Chiebot-Mirror
/
ultralytics
mirror of https://github.com/ultralytics/ultralytics.git
9
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into torch-prof

Browse Source
torch-prof
Burhan 3 months ago committed by GitHub
parent 4c71b3d889 cece2ee2cf
commit fa9f251ad0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
28 changed files with 361 additions and 524 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 2
      .github/workflows/docker.yaml
  2. 1
      .gitignore
  3. 131
      docs/en/guides/analytics.md
  4. 1
      docs/en/guides/distance-calculation.md
  5. 166
      docs/en/guides/heatmaps.md
  6. 163
      docs/en/guides/object-counting.md
  7. 52
      docs/en/guides/queue-management.md
  8. 12
      docs/en/guides/speed-estimation.md
  9. 12
      docs/en/guides/streamlit-live-inference.md
  10. 36
      docs/en/guides/workouts-monitoring.md
  11. 2
      docs/en/integrations/index.md
  12. 2
      docs/en/integrations/sony-imx500.md
  13. 1
      docs/en/macros/export-table.md
  14. 4
      docs/en/reference/utils/torch_utils.md
  15. 3
      docs/mkdocs_github_authors.yaml
  16. 4
      mkdocs.yml
  17. 9
      tests/test_exports.py
  18. 2
      ultralytics/__init__.py
  19. 176
      ultralytics/engine/exporter.py
  20. 4
      ultralytics/models/yolo/detect/val.py
  21. 4
      ultralytics/models/yolo/pose/val.py
  22. 4
      ultralytics/models/yolo/segment/val.py
  23. 27
      ultralytics/nn/autobackend.py
  24. 3
      ultralytics/nn/modules/block.py
  25. 12
      ultralytics/nn/modules/head.py
  26. 5
      ultralytics/utils/benchmarks.py
  27. 2
      ultralytics/utils/tal.py
  28. 45
      ultralytics/utils/torch_utils.py

2
.github/workflows/docker.yaml
Unescape View File

@ -172,7 +172,7 @@ jobs:
fi
if [[ "${{ matrix.tags }}" == "latest-python" ]]; then
t=ultralytics/ultralytics:latest-jupyter
v=ultralytics/ultralytics:${{ steps.get_version.outputs.version_tag }}-jupyter
v=ultralytics/ultralytics:${{ steps.get_version.outputs.version }}-jupyter
docker build -f docker/Dockerfile-jupyter -t $t -t $v .
docker push $t
if [[ "${{ steps.check_tag.outputs.new_release }}" == "true" ]]; then

1
.gitignore vendored
Unescape View File

@ -163,6 +163,7 @@ weights/
*_openvino_model/
*_paddle_model/
*_ncnn_model/
*_imx_model/
pnnx*
# Autogenerated files for tests

