Comments (4)
Hi @MatoFD,
You can use both mp_image
and mp_image2
. When providing the rgb_image
to segmentation_result = segmenter.segment(rgb_image)
, make sure you pass either mp_image
or mp_image2
. OpenCV images must be converted to a MediaPipe image first for compatibility since they are not directly supported. As for accuracy-related queries, we currently don't have metrics available for measuring segmentation accuracy.
Among the mp_image
and mp_image_2
, you can use both but generally we would recommend to feed RGB image to mp.Image()
since it has a better segmentation among similar color gradients, however we don't have concrete data to back this up.
Thank you!!
from mediapipe.
Thanks! It's good to have a recommended solution and it's working well for now
from mediapipe.
Hi @MatoFD,
Thank you for confirming, Can we now proceed to mark this matter as resolved and close the status?
from mediapipe.
Are you satisfied with the resolution of your issue?
Yes
No
from mediapipe.
Related Issues (20)
- Merge LoRA weights to LLM at initialization time on-device (Gemma) HOT 2
- Codepen example for the new javascript holistic Solution? HOT 1
- Problem when using mediapipes from inside a worker loaded as a module
- Converted Gemma 2b tflite generate same token
- Add support for Python 3.12 HOT 3
- How Mediapipe calculate the Z World Coordinate?
- How Mediapipe calculate the Z World Coordinate? HOT 2
- can't finish the download HOT 3
- MediaPipe GPU support in PyPi package HOT 4
- MediaPipe > 0.10.9 does not work on MacOS. HOT 3
- "Unsupported ImageFrame Format" when using GPU mode HOT 4
- solutions.drawing_utils.draw_landmarks does not work on RGBA images HOT 3
- GPU pose landmarker crashes on macos after a few minutes HOT 3
- Blendshape scores and facial_transformation_matrixes in holistic model HOT 2
- Add Jetpack Compose Support HOT 1
- crash at libimagegenerator_gpu.so lib HOT 1
- Add support for latest protobuf HOT 1
- How change graph vertical_fov_degrees value with input_side_packet or other way [python] HOT 2
- Pose Landmarks model not working as expected on iOS HOT 2
- Multiple Person Pose Detection HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mediapipe.