Prototypical-Networks-for-Few-shot-Learning-PyTorch
Prototypical-Networks-for-Few-shot-Learning-PyTorch copied to clipboard
orobix
Implementation of Prototypical Networks for Few Shot Learning (https://arxiv.org/abs/1703.05175) in Pytorch
可以尝试从此处获取txt文档，至于omniglot，网上很多，自己找一找吧 链接：https://pan.baidu.com/s/107kT-8A7jqzHnzIJD4Fm3A 提取码：iku1
In the original paper in "Algorithm 1", they mention that each batch is sampled "without replacement": > > ... RANDOMSAMPLE(S, N) denotes a set of N elements chosen uniformly at...
--------------------------------------------------------------------------- FileNotFoundError Traceback (most recent call last) in 252 253 if __name__ == '__main__': --> 254 main() in main() 208 init_seed(options) 209 --> 210 tr_dataloader = init_dataloader(options, 'train') 211 val_dataloader...
Hi. Thanks for the repo. I have a couple of queries in the load_img function. https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch/blob/5e18a5e5b369903092f683d434efb12c7c40a83c/src/omniglot_dataset.py#L166-L181 1) Is it necessary to do x = 1.0 - torch.from_numpy(x) ? I understand...
` paths, self.y = zip(*[self.get_path_label(pl) for pl in range(len(self))])` what is len(self)?
Thank you very much for sharing your code. I want to train models with a dataset other than miniImageNet and Omniglot. Could you guide me how to arrange dataset (main...
When i run the programe: how can i solve it? ``` opt = get_parser().parse_args() mode = "train" OmniglotDataset(mode=mode, root=opt.dataset_root) ``` == Downloading https://raw.githubusercontent.com/jakesnell/prototypical-networks/master/data/omniglot/splits/vinyals/test.txt Traceback (most recent call last): File "",...
I use your 'python train.py --cuda' to evaluate your code. But I can only get 65% test acc. Can you tall me what happened? Thank you very much
Dear author Thank you for your carefully written code. I re-use your some codes, and I found out the error please check the line 84 in prototypical_loss.py I think `y_hat`...
