Giters

yaoyao-liu / meta-transfer-learning

TensorFlow and PyTorch implementation of "Meta-Transfer Learning for Few-Shot Learning" (CVPR2019)

Home Page:https://lyy.mpi-inf.mpg.de/mtl/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

question about dataset

changykang opened this issue · comments

commented

hi,i download the dataset from the link, but they donot include lable files, can you help me solve this problem. thank you.

commented

Thanks for your interest in our work.

You don't need the label files. The images for one class are saved in a corresponding folder.
You may use the provided dataloader to generate episodes for few-shot learning.

commented

thank you solve my problem,and can i directly run the run_experiment.py in tensorflow?

commented

Yes. After you install all the requirements and put the data in the proper directory, you may run the command line following the README.md file.

commented

ok, thank you reply, when i install tensorflow-gpu=1.3.0 under the python=2.7, it shown packagenotfounderror, can you help me.

commented

If the packages can not be directly downloaded, you may build TensorFlow 1.3.0 according to this link.

commented

Thank you for solving my problem patiently

commented

i have another question about the dataset, what is the dataset in the meta-train and meta-test, and how did you split the support set and query set in the miniImageNet dataset? thank you

commented

The splits of miniImageNet are available here.
There are two different splits for miniImageNet. Most papers follow the split provided by Vinyals et al.

During the meta-training phase, the support and query sets of each episode/task are randomly sampled from the training set of miniImageNet. During the meta-test phase, the support and query sets of each episode/task are randomly sampled from the test set of miniImageNet. You may easily find the generation protocol in any few-shot learning paper, e.g., MAML.

commented

That is, in the large-scale phase, 64 classes are used for training; the meta-training phase is randomly sampled; the meta-teste stage uses the test data of miniimagenet. Am I right?

commented

During the pre-train phase, we train the encoder on a 64-way classification task using the meta-train set.

During the meta-train phase, we train the meta model on many 5-way small classification tasks generated from the meta-train set.

During the meta-test phase, we evaluate the model on many 5-way small classification tasks generated from the meta-test set.