Comments (3)
Hi @Ahsanr312 thank you for the suggestion.
Actually, you can do any of the options right now.
This repository is more about how to train it (how we trained it) than "generalizable" results.
We wanted to share our work on this competition with the world.
One thing to keep in mind is that this was built for buildings so perhaps you should use a different dataset than MS COCO (cityscape is a good one I believe).
Good luck with fine-tuning!
from open-solution-mapping-challenge.
I have looked for steps to fine-tune the model but couldn't fine anything.
Can you help me with it? @jakubczakon
from open-solution-mapping-challenge.
@Ahsanr312 Were you able to figure out how to tune the model?
I prepared the training directory as per the Readme with my own images+annotations but get a DecodeError running the train command.
Edit: that error is fixed by upgrading neptune client, however I still struggle to produce new tuned weights (no errors but I don't see the output from training).
from open-solution-mapping-challenge.
Related Issues (20)
- File b'data/meta/metadata.csv' does not exist: b'data/meta/metadata.csv' HOT 1
- AttributeError: 'StdOutWithUpload' object has no attribute 'fileno' HOT 1
- where to get Original Dataset? CrowdAi had been shut down HOT 3
- transformer aren't generate HOT 2
- Why droping small masks on the edge works HOT 1
- Dataset cant' be reachable anymore HOT 4
- Using model weights on own dataset HOT 26
- evaluate:valid data is none?
- Confused about generating target masks HOT 5
- Error when running Evaluate : axis 1 is out of bounds for array of dimension 0 HOT 21
- Use the Mapping-Challenge-weights to predict on my own data HOT 17
- KeyError: 'inference' when applying solution weight to my data HOT 11
- Transfer learning using the available weights
- FileNotFoundError: [Errno 2] No such file or directory: 'data/meta\\masks_overlayed_eroded_0_dilated_0\\train\\masks\\000000150992 HOT 3
- Pip subprocess error related to pycocotools when running 'source Makefile' HOT 2
- Adjusting 'Confidence' when Predicting on New Data
- The runtime encountered a problem HOT 1
- Segment Mask not visible on custom data
- Model weights for the winning solution is not available!
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 open-solution-mapping-challenge.