131
docs/en/guides/analytics.md
Unescape View File

@ -45,126 +45,15 @@ This guide provides a comprehensive overview of three fundamental types of [data
# generate the pie chart
yolo solutions analytics analytics_type="pie" show=True
```
=== "Python"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
out = cv2.VideoWriter(
"ultralytics_analytics.avi",
cv2.VideoWriter_fourcc(*"MJPG"),
fps,
(1920, 1080), # This is fixed
)
analytics = solutions.Analytics(
analytics_type="line",
show=True,
)
# generate the bar plots
yolo solutions analytics analytics_type="bar" show=True
frame_count = 0
while cap.isOpened():
success, im0 = cap.read()
if success:
frame_count += 1
im0 = analytics.process_data(im0, frame_count) # update analytics graph every frame
out.write(im0) # write the video file
else:
break
cap.release()
out.release()
cv2.destroyAllWindows()
# generate the area plots
yolo solutions analytics analytics_type="area" show=True
```
=== "Pie Chart"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
out = cv2.VideoWriter(
"ultralytics_analytics.avi",
cv2.VideoWriter_fourcc(*"MJPG"),
fps,
(1920, 1080), # This is fixed
)
analytics = solutions.Analytics(
analytics_type="pie",
show=True,
)
frame_count = 0
while cap.isOpened():
success, im0 = cap.read()
if success:
frame_count += 1
im0 = analytics.process_data(im0, frame_count) # update analytics graph every frame
out.write(im0) # write the video file
else:
break
cap.release()
out.release()
cv2.destroyAllWindows()
```
=== "Bar Plot"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
out = cv2.VideoWriter(
"ultralytics_analytics.avi",
cv2.VideoWriter_fourcc(*"MJPG"),
fps,
(1920, 1080), # This is fixed
)
analytics = solutions.Analytics(
analytics_type="bar",
show=True,
)
frame_count = 0
while cap.isOpened():
success, im0 = cap.read()
if success:
frame_count += 1
im0 = analytics.process_data(im0, frame_count) # update analytics graph every frame
out.write(im0) # write the video file
else:
break
cap.release()
out.release()
cv2.destroyAllWindows()
```
=== "Area chart"
=== "Python"
```python
import cv2
@ -173,9 +62,9 @@ This guide provides a comprehensive overview of three fundamental types of [data
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
out = cv2.VideoWriter(
"ultralytics_analytics.avi",
cv2.VideoWriter_fourcc(*"MJPG"),
@ -183,11 +72,15 @@ This guide provides a comprehensive overview of three fundamental types of [data
(1920, 1080), # This is fixed
)
# Init analytics
analytics = solutions.Analytics(
analytics_type="area",
show=True,
show=True, # Display the output
analytics_type="line", # Pass the analytics type, could be "pie", "bar" or "area".
model="yolo11n.pt", # Path to the YOLO11 model file
# classes=[0, 2], # If you want to count specific classes i.e person and car with COCO pretrained model.
)
# Process video
frame_count = 0
while cap.isOpened():
success, im0 = cap.read()

1
docs/en/guides/distance-calculation.md
Unescape View File

@ -55,6 +55,7 @@ Measuring the gap between two objects is known as distance calculation within a
# Init distance-calculation obj
distance = solutions.DistanceCalculation(model="yolo11n.pt", show=True)
# Process video
while cap.isOpened():
success, im0 = cap.read()
if not success:

166
docs/en/guides/heatmaps.md
Unescape View File

@ -47,119 +47,12 @@ A heatmap generated with [Ultralytics YOLO11](https://github.com/ultralytics/ult
# Pass a custom colormap
yolo solutions heatmap colormap=cv2.COLORMAP_INFERNO
```
=== "Python"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
video_writer = cv2.VideoWriter("heatmap_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Init heatmap
heatmap = solutions.Heatmap(
show=True,
model="yolo11n.pt",
colormap=cv2.COLORMAP_PARULA,
)
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = heatmap.generate_heatmap(im0)
video_writer.write(im0)
cap.release()
video_writer.release()
cv2.destroyAllWindows()
```
=== "Line Counting"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
video_writer = cv2.VideoWriter("heatmap_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# line for object counting
line_points = [(20, 400), (1080, 404)]
# Init heatmap
heatmap = solutions.Heatmap(
show=True,
model="yolo11n.pt",
colormap=cv2.COLORMAP_PARULA,
region=line_points,
)
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = heatmap.generate_heatmap(im0)
video_writer.write(im0)
cap.release()
video_writer.release()
cv2.destroyAllWindows()
# Heatmaps + object counting
yolo solutions heatmap region=[(20, 400), (1080, 404), (1080, 360), (20, 360)]
```
=== "Polygon Counting"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
video_writer = cv2.VideoWriter("heatmap_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Define polygon points
region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360), (20, 400)]
# Init heatmap
heatmap = solutions.Heatmap(
show=True,
model="yolo11n.pt",
colormap=cv2.COLORMAP_PARULA,
region=region_points,
)
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = heatmap.generate_heatmap(im0)
video_writer.write(im0)
cap.release()
video_writer.release()
cv2.destroyAllWindows()
```
=== "Region Counting"
=== "Python"
```python
import cv2
@ -173,51 +66,24 @@ A heatmap generated with [Ultralytics YOLO11](https://github.com/ultralytics/ult
# Video writer
video_writer = cv2.VideoWriter("heatmap_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Define region points
region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360)]
# Init heatmap
heatmap = solutions.Heatmap(
show=True,
model="yolo11n.pt",
colormap=cv2.COLORMAP_PARULA,
region=region_points,
)
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = heatmap.generate_heatmap(im0)
video_writer.write(im0)
cap.release()
video_writer.release()
cv2.destroyAllWindows()
```
=== "Specific Classes"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
video_writer = cv2.VideoWriter("heatmap_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# In case you want to apply object counting + heatmaps, you can pass region points.
# region_points = [(20, 400), (1080, 404)] # Define line points
# region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360)] # Define region points
# region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360), (20, 400)] # Define polygon points
# Init heatmap
heatmap = solutions.Heatmap(
show=True,
model="yolo11n.pt",
classes=[0, 2],
show=True, # Display the output
model="yolo11n.pt", # Path to the YOLO11 model file
colormap=cv2.COLORMAP_PARULA, # Colormap of heatmap
# region=region_points, # If you want to do object counting with heatmaps, you can pass region_points
# classes=[0, 2], # If you want to generate heatmap for specific classes i.e person and car.
# show_in=True, # Display in counts
# show_out=True, # Display out counts
# line_width=2, # Adjust the line width for bounding boxes and text display
)
# Process video
while cap.isOpened():
success, im0 = cap.read()
if not success:

163
docs/en/guides/object-counting.md
Unescape View File

@ -73,165 +73,22 @@ Object counting with [Ultralytics YOLO11](https://github.com/ultralytics/ultraly
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Define region points
region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360)]
# region_points = [(20, 400), (1080, 400)] # For line counting
region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360)] # For rectangle region counting
# region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360), (20, 400)] # For polygon region counting
# Video writer
video_writer = cv2.VideoWriter("object_counting_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Init Object Counter
counter = solutions.ObjectCounter(
show=True,
region=region_points,
model="yolo11n.pt",
)
# Process video
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = counter.count(im0)
video_writer.write(im0)
cap.release()
video_writer.release()
cv2.destroyAllWindows()
```
=== "OBB Object Counting"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# line or region points
line_points = [(20, 400), (1080, 400)]
# Video writer
video_writer = cv2.VideoWriter("object_counting_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Init Object Counter
counter = solutions.ObjectCounter(
show=True,
region=line_points,
model="yolo11n-obb.pt",
)
# Process video
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = counter.count(im0)
video_writer.write(im0)
cap.release()
video_writer.release()
cv2.destroyAllWindows()
```
=== "Count in Polygon"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Define region points
region_points = [(20, 400), (1080, 404), (1080, 360), (20, 360), (20, 400)]
# Video writer
video_writer = cv2.VideoWriter("object_counting_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Init Object Counter
counter = solutions.ObjectCounter(
show=True,
region=region_points,
model="yolo11n.pt",
)
# Process video
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = counter.count(im0)
video_writer.write(im0)
cap.release()
video_writer.release()
cv2.destroyAllWindows()
```
=== "Count in Line"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Define region points
line_points = [(20, 400), (1080, 400)]
# Video writer
video_writer = cv2.VideoWriter("object_counting_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Init Object Counter
counter = solutions.ObjectCounter(
show=True,
region=line_points,
model="yolo11n.pt",
)
# Process video
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = counter.count(im0)
video_writer.write(im0)
cap.release()
video_writer.release()
cv2.destroyAllWindows()
```
=== "Specific Classes"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
video_writer = cv2.VideoWriter("object_counting_output.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Init Object Counter
counter = solutions.ObjectCounter(
show=True,
model="yolo11n.pt",
classes=[0, 1],
show=True, # Display the output
region=region_points, # Pass region points
model="yolo11n.pt", # model="yolo11n-obb.pt" for object counting using YOLO11 OBB model.
# classes=[0, 2], # If you want to count specific classes i.e person and car with COCO pretrained model.
# show_in=True, # Display in counts
# show_out=True, # Display out counts
# line_width=2, # Adjust the line width for bounding boxes and text display
)
# Process video

52
docs/en/guides/queue-management.md
Unescape View File

@ -60,53 +60,23 @@ Queue management using [Ultralytics YOLO11](https://github.com/ultralytics/ultra
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
video_writer = cv2.VideoWriter("queue_management.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
queue_region = [(20, 400), (1080, 404), (1080, 360), (20, 360)]
# Define queue region points
queue_region = [(20, 400), (1080, 404), (1080, 360), (20, 360)] # Define queue region points
# queue_region = [(20, 400), (1080, 404), (1080, 360), (20, 360), (20, 400)] # Define queue polygon points
# Init Queue Manager
queue = solutions.QueueManager(
model="yolo11n.pt",
region=queue_region,
)
while cap.isOpened():
success, im0 = cap.read()
if success:
out = queue.process_queue(im0)
video_writer.write(im0)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
continue
print("Video frame is empty or video processing has been successfully completed.")
break
cap.release()
cv2.destroyAllWindows()
```
=== "Queue Manager Specific Classes"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
video_writer = cv2.VideoWriter("queue_management.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
queue_region = [(20, 400), (1080, 404), (1080, 360), (20, 360)]
queue = solutions.QueueManager(
model="yolo11n.pt",
classes=3,
show=True, # Display the output
model="yolo11n.pt", # Path to the YOLO11 model file
region=queue_region, # Pass queue region points
# classes=[0, 2], # If you want to count specific classes i.e person and car with COCO pretrained model.
# line_width=2, # Adjust the line width for bounding boxes and text display
)
# Process video
while cap.isOpened():
success, im0 = cap.read()

