
!!! Example "Object Counting Example"
=== "Object Counting"
@ -34,9 +33,7 @@ Object counting with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly
model = YOLO("yolov8n.pt")
cap = cv2.VideoCapture("path/to/video/file.mp4")
if not cap.isOpened():
print("Error reading video file")
exit(0)
assert cap.isOpened(), "Error reading video file"
counter = object_counter.ObjectCounter() # Init Object Counter
region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360)]
@ -61,9 +58,7 @@ Object counting with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly
model = YOLO("yolov8n.pt")
cap = cv2.VideoCapture("path/to/video/file.mp4")
if not cap.isOpened():
print("Error reading video file")
exit(0)
assert cap.isOpened(), "Error reading video file"
classes_to_count = [0, 2]
counter = object_counter.ObjectCounter() # Init Object Counter
@ -91,9 +86,7 @@ Object counting with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly
model = YOLO("yolov8n.pt")
cap = cv2.VideoCapture("path/to/video/file.mp4")
if not cap.isOpened():
print("Error reading video file")
exit(0)
assert cap.isOpened(), "Error reading video file"
video_writer = cv2.VideoWriter("object_counting.avi",
cv2.VideoWriter_fourcc(*'mp4v'),
@ -134,7 +127,6 @@ Object counting with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly
| track_thickness | `int` | `2` | Tracking line thickness |
| draw_tracks | `bool` | `False` | Draw Tracks lines |
### Arguments `model.track`
| Name | Type | Default | Description |

9
docs/en/guides/workouts-monitoring.md
View file

@ -23,7 +23,6 @@ Monitoring workouts through pose estimation with [Ultralytics YOLOv8](https://gi
| ![PushUps Counting](https://github.com/RizwanMunawar/ultralytics/assets/62513924/cf016a41-589f-420f-8a8c-2cc8174a16de) | ![PullUps Counting](https://github.com/RizwanMunawar/ultralytics/assets/62513924/cb20f316-fac2-4330-8445-dcf5ffebe329) |
| PushUps Counting | PullUps Counting |
!!! Example "Workouts Monitoring Example"
=== "Workouts Monitoring"
@ -34,9 +33,7 @@ Monitoring workouts through pose estimation with [Ultralytics YOLOv8](https://gi
model = YOLO("yolov8n-pose.pt")
cap = cv2.VideoCapture("path/to/video/file.mp4")
if not cap.isOpened():
print("Error reading video file")
exit(0)
assert cap.isOpened(), "Error reading video file"
gym_object = ai_gym.AIGym() # init AI GYM module
gym_object.set_args(line_thickness=2,
@ -62,9 +59,7 @@ Monitoring workouts through pose estimation with [Ultralytics YOLOv8](https://gi
model = YOLO("yolov8n-pose.pt")
cap = cv2.VideoCapture("path/to/video/file.mp4")
if not cap.isOpened():
print("Error reading video file")
exit(0)
assert cap.isOpened(), "Error reading video file"
video_writer = cv2.VideoWriter("workouts.avi",
cv2.VideoWriter_fourcc(*'mp4v'),

1
docs/en/yolov5/tutorials/clearml_logging_integration.md
View file

@ -90,7 +90,6 @@ This will capture:
- Mosaic per epoch
- Validation images per epoch
That's a lot right? 🤯 Now, we can visualize all of this information in the ClearML UI to get an overview of our training progress. Add custom columns to the table view (such as e.g. mAP_0.5) so you can easily sort on the best performing model. Or select multiple experiments and directly compare them!
There even more we can do with all of this information, like hyperparameter optimization and remote execution, so keep reading if you want to see how that works!