Comments (3)
Hi Tong Zhang,
Thanks for your interest in our work. Yes, you are correct that if we only have 1 shot and use exactly one embedded feature, the singular vector cannot be obtained.
In our code, you can see that when the number of shot is 1, we add an augmented sample (in total 2 samples).
Then we run svd with the number of column is two. This is also reflected in the Experiments section of our paper.
Hope this answers your question.
Cheers
from dsn_fewshot.
Thanks for your prompt reply!
I'm still confused about some code details. In the 1-shot case, I printed out self.num_dim from Subspace_Projection.create_subspace() in Conv4/algorithm/subspace_projection.py and found that it is all 0. This causes the return value all_hyper_ planes to be []. Here is my code and the result of running it.
I noticed the use of inverted images to expand the support set at 1-shot, but the key problem is not setting the subspace dimension correctly when the Subspace_Projection class is initialized.
Thanks again for your time and have a great day!
from dsn_fewshot.
Hi Tong Zhang,
You can see in train_subspace_discriminative.py > line 61. The subspacedim is set to 1.
Yes, there is a mistake when I initialize the subspaceprojection class. I have edited the line to initialize subspace projection, you can pull or copy from train_subspace_discriminative.py. Thanks for spotting this out!
from dsn_fewshot.
Related Issues (20)
- How to reproduce the reported results? HOT 1
- The setting of '--train-shot' in ResNet12/train.py HOT 3
- About discriminative loss. HOT 2
- what is timining for training on miniimagenet using subspace classifier? using 4 gpus, its taking around 17 hrs in my case. Is that the case in general? HOT 1
- Question about Equation 2 and its implementation HOT 4
- a request HOT 3
- DSN for CUB dataset HOT 1
- Question for test_subspace_discriminative.py
- where is the CIFAR_FS_train.pickle
- tensors in double for SVD HOT 2
- Dataset mini-ImageNet - ResNet12 link issue.
- resnet12 miniimagenet link error
- CUDA error: an illegal memory access was encountered HOT 1
- Test on the miniimagenet dataset HOT 1
- parameters for the protonet (resnet12)is what? I use the default config to train, the5way 1 shot for cifarfs accuracy is just 63? HOT 1
- tieredImagenet loader meet a problem ,the dict don't have attribute labels ,it have label_general and label_specific? HOT 2
- I trained the tired-Imagnet with protonet,used resnet12,bu the accuracy test is only 78.4,less than 80,so whats the parameters? HOT 1
- The val and test set problem in ResNet-12 mini-Imagenet experiment. HOT 1
- Could you please release the pre-trained conv4 and resnet12 model of miniImageNet? HOT 3
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 dsn_fewshot.