12
docs/en/guides/speed-estimation.md
Unescape View File

@ -61,16 +61,24 @@ keywords: Ultralytics YOLO11, speed estimation, object tracking, computer vision
from ultralytics import solutions
cap = cv2.VideoCapture("Path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
video_writer = cv2.VideoWriter("speed_management.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Define speed region points
speed_region = [(20, 400), (1080, 404), (1080, 360), (20, 360)]
speed = solutions.SpeedEstimator(model="yolo11n.pt", region=speed_region, show=True)
speed = solutions.SpeedEstimator(
show=True, # Display the output
model="yolo11n-pose.pt", # Path to the YOLO11 model file.
region=speed_region, # Pass region points
# classes=[0, 2], # If you want to estimate speed of specific classes.
# line_width=2, # Adjust the line width for bounding boxes and text display
)
# Process video
while cap.isOpened():
success, im0 = cap.read()

12
docs/en/guides/streamlit-live-inference.md
Unescape View File

@ -40,6 +40,12 @@ Streamlit makes it simple to build and deploy interactive web applications. Comb
!!! example "Streamlit Application"
=== "CLI"
```bash
yolo streamlit-predict
```
=== "Python"
```python
@ -50,12 +56,6 @@ Streamlit makes it simple to build and deploy interactive web applications. Comb
### Make sure to run the file using command `streamlit run <file-name.py>`
```
=== "CLI"
```bash
yolo streamlit-predict
```
This will launch the Streamlit application in your default web browser. You will see the main title, subtitle, and the sidebar with configuration options. Select your desired YOLO11 model, set the confidence and NMS thresholds, and click the "Start" button to begin the real-time object detection.
You can optionally supply a specific model in Python:

