search

seongmin-kye / MCT

Pytorch implementation of Meta-Learned Confidence for Few-shot Learning
71 stars 12 forks source link

pickle file #5

Open jjn037 opened 4 years ago

jjn037 commented 4 years ago

What should I preprocess with my data to make pickle file

jjn037 commented 4 years ago

And I download miniImageNet using link https://drive.google.com/file/d/1uxpnJ3Pmmwl-6779qiVJ5JpWwOGl48xt/view?usp=sharing, and preprocess data with self.transform_train = T.Compose([ T.Resize((84, 84), interpolation=3), T.RandomCrop(84, padding=8), T.RandomHorizontalFlip(), T.ToTensor(), T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), T.RandomErasing(0.5) ]) but model can't convergeļ¼Œcould u give me some advice, or make my data to pickle file

seongmin-kye commented 4 years ago

Hi, Why don't you use presented data in readme?