Comments (4)
The class score is the probability at the index of the gt class of that crop/image. It's not the argmax index. We use this score as an indicator of how much categorized semantic information the input crop contains.
from contrastivecrop.
Hi, Khoa-NT
Thank you for your interest and your questions.
- Sorry for the confusion. By class score we mean the class probability after softmax (a real number within (0, 1)). We get the class score by inputting a crop to a standard ResNet50 trained with ImageNet labels. We didn't put it in the code since it is not the main experiment.
- The linear classifier learning rate is adapted from MoCo. The linear cls lr is 30.0 in MoCo. We did a little parameter tuning to make it suitable for all models on small datasets.
- It's a mistake that we did not remove the latter half sentence. Please ignore that.
from contrastivecrop.
Hi @xyupeng,
Thank you for your details and congratulation on the Oral paper.
In 1)
Sorry for the confusion. By class score we mean the class probability after softmax (a real number within (0, 1)). We get the class score by inputting a crop to a standard ResNet50 trained with ImageNet labels. We didn't put it in the code since it is not the main experiment.
If I understand correctly, the class score
is the argmax
class probability of the prediction (after softmax).
Did you check the predicted class
, which is corresponding with that class probability
, is the same as the GT?
I just wonder, if the predicted class
was wrong, then maybe the semantic information is not useful.
from contrastivecrop.
Thank you for clarifying. I got it.
from contrastivecrop.
Related Issues (20)
- ask about the downstream application HOT 2
- some question about bbox_update HOT 4
- question HOT 3
- datasets HOT 2
- A little confusion about training HOT 4
- Some questions about the running process of contrastive cropping HOT 2
- The cropping may have some issues HOT 4
- Question about the cropping candidate regions
- A question about pseudocode HOT 5
- More models and datasets coming soon? HOT 2
- An implementation detail to consult HOT 1
- A HOT 1
- A quesition
- 请问TypeError: forward() missing 1 required positional argument: 'box',这个box参数具体我应该传什么参数 HOT 7
- 请问ContrastiveCrop的ratio的参数是多少? HOT 1
- How can I use it for downstream tasks HOT 4
- dataloader and updating the box HOT 3
- support custom dataset HOT 2
- how to use this code,thanks HOT 1
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 contrastivecrop.