36
docs/en/guides/workouts-monitoring.md
Unescape View File

@ -60,40 +60,18 @@ Monitoring workouts through pose estimation with [Ultralytics YOLO11](https://gi
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
gym = solutions.AIGym(
model="yolo11n-pose.pt",
show=True,
kpts=[6, 8, 10],
)
while cap.isOpened():
success, im0 = cap.read()
if not success:
print("Video frame is empty or video processing has been successfully completed.")
break
im0 = gym.monitor(im0)
cv2.destroyAllWindows()
```
=== "Workouts Monitoring with Save Output"
```python
import cv2
from ultralytics import solutions
cap = cv2.VideoCapture("path/to/video/file.mp4")
assert cap.isOpened(), "Error reading video file"
w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
# Video writer
video_writer = cv2.VideoWriter("workouts.avi", cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
# Init AIGym
gym = solutions.AIGym(
show=True,
kpts=[6, 8, 10],
show=True, # Display the frame
kpts=[6, 8, 10], # keypoints index of person for monitoring specific exercise, by default it's for pushup
model="yolo11n-pose.pt", # Path to the YOLO11 pose estimation model file
# line_width=2, # Adjust the line width for bounding boxes and text display
)
# Process video
while cap.isOpened():
success, im0 = cap.read()
if not success:

2
docs/en/integrations/index.md
Unescape View File

@ -61,6 +61,8 @@ Welcome to the Ultralytics Integrations page! This page provides an overview of
- [Albumentations](albumentations.md): Enhance your Ultralytics models with powerful image augmentations to improve model robustness and generalization.
- [SONY IMX500](sony-imx500.md): Optimize and deploy [Ultralytics YOLOv8](https://docs.ultralytics.com/models/yolov8/) models on Raspberry Pi AI Cameras with the IMX500 sensor for fast, low-power performance.
## Deployment Integrations
- [CoreML](coreml.md): CoreML, developed by [Apple](https://www.apple.com/), is a framework designed for efficiently integrating machine learning models into applications across iOS, macOS, watchOS, and tvOS, using Apple's hardware for effective and secure [model deployment](https://www.ultralytics.com/glossary/model-deployment).

2
docs/en/integrations/sony-imx500.md
Unescape View File

@ -4,7 +4,7 @@ description: Learn to export Ultralytics YOLOv8 models to Sony's IMX500 format t
keywords: Sony, IMX500, IMX 500, Atrios, MCT, model export, quantization, pruning, deep learning optimization, Raspberry Pi AI Camera, edge AI, PyTorch, IMX
---
# IMX500 Export for Ultralytics YOLOv8
# Sony IMX500 Export for Ultralytics YOLOv8
This guide covers exporting and deploying Ultralytics YOLOv8 models to Raspberry Pi AI Cameras that feature the Sony IMX500 sensor.

1
docs/en/macros/export-table.md
Unescape View File

@ -14,3 +14,4 @@
| [PaddlePaddle](../integrations/paddlepaddle.md) | `paddle` | `{{ model_name or "yolo11n" }}_paddle_model/` | ✅ | `imgsz`, `batch` |
| [MNN](../integrations/mnn.md) | `mnn` | `{{ model_name or "yolo11n" }}.mnn` | ✅ | `imgsz`, `batch`, `int8`, `half` |
| [NCNN](../integrations/ncnn.md) | `ncnn` | `{{ model_name or "yolo11n" }}_ncnn_model/` | ✅ | `imgsz`, `half`, `batch` |
| [IMX500](../integrations/sony-imx500.md) | `imx` | `{{ model_name or "yolo11n" }}_imx_model/` | ✅ | `imgsz`, `int8` |

4
docs/en/reference/utils/torch_utils.md
Unescape View File

@ -19,6 +19,10 @@ keywords: Ultralytics, torch utils, model optimization, device selection, infere
<br><br><hr><br>
## ::: ultralytics.utils.torch_utils.FXModel
<br><br><hr><br>
## ::: ultralytics.utils.torch_utils.torch_distributed_zero_first
<br><br><hr><br>

3
docs/mkdocs_github_authors.yaml
Unescape View File

@ -109,6 +109,9 @@ chr043416@gmail.com:
davis.justin@mssm.org:
avatar: https://avatars.githubusercontent.com/u/23462437?v=4
username: justincdavis
francesco.mttl@gmail.com:
avatar: https://avatars.githubusercontent.com/u/3855193?v=4
username: ambitious-octopus
glenn.jocher@ultralytics.com:
avatar: https://avatars.githubusercontent.com/u/26833433?v=4
username: glenn-jocher

