Repository containing code to run Score-CAM algorithm available on https://arxiv.org/pdf/1910.01279v1.pdf.
License: MIT License
Repository containing code to run Score-CAM algorithm available on https://arxiv.org/pdf/1910.01279v1.pdf.
Make sure you have installed python 3.6+ and setup GPU configuration in case you have GPU available.
At the root run:
$ virtualenv env
$ source env/bin/activate
$ pip install -r requirements.txt
To run a simple example just enter python example.py on terminal. Output image will be saved at the root.
Hi,
Thank you for writing and maintaining this repo, it's a very easy to understand implementation of Score-CAM!
I have the VGG16 example working fine, and am now trying to adapt this to use my own Mask-RCNN model I have developed using this repo as a basis. I am running into an error however that I am unsure of how to fix, and was wondering if any advice could be provided?
When running
explainer = ScoreCAM()
target_size = (3456, 5184)
data = (img, None)
# Compute ScoreCAM on VGG16
image = explainer.explain(
data, model.keras_model, max_prob, target_size, _grid=False
)[0]
explainer.save(image, ".", "score_cam.png")
I am running into the following error:
ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 3 array(s), but instead got the following list of 1 arrays: [<tf.Tensor: id=10530, shape=(64, 3456, 5184, 3), dtype=float32, numpy=
array([[[[ 3.64952057e+02, 3.75305298e+02, 3.77893616e+02],
[ 1.37095261e+02, 1.40957092e+02, 1.41922562e+02],
The full stack trace can be seen here. I think the issue is that masked_images is not in the form it should be? A printout of masked_images can be seen here.
Any help is greatly appreciated!
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
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.