FeatureLearningRotNet

FeatureLearningRotNet copied to clipboard

When run CIFAR10_ConvClassifier_on_RotNet_NIN4blocks_Conv2_feats_K1000.py, there are some errors iin dataloader.py. if self.dataset_name == 'cifar10': labels = self.data.test_labels if (self.split == 'test') else self.data.train_labels data = self.data.test_data if (self.split == 'test') else...

xiaopanchen

pratt3000

How do you create attention map?

2

I read your paper, it says `` In order to generate the attention mapof a conv. layer we first compute the feature maps of this layer, then we raise each...

wzm2256

Please provide a requirements file

1

Please provide a requirements file.

awaelchli

Thanks for your work and share! I am confused that, after rotate, the image size w*h will change to h*w, how to stack them together?

cvchanghao

Is there any way to implement this code on a custom dataset ?

2

Hi, congratulations on your work! I was actually wondering if there is any way to run this code on a custom dataset?

jiteshm17

Problem about accuracy of rotnet and how many data used for comparing the features

1

May I know what is the accuracy of rotnet to predict the angle of rotation? Also, how many data are used for evaluating the features got by rotnet? Is it...

pinyuan1

Horizontal flip augmentation changes angle

2

Hi all, this might be a basic question, but in this [line](https://github.com/gidariss/FeatureLearningRotNet/blob/master/dataloader.py#L106), and other lines in the dataloader, the `RandomHorizontalFlip()` is one of the augmentations, but would that not change...

meghbhalerao

In NonLinearClassifier file, you used BatchNorm2d after Linear layer in "Multilayer" settings, is this a bug?

3

MrChenFeng

Question regarding fine-tuning phase of ImageNet classification task

1

The paper published [here](https://arxiv.org/pdf/1803.07728.pdf) explains how the pretext task training is conducted, but not how the transfer learning is conducted. I had some questions regarding the procedure for transfer learning...

SohamTamba