4
mkdocs.yml
Unescape View File

@ -412,12 +412,14 @@ nav:
- TF.js: integrations/tfjs.md
- TFLite: integrations/tflite.md
- TFLite Edge TPU: integrations/edge-tpu.md
- Sony IMX500: integrations/sony-imx500.md
- TensorBoard: integrations/tensorboard.md
- TensorRT: integrations/tensorrt.md
- TorchScript: integrations/torchscript.md
- VS Code: integrations/vscode.md
- Weights & Biases: integrations/weights-biases.md
- Albumentations: integrations/albumentations.md
- SONY IMX500: integrations/sony-imx500.md
- HUB:
- hub/index.md
- Web:
@ -559,7 +561,6 @@ nav:
- utils: reference/nn/modules/utils.md
- tasks: reference/nn/tasks.md
- solutions:
- solutions: reference/solutions/solutions.md
- ai_gym: reference/solutions/ai_gym.md
- analytics: reference/solutions/analytics.md
- distance_calculation: reference/solutions/distance_calculation.md
@ -567,6 +568,7 @@ nav:
- object_counter: reference/solutions/object_counter.md
- parking_management: reference/solutions/parking_management.md
- queue_management: reference/solutions/queue_management.md
- solutions: reference/solutions/solutions.md
- speed_estimation: reference/solutions/speed_estimation.md
- streamlit_inference: reference/solutions/streamlit_inference.md
- trackers:

9
tests/test_exports.py
Unescape View File

@ -205,3 +205,12 @@ def test_export_ncnn():
"""Test YOLO exports to NCNN format."""
file = YOLO(MODEL).export(format="ncnn", imgsz=32)
YOLO(file)(SOURCE, imgsz=32) # exported model inference
@pytest.mark.skipif(True, reason="Test disabled as keras and tensorflow version conflicts with tflite export.")
@pytest.mark.skipif(not LINUX or MACOS, reason="Skipping test on Windows and Macos")
def test_export_imx():
"""Test YOLOv8n exports to IMX format."""
model = YOLO("yolov8n.pt")
file = model.export(format="imx", imgsz=32)
YOLO(file)(SOURCE, imgsz=32)

2
ultralytics/__init__.py
Unescape View File

@ -1,6 +1,6 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
__version__ = "8.3.28"
__version__ = "8.3.29"
import os

