Comments (4)
Hi, thank you for your interest in our work!
I think you should run the SimCLR code with --shift_trans_type none
and also test with the same option (since as you already mentioned, SimCLR does not require shifting transformation classification layer).
If you don't want to train the model again, maybe forcing the P.K_Shift=1
(after get_shift_module
function) might resolve the problem (not sure about this...).
And by the way, I recommend lars
optimizer since I had never tried with adam
and I am not sure about the performance. When I used sgd
rather than lars
optimizer, the overall performance had dropped around 1~2%. Also, If you are training SimCLR, you should set the batch size to 128 (then it will make 4 * 128 in total, for CSI it was 32 since we multiply with the number of rotation transformation).
Thank you again for your interest.
from csi.
Hi, I run the following code.
for training:
CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m torch.distributed.launch --nproc_per_node=4 train.py --dataset cifar10 --model resnet18 --mode simclr --shift_trans_type none --batch_size 128 --one_class_idx 0 --optimizer adam --suffix new
for evaluation:
python3 eval.py --mode ood_pre --dataset cifar10 --model resnet18 --ood_score simclr --shift_trans_type none --print_score --ood_samples 10 --resize_factor 0.54 --resize_fix --one_class_idx 0 --load_path <load_path>
And I got a different result.
I think it should be 87.9 (in the paper, Table 7a). It may be lower due to the optimizer, but it is too low.
- Is there any problem with my command?
- Could you provide sample codes to reproduce the Table 7a result?
Thanks
from csi.
Thanks a lot!
I will try --shift_trans_type none
with batch size 128
CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m torch.distributed.launch --nproc_per_node=4 train.py --dataset cifar10 --model resnet18 --mode simclr --shift_trans_type none --batch_size 128 --one_class_idx 0 --optimizer adam --suffix new
from csi.
If you have any problems, feel free to reopen the issue.
Thank you.
from csi.
Related Issues (20)
- 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.
- Problem
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.