Functions — github.com/Junya-Chen/FlatCLR

CodeHub MCPcopy Create free account

hub / github.com/Junya-Chen/FlatCLR / functions

Functions113 in github.com/Junya-Chen/FlatCLR

⨍ Functions 113◇ Types & classes 26

↓ 12 callersMethodinfo

↓ 10 callersFunction_resnet

(arch, block, layers, pretrained, progress, **kwargs)

models/resnet.py:247

↓ 8 callersFunctionaccuracy

Computes the accuracy over the k top predictions for the specified values of k

↓ 8 callersFunctionsave_checkpoint

(state, is_best, filename='checkpoint.pth.tar')

↓ 8 callersMethodstep

(self, epoch=None, closure=None)

optimizer/lars.py:51

↓ 4 callersMethod__init__

models/utils.py:31

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1, dilate=False)

models/resnet.py:197

↓ 4 callersMethodget_simclr_pipeline_transform

Return a set of data augmentation transformations as described in the SimCLR paper.

data_aug/contrastive_learning_dataset.py:14

↓ 4 callersFunctionload_dataloader

datasets/load_dataloader.py:232

↓ 4 callersFunctionload_model

models/load_model.py:3

↓ 3 callersFunctionconv1x1

1x1 convolution

models/resnet.py:31

↓ 3 callersFunctionconv3x3

3x3 convolution with padding

models/resnet.py:25

↓ 3 callersFunctionsave_config_file

(model_checkpoints_folder, args)

↓ 2 callersMethod__init__

(self, block, layers, num_classes=1000, zero_init_residual=False, groups=1, width_per_group=6

models/resnet.py:123

↓ 2 callersFunctioncosine_annealing

(step, total_steps, lr_max, lr_min, warmup_steps=0)

optimizer/cos_anneal.py:3

↓ 2 callersFunctionload_fc_optimizer_scheduler

(model, args, train_loader)

optimizer/load_optimizer_scheduler.py:38

↓ 2 callersFunctionmain_transfer_ft

↓ 2 callersFunctionprepare_sub_imagenet

datasets/prepare_subimagenet.py:8

↓ 2 callersMethodtrain

(self, train_loader)

↓ 2 callersFunctiontrain_fc

(epo, train_loader, test_loader, args)

↓ 2 callersMethodupdate

(self, val, n=1)

↓ 1 callersMethod__init__

(self, path, local_rank=0)

↓ 1 callersMethod_forward_impl

models/resnet.py:221

↓ 1 callersMethodflat_loss

(self, features)

↓ 1 callersFunctionget_caltech_data_loaders

(root, num_workers=5, shuffle=False, batch_size=256, transfer=True)

datasets/load_dataloader.py:56

↓ 1 callersFunctionget_cifar100_data_loaders

(root, download, num_workers=5, shuffle=False, batch_size=256, transfer=False)

datasets/load_dataloader.py:34

↓ 1 callersFunctionget_cifar10_data_loaders

(root, download, num_workers = 5, shuffle=False, batch_size=256, transfer=False)

datasets/load_dataloader.py:12

↓ 1 callersMethodget_dataset

(self, name, n_views, gaussian=False)

data_aug/contrastive_learning_dataset.py:36

↓ 1 callersFunctionget_flower_data_loaders

(root, num_workers=5, shuffle=False, batch_size=256, transfer=True)

datasets/load_dataloader.py:85

↓ 1 callersFunctionget_imagenet_data_loaders

(root, num_workers=5, shuffle=False, batch_size=256)

datasets/load_dataloader.py:119

↓ 1 callersFunctionget_simclr_pipeline_newtransform

Return a set of data augmentation transformations as described in the SimCLR paper.

data_aug/contrastive_learning_dataset_new.py:181

↓ 1 callersFunctionget_subimagenet_data_loaders

(root, num_workers=5, shuffle=False, batch_size=256, ratio=0.01)

datasets/load_dataloader.py:207

↓ 1 callersFunctionget_sun_data_loaders

(root, num_workers=5, shuffle=False, batch_size=256, transfer=True)

datasets/load_dataloader.py:102

↓ 1 callersFunctionget_voc_data_loaders

(root, num_workers=5, shuffle=False, batch_size=256, transfer=True)

datasets/load_dataloader.py:189

↓ 1 callersMethodinfo_nce_loss

(self, features)