176
ultralytics/engine/exporter.py
Unescape View File

@ -18,6 +18,7 @@ TensorFlow.js | `tfjs` | yolo11n_web_model/
PaddlePaddle | `paddle` | yolo11n_paddle_model/
MNN | `mnn` | yolo11n.mnn
NCNN | `ncnn` | yolo11n_ncnn_model/
IMX | `imx` | yolo11n_imx_model/
Requirements:
$ pip install "ultralytics[export]"
@ -44,6 +45,7 @@ Inference:
yolo11n_paddle_model # PaddlePaddle
yolo11n.mnn # MNN
yolo11n_ncnn_model # NCNN
yolo11n_imx_model # IMX
TensorFlow.js:
$ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example
@ -94,7 +96,7 @@ from ultralytics.utils.checks import check_imgsz, check_is_path_safe, check_requ
from ultralytics.utils.downloads import attempt_download_asset, get_github_assets, safe_download
from ultralytics.utils.files import file_size, spaces_in_path
from ultralytics.utils.ops import Profile
from ultralytics.utils.torch_utils import TORCH_1_13, get_latest_opset, select_device, smart_inference_mode
from ultralytics.utils.torch_utils import TORCH_1_13, get_latest_opset, select_device
def export_formats():
@ -114,6 +116,7 @@ def export_formats():
["PaddlePaddle", "paddle", "_paddle_model", True, True],
["MNN", "mnn", ".mnn", True, True],
["NCNN", "ncnn", "_ncnn_model", True, True],
["IMX", "imx", "_imx_model", True, True],
]
return dict(zip(["Format", "Argument", "Suffix", "CPU", "GPU"], zip(*x)))
@ -171,7 +174,6 @@ class Exporter:
self.callbacks = _callbacks or callbacks.get_default_callbacks()
callbacks.add_integration_callbacks(self)
@smart_inference_mode()
def __call__(self, model=None) -> str:
"""Returns list of exported files/dirs after running callbacks."""
self.run_callbacks("on_export_start")
@ -194,9 +196,22 @@ class Exporter:
flags = [x == fmt for x in fmts]
if sum(flags) != 1:
raise ValueError(f"Invalid export format='{fmt}'. Valid formats are {fmts}")
jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, mnn, ncnn = (
flags # export booleans
)
(
jit,
onnx,
xml,
engine,
coreml,
saved_model,
pb,
tflite,
edgetpu,
tfjs,
paddle,
mnn,
ncnn,
imx,
) = flags # export booleans
is_tf_format = any((saved_model, pb, tflite, edgetpu, tfjs))
# Device
@ -210,6 +225,9 @@ class Exporter:
self.device = select_device("cpu" if self.args.device is None else self.args.device)
# Checks
if imx and not self.args.int8:
LOGGER.warning("WARNING ⚠️ IMX only supports int8 export, setting int8=True.")
self.args.int8 = True
if not hasattr(model, "names"):
model.names = default_class_names()
model.names = check_class_names(model.names)
@ -249,6 +267,7 @@ class Exporter:
)
if mnn and (IS_RASPBERRYPI or IS_JETSON):
raise SystemError("MNN export not supported on Raspberry Pi and NVIDIA Jetson")
# Input
im = torch.zeros(self.args.batch, 3, *self.imgsz).to(self.device)
file = Path(
@ -264,6 +283,11 @@ class Exporter:
model.eval()
model.float()
model = model.fuse()
if imx:
from ultralytics.utils.torch_utils import FXModel
model = FXModel(model)
for m in model.modules():
if isinstance(m, (Detect, RTDETRDecoder)): # includes all Detect subclasses like Segment, Pose, OBB
m.dynamic = self.args.dynamic
@ -273,6 +297,15 @@ class Exporter:
elif isinstance(m, C2f) and not is_tf_format:
# EdgeTPU does not support FlexSplitV while split provides cleaner ONNX graph
m.forward = m.forward_split
if isinstance(m, Detect) and imx:
from ultralytics.utils.tal import make_anchors
m.anchors, m.strides = (
x.transpose(0, 1)
for x in make_anchors(
torch.cat([s / m.stride.unsqueeze(-1) for s in self.imgsz], dim=1), m.stride, 0.5
)
)
y = None
for _ in range(2):
@ -347,6 +380,8 @@ class Exporter:
f[11], _ = self.export_mnn()
if ncnn: # NCNN
f[12], _ = self.export_ncnn()
if imx:
f[13], _ = self.export_imx()
# Finish
f = [str(x) for x in f if x] # filter out '' and None
@ -1068,6 +1103,137 @@ class Exporter:
yaml_save(Path(f) / "metadata.yaml", self.metadata) # add metadata.yaml
return f, None
@try_export
def export_imx(self, prefix=colorstr("IMX:")):
"""YOLO IMX export."""
gptq = False
assert LINUX, "export only supported on Linux. See https://developer.aitrios.sony-semicon.com/en/raspberrypi-ai-camera/documentation/imx500-converter"
if getattr(self.model, "end2end", False):
raise ValueError("IMX export is not supported for end2end models.")
if "C2f" not in self.model.__str__():
raise ValueError("IMX export is only supported for YOLOv8 detection models")
check_requirements(("model-compression-toolkit==2.1.1", "sony-custom-layers==0.2.0", "tensorflow==2.12.0"))
check_requirements("imx500-converter[pt]==3.14.3") # Separate requirements for imx500-converter
import model_compression_toolkit as mct
import onnx
from sony_custom_layers.pytorch.object_detection.nms import multiclass_nms
try:
out = subprocess.run(
["java", "--version"], check=True, capture_output=True
) # Java 17 is required for imx500-converter
if "openjdk 17" not in str(out.stdout):
raise FileNotFoundError
except FileNotFoundError:
subprocess.run(["sudo", "apt", "install", "-y", "openjdk-17-jdk", "openjdk-17-jre"], check=True)
def representative_dataset_gen(dataloader=self.get_int8_calibration_dataloader(prefix)):
for batch in dataloader:
img = batch["img"]
img = img / 255.0
yield [img]
tpc = mct.get_target_platform_capabilities(
fw_name="pytorch", target_platform_name="imx500", target_platform_version="v1"
)
config = mct.core.CoreConfig(
mixed_precision_config=mct.core.MixedPrecisionQuantizationConfig(num_of_images=10),
quantization_config=mct.core.QuantizationConfig(concat_threshold_update=True),
)
resource_utilization = mct.core.ResourceUtilization(weights_memory=3146176 * 0.76)
quant_model = (
mct.gptq.pytorch_gradient_post_training_quantization( # Perform Gradient-Based Post Training Quantization
model=self.model,
representative_data_gen=representative_dataset_gen,
target_resource_utilization=resource_utilization,
gptq_config=mct.gptq.get_pytorch_gptq_config(n_epochs=1000, use_hessian_based_weights=False),
core_config=config,
target_platform_capabilities=tpc,
)[0]
if gptq
else mct.ptq.pytorch_post_training_quantization( # Perform post training quantization
in_module=self.model,
representative_data_gen=representative_dataset_gen,
target_resource_utilization=resource_utilization,
core_config=config,
target_platform_capabilities=tpc,
)[0]
)
class NMSWrapper(torch.nn.Module):
def __init__(
self,
model: torch.nn.Module,
score_threshold: float = 0.001,
iou_threshold: float = 0.7,
max_detections: int = 300,
):
"""
Wrapping PyTorch Module with multiclass_nms layer from sony_custom_layers.
Args:
model (nn.Module): Model instance.
score_threshold (float): Score threshold for non-maximum suppression.
iou_threshold (float): Intersection over union threshold for non-maximum suppression.
max_detections (float): The number of detections to return.
"""
super().__init__()
self.model = model
self.score_threshold = score_threshold
self.iou_threshold = iou_threshold
self.max_detections = max_detections
def forward(self, images):
# model inference
outputs = self.model(images)
boxes = outputs[0]
scores = outputs[1]
nms = multiclass_nms(
boxes=boxes,
scores=scores,
score_threshold=self.score_threshold,
iou_threshold=self.iou_threshold,
max_detections=self.max_detections,
)
return nms
quant_model = NMSWrapper(
model=quant_model,
score_threshold=self.args.conf or 0.001,
iou_threshold=self.args.iou,
max_detections=self.args.max_det,
).to(self.device)
f = Path(str(self.file).replace(self.file.suffix, "_imx_model"))
f.mkdir(exist_ok=True)
onnx_model = f / Path(str(self.file).replace(self.file.suffix, "_imx.onnx")) # js dir
mct.exporter.pytorch_export_model(
model=quant_model, save_model_path=onnx_model, repr_dataset=representative_dataset_gen
)
model_onnx = onnx.load(onnx_model) # load onnx model
for k, v in self.metadata.items():
meta = model_onnx.metadata_props.add()
meta.key, meta.value = k, str(v)
onnx.save(model_onnx, onnx_model)
subprocess.run(
["imxconv-pt", "-i", str(onnx_model), "-o", str(f), "--no-input-persistency", "--overwrite-output"],
check=True,
)
# Needed for imx models.
with open(f / "labels.txt", "w") as file:
file.writelines([f"{name}\n" for _, name in self.model.names.items()])
return f, None
def _add_tflite_metadata(self, file):
"""Add metadata to *.tflite models per https://www.tensorflow.org/lite/models/convert/metadata."""
import flatbuffers

