Comments (4)
marco-rudolph
commented on June 30, 2024
Hi,
about which dataset are we talking?
I have observed sometimes strong differences in AUROC between the feature extractors, sometimes then also between the classes of MVTec AD. So I would say it is normal.
But in this case, I think you missed this line (maxpool).
from differnet.
renqiqi
commented on June 30, 2024
Hi,
I trained the model on my own dataset which is a defect dataset.
From the experimental point of view, the results obtained by using Resnet as a feature extractor are not as good as using VGG & Alexnet.
Why use Resnet as a feature extractor to get poor results?
Thanks a lot!
from differnet.
marco-rudolph
commented on June 30, 2024
This is hard to say. One reason could be that ResNet's feature are too high level (but intermediate layers do not change the game here) or too overfitted to ImageNet. Maybe you could try EfficientNet as this paper suggests.
from differnet.
renqiqi
commented on June 30, 2024
I guess the reason is that ResNet is not suitable for the data I am researching.
I might try EfficientNet in the future.
thanks a lot!
from differnet.
Related Issues (20)
- How to test? HOT 1
- Few-shots HOT 1
- when set grad_map_viz to be True, I got a mistake: rotate() got an unexpected keyword argument 'reshape' HOT 6
- How to train anomaly data set to improve accuracy ? HOT 2
- Error in running dummy dataset HOT 2
- size issue in anomaly score HOT 1
- error when I run command HOT 1
- AttributeError: 'ImageFolderMultiTransform' object has no attribute '_find_classes' HOT 4
- How to train a model for several classes? HOT 2
- How to improve accuracy of the localisation of anomalies at gradient map? HOT 1
- The work can be used in finding small exceptional points in images? HOT 5
- Can this work process one channel pics? HOT 1
- Qualitative results between CS-Flow and DifferNet on MTD dataset HOT 1
- Why is the loss function negative HOT 2
- Test after training HOT 1
- train loss HOT 1
- Question about using FrEIA instead of custom NF codes. HOT 1
- Train loss might be negative during training, what does this situation mean?
- Is it normal for the train loss to often be negative? HOT 1
- How can I locate the defects on the test image? 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 differnet.