Comments (4)
In many cases the model should do that automatically but there are two effects working against it:
- In COCO groups of objects are labelled as "crowds" and detected with a single box
- The base implementation is from 2017 and the performance is accordingly. A lot has happened since but this cannot easily be transferred to this rather "old" implementation.
from siamese-mask-rcnn.
Thank you for the insight!
For the first point, it sounds like the performance will improve If I retrain the coco weight on my custom dataset where instances of a group are labeled separately.
For the second point, is there any "newer" implementation on few-shot instance segmentation that you can point to? Or is there any change you would like to make to this impelemtatation?
from siamese-mask-rcnn.
We will likely release a new implementation of this at some point however we have not set any date yet.
from siamese-mask-rcnn.
Thank you, looking forward to the update!
from siamese-mask-rcnn.
Related Issues (20)
- How to use the pretrained weights? HOT 5
- plz help HOT 5
- shape error HOT 1
- Problem with mask predictions HOT 17
- How to design the loss function? HOT 4
- Multiple runs on training not evaluation HOT 2
- typo HOT 1
- Small typo HOT 1
- Dimension dismatch error when evaluate the retrained model for COCO, from epoch 2 HOT 2
- Problem with custom dataset HOT 8
- Performance is not as good as Mask RCNN when training on a small custom dataset HOT 1
- Modifications for training on custom dataset
- Test.ipynb
- One-Shot Detection - input_target shape Error HOT 3
- TypeError: unhashable type: 'ListWrapper' when try to train model HOT 1
- issue re-running
- Support for Tensorflow 2.4+ HOT 1
- Loading weights
- Why are model loading and inference times so slow?
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 siamese-mask-rcnn.