4
ultralytics/models/yolo/detect/val.py
Unescape View File

@ -155,8 +155,8 @@ class DetectionValidator(BaseValidator):
# Evaluate
if nl:
stat["tp"] = self._process_batch(predn, bbox, cls)
if self.args.plots:
self.confusion_matrix.process_batch(predn, bbox, cls)
if self.args.plots:
self.confusion_matrix.process_batch(predn, bbox, cls)
for k in self.stats.keys():
self.stats[k].append(stat[k])

4
ultralytics/models/yolo/pose/val.py
Unescape View File

@ -138,8 +138,8 @@ class PoseValidator(DetectionValidator):
if nl:
stat["tp"] = self._process_batch(predn, bbox, cls)
stat["tp_p"] = self._process_batch(predn, bbox, cls, pred_kpts, pbatch["kpts"])
if self.args.plots:
self.confusion_matrix.process_batch(predn, bbox, cls)
if self.args.plots:
self.confusion_matrix.process_batch(predn, bbox, cls)
for k in self.stats.keys():
self.stats[k].append(stat[k])

4
ultralytics/models/yolo/segment/val.py
Unescape View File

@ -135,8 +135,8 @@ class SegmentationValidator(DetectionValidator):
stat["tp_m"] = self._process_batch(
predn, bbox, cls, pred_masks, gt_masks, self.args.overlap_mask, masks=True
)
if self.args.plots:
self.confusion_matrix.process_batch(predn, bbox, cls)
if self.args.plots:
self.confusion_matrix.process_batch(predn, bbox, cls)
for k in self.stats.keys():
self.stats[k].append(stat[k])

27
ultralytics/nn/autobackend.py
Unescape View File

@ -123,6 +123,7 @@ class AutoBackend(nn.Module):
paddle,
mnn,
ncnn,
imx,
triton,
) = self._model_type(w)
fp16 &= pt or jit or onnx or xml or engine or nn_module or triton # FP16
@ -182,8 +183,8 @@ class AutoBackend(nn.Module):
check_requirements("opencv-python>=4.5.4")
net = cv2.dnn.readNetFromONNX(w)
# ONNX Runtime
elif onnx:
# ONNX Runtime and IMX
elif onnx or imx:
LOGGER.info(f"Loading {w} for ONNX Runtime inference...")
check_requirements(("onnx", "onnxruntime-gpu" if cuda else "onnxruntime"))
if IS_RASPBERRYPI or IS_JETSON:
@ -199,7 +200,22 @@ class AutoBackend(nn.Module):
device = torch.device("cpu")
cuda = False
LOGGER.info(f"Preferring ONNX Runtime {providers[0]}")
session = onnxruntime.InferenceSession(w, providers=providers)
if onnx:
session = onnxruntime.InferenceSession(w, providers=providers)
else:
check_requirements(
["model-compression-toolkit==2.1.1", "sony-custom-layers[torch]==0.2.0", "onnxruntime-extensions"]
)
w = next(Path(w).glob("*.onnx"))
LOGGER.info(f"Loading {w} for ONNX IMX inference...")
import mct_quantizers as mctq
from sony_custom_layers.pytorch.object_detection import nms_ort # noqa
session = onnxruntime.InferenceSession(
w, mctq.get_ort_session_options(), providers=["CPUExecutionProvider"]
)
task = "detect"
output_names = [x.name for x in session.get_outputs()]
metadata = session.get_modelmeta().custom_metadata_map
dynamic = isinstance(session.get_outputs()[0].shape[0], str)
@ -520,7 +536,7 @@ class AutoBackend(nn.Module):
y = self.net.forward()
# ONNX Runtime
elif self.onnx:
elif self.onnx or self.imx:
if self.dynamic:
im = im.cpu().numpy() # torch to numpy
y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im})
@ -537,6 +553,9 @@ class AutoBackend(nn.Module):
)
self.session.run_with_iobinding(self.io)
y = self.bindings
if self.imx:
# boxes, conf, cls
y = np.concatenate([y[0], y[1][:, :, None], y[2][:, :, None]], axis=-1)
# OpenVINO
elif self.xml:

