Comments (15)
@Trion129 sounds good, please file an issue (Try using Simnet architecture
) with the same description you put in your comment and add a reference to this issue.
from autowebcompat.
@marco-c I am planning to add, Resnet along with a siamese module as class now. Later I will proceed using pretrained models of these networks (Vgg, Resnet) and compare the accuracies. Then we will have a better picture about how to proceed (As I said in #2). If you have something specific in mind, please let me know.
from autowebcompat.
We can test pre-defined and later fine-tuned networks, but I'm concerned about the size of the input layer, because a small length could distort and skew the relevant visual representation of the bug.
from autowebcompat.
@nok Yes, I understand.
To detect differences, Y+D and N in a better way or even Y and D+N finding attention based ROIs and feeding those patches to the NN would be a good idea. Because, some times the advertisements act as blocks and also grab most of the visual representation. Although this can be considered as an add-on to improve accuracy after using pre-trained and fine tuned networks. I guess, this method can also act as a solution to the case you mentioned.
from autowebcompat.
@marco-c Do you have any specific architecture in mind? Or perhaps we could add support for attention based layers ?
from autowebcompat.
@marco-c Do you think a YOLO type network will be good to identify relevant ROIs and then classify them?
I am new to this repository, so please correct me if I am wrong.
from autowebcompat.
@marco-c Do you have any specific architecture in mind? Or perhaps we could add support for attention based layers ?
@marco-c Do you think a YOLO type network will be good to identify relevant ROIs and then classify them?
I am new to this repository, so please correct me if I am wrong.
I don't have specific ideas, we should just add whatever we think might work for us and then compare the results.
from autowebcompat.
@marco-c , Is there a documentation I can read?
I have very little knowledge of this repository ,but if we target some rendering glitches or bugs, we can use YOLO type network.
from autowebcompat.
@marco-c , Is there a documentation I can read?
I'm going to improve the documentation (#77). At the moment, the documentation is the code (which is not too much anyway).
I have very little knowledge of this repository ,but if we target some rendering glitches or bugs, we can use YOLO type network.
Sounds good to me. I have never used them myself, but it's worth testing them and comparing them with other solutions.
from autowebcompat.
@marco-c , Is there a documentation I can read?
I've updated README to add more documentation. Feel free to ask if you still have some doubts.
from autowebcompat.
@marco-c . Thanks.
from autowebcompat.
I found this architecture Simnet by Amazon Development Services, it uses a variation of Siamese network, they use 2 extra shallower models trained on downsampled images alongside the ImageNet,
The final results are better.
https://arxiv.org/pdf/1709.08761.pdf
I can try implementing this, what are your thoughts?
from autowebcompat.
@marco-c should we try out vgg19 , the microsoft resnet and other forms of inception later on ? i mean can we add them in networks.py?
from autowebcompat.
Sure, we can add them.
from autowebcompat.
Closing in favor of #194.
from autowebcompat.
Related Issues (20)
- Sort labels when saving them
- test_labels should validate all labels files
- test_labels.py is not actually testing the screenshots actually exist HOT 3
- Limit size of full page screenshot HOT 4
- Script to rename images and labels according to new convention
- Implementing Object Segmentation networks for bounding box annotations HOT 1
- Throw a meaningful error in utils.read_labels when labels.csv is empty HOT 2
- Running pretrain.py gives FileNotFoundError. HOT 4
- Try training a neural network using the responses from a DOM-based tool as features
- Try using the responses from a DOM-based tool as additional features
- Create a web-based tool to show predicted differences HOT 2
- Move the labeling tool to be web-based
- Use multiple releases of each browser
- Try using mdn/browser-compat-data to automatically label screenshot pairs
- Investigate training a model to detect regressions in a browser
- When prefilling an issue on webcompat.com, prefill as much as possible
- Add possibility to navigate to websites on demand
- Use Docker to run browsers and collect screenshots
- Train a baseline classifier HOT 12
- Out of memory error while training vgg16 and vgg19 with imagenet weights on Colab
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 autowebcompat.