New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to build my own train_set use own data #64
Comments
Hi! This seems to be related to #44 . You can build a More recently, we added the SupportSetFolder class that helps you to build a support set easily from custom data. So depending on your use case, it will be one or the other. |
Thanks for your suggest @ebennequin. path = 'D:/G/few_shot_learning/try_code/flowers' device = torch.device('cuda:0' if torch.cuda.is_available() else "cpu") model = PrototypicalNetworks(convolutional_network).cuda() test_sampler = TaskSampler(test_set, n_way=N_WAY, n_shot=N_SHOT, n_query=N_QUERY, n_tasks=N_EVALUATION_TASKS) test_loader = DataLoader( ( The structure of flowers file is: |
This error is risen in You are using task samplers on a dataset that is not meant to be used to sample few-shot tasks. As its name and docstring indicate, it is only meant to handle the support set of a unique few-shot task. I made this choice for For your issue, I suggest you use |
I have built custom data by using EasySet, thanks very much! @ebennequin |
Problem
Thanks for your sharing about FSL, there is one problem:
When I finished the tutorial 'Discovering Prototypical Networks' , I want to use my own photo data to build test_set, how can I do that and How should I construct my data's structure
The text was updated successfully, but these errors were encountered: