Comments (3)
Okay thanks. This is pretty much what I was doing and just wanted to make sure I was on the right track and get your insight.
from flashtorch.
I think you can hack the script at backprob.py to generate the target vector you are looking for:
def calculate_gradients(self,
input_,
target_class=None,
take_max=False,
guided=False,
use_gpu=False):
(...some unrelated code...)
target = torch.FloatTensor(1, output.shape[-1]).zero_()
(...some unrelated code...)
target[0][top_class] = 1
and change that to something like:
def calculate_gradients(self,
input_,
target_vector=None, <--- your target vector goes here
take_max=False,
guided=False,
use_gpu=False):
if isinstance(target_class, torch.tensor):
target = target_vector # in this case, you have to generate the target-vector yourself.
else:
(continue as before)
Then you also have to change the respective parent functions that call this function such that you can pass your own target vector, but this should be easy.
In that way you can set a arbitrary target vector, which can also contain multiple "1"-entries. This might achieve what you are looking for. I am not deep enough in the math behind saliency maps though. i hope @MisaOgura can comment on this.
from flashtorch.
Hi @rrags, apologies for the late reply and thanks @dnns92 for jumping in.
The current behaviour is that if target_class
and top_class
are different, it defaults to visualise the gradients w.r.t the top_class
(see here). The simplest hack to achieve what you want to do would be to change backprop.py#L117 from target[0][top_class] = 1
to target[0][target_class] = 1
.
Allowing users to have more control over which class to visualise, is something I have been wanting to revisit - please expect an update on this.
@dnns92 The modification suggested would make sense when target_vector
contains only one value of 1 (i.e. one target class). When there is more than one target class, .backward()
would calculate gradients w.r.t multiple target classes at once, and you will only get one set of gradients out of the graph. This probably wouldn't be the desired behaviour when creating per-class saliency map, so multiple targets would need to be handled differently. Hope this helps.
from flashtorch.
Related Issues (20)
- python2 or python3? HOT 1
- NOT WORKING FOR CONV3D HOT 1
- Custom Pytorch Model error HOT 2
- [BUG] Backprop.calculate_gradients gives rise to " AttributeError: 'NoneType' object has no attribute 'shape' " error HOT 3
- How can I use FlashTorch to see what the EfficientNet learn? HOT 1
- [REQUEST] HOT 3
- Can I use my own model? HOT 3
- 3D images HOT 1
- use of custom model throws an error HOT 2
- [REQUEST]Support torch detection model?
- When I test my demo.jpg[BUG]
- [BUG] Colab demo for saliency maps: Gradient images are blank HOT 2
- Google Colab version not running [BUG] HOT 7
- Backprop is not working HOT 1
- RuntimeError HOT 2
- [REQUEST] calculate gradients for customized inputs
- Saliency map for a group of images
- [BUG]
- [Q] Does this support Vision Transformers (ViT)?
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 flashtorch.