↓ 1 callersMethodlabel_index

(self, category)

datasets/load_dataloader.py:162

↓ 1 callersFunctionload_data

(args, device=None, download=True)

data_aug/contrastive_learning_dataset_new.py:14

↓ 1 callersFunctionload_optimizer_scheduler

(model, args, train_loader)

optimizer/load_optimizer_scheduler.py:5

↓ 1 callersFunctionmain_eval

↓ 1 callersFunctionmain_ssl

↓ 1 callersFunctionmain_supervised

↓ 1 callersFunctionmain_transfer

↓ 1 callersFunctionnormalize_fn

Differentiable version of torchvision.functional.normalize

↓ 1 callersFunctionnormalize_fn

Differentiable version of torchvision.functional.normalize

models/utils.py:5

↓ 1 callersFunctionprepare_caltech_data

(root='/home/cytao/projects-summer/datasets')

datasets/prepare_caltech.py:8

↓ 1 callersFunctionprepare_subimagenet_data

(root='/expanse/lustre/projects/dku142/cytao/datasets/imagenet')

datasets/prepare_subimagenet.py:25

↓ 1 callersFunctionprepare_tinyimagenet

(root = 'datasets/tiny_imagenet/tiny-imagenet-200')

prepare_data.py:90

↓ 1 callersMethodrefresh

data_aug/contrastive_learning_dataset_new.py:80

↓ 1 callersMethodreset

↓ 1 callersFunctionresnet10

r"""ResNet-18 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (b

models/resnet.py:256

↓ 1 callersFunctionresnet101

r"""ResNet-101 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (

models/resnet.py:304

↓ 1 callersFunctionresnet152

r"""ResNet-152 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (

models/resnet.py:316

↓ 1 callersFunctionresnet18

r"""ResNet-18 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (b

models/resnet.py:268

↓ 1 callersFunctionresnet50

r"""ResNet-50 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (b

models/resnet.py:292

↓ 1 callersMethodtrain

(self, train_loader)

↓ 1 callersFunctiontrain_ft

(epo, train_loader, test_loader, args)

fine_tune.py:13

↓ 1 callersFunctiontrain_supervised

(train_loader, test_loader, args)

train_supervised.py:17

data_aug/contrastive_learning_dataset_new.py:167

data_aug/gaussian_blur.py:20

data_aug/view_generator.py:13

Method__getitem__

Method__getitem__

Method__getitem__

prepare_data.py:131

Method__getitem__

data_aug/contrastive_learning_dataset_new.py:70

Method__getitem__

Args: index (int): Index Returns: tuple: (image, target) where target is the image segmentation.

datasets/load_dataloader.py:171

(self, *args, **kwargs)

(self, x, y, transform=None)

(self, x, y, transform=None)

(self, mean, std)

(self, root = None, train=True, transform=transforms.ToTensor())

prepare_data.py:115

(self, *args, **kwargs)

(self, X, Y, name, n_view = 2, batch_size = 128)

data_aug/contrastive_learning_dataset_new.py:55

(self, kernel_size,device='cpu')

data_aug/contrastive_learning_dataset_new.py:148

(self, kernel_size, p=0.5, min=0.1, max=2.0)

data_aug/gaussian_blur.py:12

data_aug/contrastive_learning_dataset.py:10

(self, base_transform, n_views=2)

data_aug/view_generator.py:9

(self, root, year='2012', image_set='train', download=True, transform=None, target_transform=None)

datasets/load_dataloader.py:152

(self, mean, std)

models/utils.py:14

(self, input_size, output_size, h_dim=[], use_bn=False)

models/utils.py:39

(self, args, in_channel)

models/utils.py:62

(self, in_channel, num_classes)

models/utils.py:94

(self, inplanes, planes, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm

models/resnet.py:40

(self, inplanes, planes, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm

models/resnet.py:81

( self, params, lr=required, momentum=0.9, use_nesterov=False,

optimizer/lars.py:13

prepare_data.py:128

data_aug/contrastive_learning_dataset_new.py:67

datasets/load_dataloader.py:185

Method_do_layer_adaptation

Whether to do layer-wise learning rate adaptation for `param_name`.

optimizer/lars.py:128

Method_use_weight_decay

Whether to use L2 weight decay for `param_name`.

optimizer/lars.py:118

Functionchange_batchnorm_momentum

(module, value)

Methodextra_repr

Methodextra_repr

models/utils.py:26

models/utils.py:23

models/utils.py:34

models/utils.py:57

models/utils.py:81

next →1–100 of 113, ranked by callers