mongeoroo / relevance-cam Goto Github PK
View Code? Open in Web Editor NEWThe official code of Relevance-CAM
The official code of Relevance-CAM
Hi @mongeoroo,
Thanks for the incredible work – the results in the paper look great!
I am looking to use Relevance-CAM with my custom dataset. I would need to train ResNet50 (initialized with ImageNet) on my custom dataset first. Can I use the resnet50 model from your repo? Will I need to write the training script? How do I approach this? I think the Multi_CAM.py shows only the inference examples. Thank you!
I do thank you so much to get your paper with github code because it helps me a lot to my study. It is ok to train with my custom dataset with other layers (2, 3 and 4) but not its layer 1. Please help me how I should fix it.
Thanks for you great job! However, I have a question. When I use vgg19 rather than vgg16, there is an error shown below. It seems that something is wrong, the code path of which is "./modules/layers.py". Can it be used in vgg19 or we need to do some change to make it in vgg19. By the way, can it be used with transformer network? I am looking forward to your reply!
RuntimeError: The size of tensor a (7) must match the size of tensor b (14) at non-singleton dimension 3
Hello author, I use the layer1 layer of resnet50 to operate, but an error is reported, what is the reason?
R_CAM, output = model(in_tensor, args.target_layer, [args.target_class])
ValueError: not enough values to unpack (expected 2, got 1)
Hi! Thank you for the great work!
In the read.me you mentioned that the script supports vgg inference also, but it seems like it does not work for vgg16 (target layer index out of range, size mismatches in relprop...). Could you please provide working scripts for the vgg architecture.
Hi, thanks so much for your work on this - the results look fantastic!
I was interested in trying out the Average Drop and Average Increase evaluation over the 2000 ImageNet validation images, but couldn't find the code for those metrics. Is that available somewhere?
Thank you for your excellent work. Can you provide Sanity check code?
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 is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
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.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.