Comments (5)
I have processed the omniglot into noLatin.json as the requirement, however, it raises this issue.
Traceback (most recent call last): File "train.py", line 108, in assert params.num_classes >= 1597, 'class number need to be larger than max label id in base class' AssertionError: class number need to be larger than max label id in base class
The form of Json is "{label_names": ["Alphabet_of_the_Magi/character01","Alphabet_of_the_Magi/character02",..."ULOG/character26"],"image_names": ["E:/Project/CloserLookFewShot-master/filelists/omniglot/images/Alphabet_of_the_Magi/character01/0709_19.png",...,"E:/Project/CloserLookFewShot-master/filelists/omniglot/images/ULOG/character26/1623_15.png"],"image_labels": [0,...,1596]}
When you train the model, you need to specify num_classes, for example python ./train.py --model Conv4 --method baseline --num_classes 1597
from closerlookfewshot.
I have processed the omniglot into noLatin.json as the requirement, however, it raises this issue.
Traceback (most recent call last): File "train.py", line 108, in assert params.num_classes >= 1597, 'class number need to be larger than max label id in base class' AssertionError: class number need to be larger than max label id in base class
The form of Json is "{label_names": ["Alphabet_of_the_Magi/character01","Alphabet_of_the_Magi/character02",..."ULOG/character26"],"image_names": ["E:/Project/CloserLookFewShot-master/filelists/omniglot/images/Alphabet_of_the_Magi/character01/0709_19.png",...,"E:/Project/CloserLookFewShot-master/filelists/omniglot/images/ULOG/character26/1623_15.png"],"image_labels": [0,...,1596]}When you train the model, you need to specify num_classes, for example python ./train.py --model Conv4 --method baseline --num_classes 1597
Thank you for the helpful answer, however, I have added the --num_classes 1597 or defined the num_classes = 1597 before reporting this issue. I think there may have another reason.
from closerlookfewshot.
Thank you for the helpful answer, however, I have added the --num_classes 1597 or defined the unm_classes = 1597 before reporting this issue. I think there may have another reason.
Have you ever tried the cross domain tasks(miniImagenet-CUB) in table 3? I have met the problem of lower accuracy 52% in baseline using ResNet18. And I didn't get the reason of this. If you have done this research, can you tell me what the problem is? Thank you very much!
from closerlookfewshot.
Thank you for the helpful answer, however, I have added the --num_classes 1597 or defined the unm_classes = 1597 before reporting this issue. I think there may have another reason.
Have you ever tried the cross domain tasks(miniImagenet-CUB) in table 3? I have met the problem of lower accuracy 52% in baseline using ResNet18. And I didn't get the reason of this. If you have done this research, can you tell me what the problem is? Thank you very much!
Sorry, I do not have the imagenent dataset on my PC. Therefore, I tried cross_char instead but it can not run.
from closerlookfewshot.
Hello, were you able to resolve the issue of running cross_char? We were able to run cross_char with python ./train.py --dataset cross_char --method baseline++ --num_classes 1597
, however the baseline++ accuracy (80%) is lower than baseline (85%) for omniglot -> EMNIST. Please let us know if you also have this issue, thank you so much.
from closerlookfewshot.
Related Issues (20)
- Training accuracies are low and their gaps are big when Conv4 backbone is used.
- Question on feature_loader.py:32,33
- The stop_epoch number of maml
- Larger batch size for CUBS.
- Query Regarding Figure 5.
- TypeError: super() argument 1 must be type, not classobj
- h
- Training using 'protonet', 'matchingnet', 'relationnet', 'relationnet_softmax', 'maml', 'maml_approx' methods with an unbalanced dataset.
- Baseline++ cross_char accuracy lower than Baseline
- About the lacking of query sample in data_loader and the lacking of target in calculating loss
- h
- CUB dataset's link no longer valid
- Baseline ++ validation wrongly reported in paper?
- What does fid mean in write_miniImagenet_filelist.py ?
- How to fine-tune the Matching Network HOT 1
- errro _pickle.PicklingError HOT 1
- RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'
- how to make the experiments repeatable?
- How to get the pre-trained model?
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 closerlookfewshot.