3
ultralytics/nn/modules/block.py
Unescape View File

@ -240,7 +240,8 @@ class C2f(nn.Module):
def forward_split(self, x):
"""Forward pass using split() instead of chunk()."""
y = list(self.cv1(x).split((self.c, self.c), 1))
y = self.cv1(x).split((self.c, self.c), 1)
y = [y[0], y[1]]
y.extend(m(y[-1]) for m in self.m)
return self.cv2(torch.cat(y, 1))

12
ultralytics/nn/modules/head.py
Unescape View File

@ -23,6 +23,7 @@ class Detect(nn.Module):
dynamic = False # force grid reconstruction
export = False # export mode
format = None # export format
end2end = False # end2end
max_det = 300 # max_det
shape = None
@ -101,7 +102,7 @@ class Detect(nn.Module):
# Inference path
shape = x[0].shape # BCHW
x_cat = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2)
if self.dynamic or self.shape != shape:
if self.format != "imx" and (self.dynamic or self.shape != shape):
self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
self.shape = shape
@ -119,6 +120,11 @@ class Detect(nn.Module):
grid_size = torch.tensor([grid_w, grid_h, grid_w, grid_h], device=box.device).reshape(1, 4, 1)
norm = self.strides / (self.stride[0] * grid_size)
dbox = self.decode_bboxes(self.dfl(box) * norm, self.anchors.unsqueeze(0) * norm[:, :2])
elif self.export and self.format == "imx":
dbox = self.decode_bboxes(
self.dfl(box) * self.strides, self.anchors.unsqueeze(0) * self.strides, xywh=False
)
return dbox.transpose(1, 2), cls.sigmoid().permute(0, 2, 1)
else:
dbox = self.decode_bboxes(self.dfl(box), self.anchors.unsqueeze(0)) * self.strides
@ -137,9 +143,9 @@ class Detect(nn.Module):
a[-1].bias.data[:] = 1.0 # box
b[-1].bias.data[: m.nc] = math.log(5 / m.nc / (640 / s) ** 2) # cls (.01 objects, 80 classes, 640 img)
def decode_bboxes(self, bboxes, anchors):
def decode_bboxes(self, bboxes, anchors, xywh=True):
"""Decode bounding boxes."""
return dist2bbox(bboxes, anchors, xywh=not self.end2end, dim=1)
return dist2bbox(bboxes, anchors, xywh=xywh and (not self.end2end), dim=1)
@staticmethod
def postprocess(preds: torch.Tensor, max_det: int, nc: int = 80):

5
ultralytics/utils/benchmarks.py
Unescape View File

@ -118,6 +118,11 @@ def benchmark(
assert not IS_JETSON, "MNN export not supported on NVIDIA Jetson"
if i == 13: # NCNN
assert not isinstance(model, YOLOWorld), "YOLOWorldv2 NCNN exports not supported yet"
if i == 14: # IMX
assert not is_end2end
assert not isinstance(model, YOLOWorld), "YOLOWorldv2 IMX exports not supported"
assert model.task == "detect", "IMX only supported for detection task"
assert "C2f" in model.__str__(), "IMX only supported for YOLOv8"
if "cpu" in device.type:
assert cpu, "inference not supported on CPU"
if "cuda" in device.type:

2
ultralytics/utils/tal.py
Unescape View File

@ -306,7 +306,7 @@ def make_anchors(feats, strides, grid_cell_offset=0.5):
assert feats is not None
dtype, device = feats[0].dtype, feats[0].device
for i, stride in enumerate(strides):
_, _, h, w = feats[i].shape
h, w = feats[i].shape[2:] if isinstance(feats, list) else (int(feats[i][0]), int(feats[i][1]))
sx = torch.arange(end=w, device=device, dtype=dtype) + grid_cell_offset # shift x
sy = torch.arange(end=h, device=device, dtype=dtype) + grid_cell_offset # shift y
sy, sx = torch.meshgrid(sy, sx, indexing="ij") if TORCH_1_10 else torch.meshgrid(sy, sx)

45
ultralytics/utils/torch_utils.py
Unescape View File

@ -730,3 +730,48 @@ class EarlyStopping:
f"i.e. `patience=300` or use `patience=0` to disable EarlyStopping."
)
return stop
class FXModel(nn.Module):
"""
A custom model class for torch.fx compatibility.
This class extends `torch.nn.Module` and is designed to ensure compatibility with torch.fx for tracing and graph manipulation.
It copies attributes from an existing model and explicitly sets the model attribute to ensure proper copying.
Args:
model (torch.nn.Module): The original model to wrap for torch.fx compatibility.
"""
def __init__(self, model):
"""
Initialize the FXModel.
Args:
model (torch.nn.Module): The original model to wrap for torch.fx compatibility.
"""
super().__init__()
copy_attr(self, model)
# Explicitly set `model` since `copy_attr` somehow does not copy it.
self.model = model.model
def forward(self, x):
"""
Forward pass through the model.
This method performs the forward pass through the model, handling the dependencies between layers and saving intermediate outputs.
Args:
x (torch.Tensor): The input tensor to the model.
Returns:
(torch.Tensor): The output tensor from the model.
"""
y = [] # outputs
for m in self.model:
if m.f != -1: # if not from previous layer
# from earlier layers
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]
x = m(x) # run
y.append(x) # save output
return x

Write Preview
Loading…
Cancel
Save