Comments (8)
I can confirm that this change makes it work perfectly on all my tools, not just the needle holder!
from cnos.
Can you share the results here (+input images, renderings of CAD model)? In the custom inference script, I set confidence_score=0.5 by default. It may be helpful to use a lower threshold to visualize more detections.
from cnos.
From what you said “close-ups of the objects, the single object only, a white background, and no occlusion” but there is still no segmentation on objects are so weird since SAM or FastSAM should segment everything. You can reduce confidence_threshold to see all detections first and make sure that there are at least some masks on objects.
from cnos.
Thank you for your very fast reply!
So here is an example where it worked best for me. As you can see, it still does not segment the entire object:
When I do it for another tool, I only get the background for some reason:
I am confused because as soon as I use a CAD model and RGB image from one of the example datasets it segments it absolutely perfectly despite the object being far away from the camera in an extremely cluttered space. Lowering the confidence threshold did not help by the way. I appreciate your help!
from cnos.
CNOS should work on this example. Can you share the RGB image + CAD model so that I can try it?
from cnos.
Sure! Here are two example images and the CAD model of the needle holder:
https://drive.google.com/drive/folders/1pn7letIZNACC7D1u-pwCyPvzlMBdfHJ3?usp=drive_link
from cnos.
I added stability_score_thresh parameter in inference_custom.py script so that the segmentation model can output more unstable masks (it usually happens for very tiny objects like yours). Here is the result after fine-tuning this parameter of SAM:
Here are the commands to reproduce the results:
export CAD_PATH=./media/demo2/NeedleHolder.ply
export RGB_PATH=./media/demo2/ThreeToolTest.png
export OUTPUT_DIR=./tmp/custom_dataset
python -m src.scripts.inference_custom --template_dir $OUTPUT_DIR --rgb_path $RGB_PATH --stability_score_thresh 0.5
I shared your example in this repo so that new users can be aware of it. Please let me know if you don't want to share this example. Thanks!
from cnos.
Thank you so much for he very quick response and great solution! Yes I am okay with this being used as an example!
from cnos.
Related Issues (20)
- Any standard for scaling CAD models? HOT 2
- Problems with detecting multi-color objects (?) HOT 1
- How to use this project? What are parameters of train ? HOT 2
- precomputed results on YCBV HOT 2
- Pixel to point correspondances with renderer HOT 1
- Installation of ultralytics HOT 1
- Segmentation evaluation using bop_toolkit HOT 2
- CAD-object free results HOT 3
- Why is the paper's reported result different from that in the BOP leaderboard? HOT 3
- size mismatch for pos_embed HOT 3
- Using FastSAM on custom dataset inference HOT 6
- Poor performance in a object with two colors.
- Multi object segmentation support HOT 2
- Help Needed: Improving Prediction Accuracy on Custom Dataset HOT 1
- Why are the results in the paper different from those in the baseline of the BOP? HOT 1
- pre-computed segmentation is not complete on the YCBV dataset HOT 2
- Running custom inference on multiple GPUs HOT 2
- Rendering templates HOT 1
- DINOv2 for image feature extraction HOT 2
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 cnos.