Comments (2)
Thank you for the interest!
I believe your question can be summarized as follows:
(1) Is the ood_sample
parameter in eval.py
and # of samples
in Table 11 the same?
(2) The ood_sample
parameter doesn't show dramatic performance as Table 11.
(3) How to achieve controlled
results (of Table 11) in our code.
by the way, you don't need to retrain the network to achieve the same results.
We will answer in following orders: (1) -> (3) -> (2)
(1) Yes, the ood_sample
parameter in eval.py
denotes the # of samples
in Table 11.
(3) Our evaluation examples in README.md
is a controlled
version. If you want an uncontrolled version, first remove --resize-fix
and set --resize_factor
to 0.08.
--resize_factor
decides the resizing(i.e., cropping) area range (in Inception crop, we uniformly sample from 0.08~1.0 to obtain the size for cropped image).--resize_fix
fixed the sampling range. For instance, if you set--resize_factor
to 0.54 and set--resize_fix
, the size of the cropped image will have 0.54 * original image size.
(2) I think that you have run a controlled
version with different # of samples
. Is it possible to rerun the inference with the uncontrolled version as mentioned in the answer (3) above (to obtain the same result with Table 11)?
If you have more questions please let us know!
Thank you
from csi.
If you have more questions or any problems with running the code, feel free to reopen this issue.
Thank you!
from csi.
Related Issues (20)
- Your data is 4 times bigger than Simclr. Is it fair? HOT 1
- Can you share the implementation detail for baseline?(Cross-Entropy) HOT 3
- Why did you do the rotation transformation firstly and then apply the simlcr_aug? HOT 1
- batch size HOT 4
- The result of using the checkpoint of unlabeled ImageNet-30 HOT 3
- CSI/training/unsup/simclr_CSI.py HOT 1
- Error while running the training script. HOT 1
- GPU requirement for training ImageNet model HOT 1
- About how to get result for noise condition
- How to define the joint_labels
- ImportError: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.21' not found HOT 1
- The hyper parmeter of Rot(resnet18) and Rot+Trans(resnet18)
- Reproducing results for Cifar100 ens multi-class
- How can i train it on my own dataset? HOT 10
- GPU requirement for training One-class ImageNet-30
- Some questions about Supervised_NT_xent
- baseline code?
- cannot reach the results when removing the four-way rotation classifier
- why use the hfilp() function during training? What does it do?
- Model is provided extra arguments.
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 csi.