SUR
SUR copied to clipboard
Code for the paper "Selecting Relevant Features from a Universal Representation for Few-shot Classification"
Hi, thank you for sharing your outstanding work! I have a little doubt that when using this function"MetaDatasetBatchReader" for batch sampling, is each sampling a non-repetitive sampling? That is to...
Hello, thanks for sharing the codes. Can you explain how you got Equation 5? Shouldn't it be [cos(.,.)-log(exp(cos(.,.)))]?
Hello! When i run './scripts/train_pnf.sh', it appears '' tf.map_fn()......'imagedecoder' object has no attribute 'out_type' ''. The version of my tensorflow is 2.4. Should I lower the version of tf to...
Hi, Thank you for sharing your code. But why is it that using the pre-training model you provided, without any changes in the code, the test results vary greatly, even...
What exact versions of tensorflow and pytorch did you use for this? I can't seem to get meta-dataset and this code base both working at once.
Thanks for providing the code implementation. When training pnf model, is "--model.backbone=resnet18_pnf" needed in scripts/train_pnf.sh?
Dear author: Can you provide the code to reproduce the few-shot classification experiment on mini-ImageNet?