Comments (7)
Yeah, this is an ONNX thing. It can be handled at an application level pretty easily (generate all models corresponding to each resolution for a dataset, pick the model based on resolution). I have added #3 enhancement covering this, closing this issue for now.
from salt.
So this is an artifact of ONNX generator helper. Did you change the resolution of the helper to generate a ONNX model of the resolution of your images? ONNX supports models for a specific resolution.
from salt.
I would appreciate a PR that can select the right ONNX model based on the resolution of the input (assuming ONNX model name format maybe -- onnx_model_<res>.onnx).
from salt.
Thank you very much for your prompt reply!I use default resolution of the input as shown blow.
Is there anything that I need to change ?
from salt.
from salt.
Yeah, change it to the resolution of your input image and try again? It should work. This is how ONNX models work, they compile the model ops to a specified resolution (and usually it works for multiples of that resolution, which your image probably isn't).
from salt.
yes it works nicely now.
this issule(facebookresearch/segment-anything#56) has reported this problem either.
from salt.
Related Issues (20)
- Failed to run, maybe caused by parsing annotations.json HOT 2
- Some GUI problems HOT 3
- TypeError: 'torch._C.Value' object is not iterable HOT 1
- remote labeling HOT 1
- Package libffi conflict
- Pink line generated from the top left corner of the image HOT 2
- Excluded regions are still getting annotated within the annotated area of the image.
- IndexError: list index out of range
- How to do box labeling mode? I left clicked just marked the mask HOT 1
- Error for low quality image HOT 2
- An error occurred when importing the labeling results into cvat, has anyone encountered it? HOT 1
- When you add it, you get this extra piece. How to solve HOT 1
- ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (8,) + inhomogeneous part. HOT 1
- Suggestion - Integrate MobileSAM into the pipeline for lightweight and faster inference HOT 1
- Error when clicking middle mouse button
- There is a problem with the reshape node exported by ONNX. I checked the network structure and found that it is only a simple reshape node. Have you encountered this problem
- check this problem, has been quite persistent, when creating a label which is partially covered under a label. Crashing Frequntly HOT 1
- Unreasonable segmentation results HOT 1
- A bug occur when I want to change the categories HOT 1
- Support for adding custom model? HOT 5
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 salt.