Functions — github.com/cugzj/KT-pFL

hub / github.com/cugzj/KT-pFL / functions

Functions149 in github.com/cugzj/KT-pFL

⨍ Functions 149◇ Types & classes 30

↓ 12 callersMethod__init__

(self, input_dim = 784*3, mid_dim = 100, output_dim = 10)

src/model.py:9

↓ 12 callersFunctionread_user_data

(index,data,dataset)

src/model_utils.py:292

↓ 9 callersMethod__init__

(self,input = 3, output = 128,conv_kernel = (3,3),conv_padding=(1,1),con_strides = (1,1), po

src/new_model.py:9

↓ 8 callersFunctionread_data

parses data in given train and test data directories assumes: - the data in the input directories are .json files with keys 'users'

src/model_utils.py:243

↓ 6 callersFunctiongenerate_partial_data

(X, y, class_in_use = None, verbose = False)

src/data_utils.py:197

↓ 5 callersMethod_make_stage

(self, repeat, in_channels, out_channels, stride, t)

src/new_model.py:298

↓ 5 callersMethod_make_stage

(self, repeat, in_channels, out_channels, stride, t)

src/model.py:332

↓ 5 callersFunctionargs_parser

()

src/options.py:9

↓ 5 callersFunctionget_dataarray

Returns train and test dataarray

src/data_utils.py:161

↓ 4 callersMethod_make_layer

make resnet layers(by layer i didnt mean this 'layer' was the same as a neuron netowork layer, ex. conv layer), one layer may contai

src/new_model.py:142

↓ 4 callersMethod_make_layer

make resnet layers(by layer i didnt mean this 'layer' was the same as a neuron netowork layer, ex. conv layer), one layer may contain

src/model.py:212

↓ 4 callersFunctiongenerate_alignment_data

(X, y, N_alignment = 3000)

src/data_utils.py:255

↓ 4 callersFunctiongetdataset

(args,conf_dict)

src/data_utils.py:53

↓ 4 callersFunctiontrain_one_model

(model,train_dataloader,test_dataloader,optimizer,epoch,device,criterion, min_delta=0.01,patience=3,

src/engine_topk.py:34

↓ 4 callersFunctiontrain_one_model

(model,train_dataloader,test_dataloader,optimizer,epoch,device,criterion, min_delta=0.01,patience=3,

src/engine_kt_pfl.py:33

↓ 4 callersFunctiontrain_one_model

(model,train_dataloader,test_dataloader,optimizer,epoch,device,criterion, min_delta=0.01,patience=3,

src/engine_cos.py:35

↓ 4 callersFunctiontrain_one_model

(model,train_dataloader,test_dataloader,optimizer,epoch,device,criterion, min_delta=0.01,patience=3,

src/engine_normal.py:42

↓ 4 callersMethodwrite

(self)

src/model_utils.py:336

↓ 3 callersMethod_make_stage

(self, in_channels, out_channels, repeat)

src/new_model.py:442

↓ 3 callersMethod_make_stage

(self, in_channels, out_channels, repeat)

src/model.py:476

↓ 2 callersFunctionget_sample_data

(X_train_private, y_train_private,users_index,N_samples_per_class=10)

src/data_utils.py:183

↓ 2 callersFunctionmnist_noniid

Sample non-I.I.D client data from MNIST dataset :param dataset: :param num_users: :return:

src/sampling.py:25

↓ 2 callersMethodupdate

(self, rnd, cid, stats)

src/model_utils.py:330

↓ 2 callersFunctionval_one_model

(model,dataloader,criterion=None,device= torch.device('cuda'))

src/engine_topk.py:77

↓ 2 callersFunctionval_one_model

(model,dataloader,criterion=None,device= torch.device('cuda'))

src/engine_kt_pfl.py:79

↓ 2 callersFunctionval_one_model

(model,dataloader,criterion=None,device= torch.device('cuda'))

src/engine_cos.py:78

↓ 2 callersFunctionval_one_model

(model,dataloader,criterion=None,device= torch.device('cuda'))

src/engine_normal.py:90

↓ 1 callersFunctionKL_loss

(inputs, target, reduction='average')

src/engine_topk.py:13

↓ 1 callersFunctionKL_loss

(inputs, target, reduction='average')

src/engine_kt_pfl.py:12

↓ 1 callersFunctionKL_loss

(inputs, target, reduction='average')

src/engine_cos.py:13

↓ 1 callersFunctionKL_loss

(inputs, target, reduction='average')

src/engine_normal.py:12

↓ 1 callersFunctionchannel_shuffle

channel shuffle operation Args: x: input tensor groups: input branch number

src/new_model.py:323

↓ 1 callersFunctionchannel_shuffle

channel shuffle operation Args: x: input tensor groups: input branch number

src/model.py:357

↓ 1 callersFunctionchannel_split

split a tensor into two pieces along channel dimension Args: x: input tensor split:(int) channel size for each pieces

src/new_model.py:314

↓ 1 callersFunctionchannel_split

split a tensor into two pieces along channel dimension Args: x: input tensor split:(int) channel size for each pieces

src/model.py:348

↓ 1 callersFunctioncifar_noniid

Sample non-I.I.D client data from CIFAR10 dataset :param dataset: :param num_users: :return:

src/sampling.py:161

↓ 1 callersMethodcollaborative_training

(self)

src/engine_topk.py:361

↓ 1 callersMethodcollaborative_training

(self)

src/engine_kt_pfl.py:374

↓ 1 callersMethodcollaborative_training

(self)

src/engine_cos.py:387

↓ 1 callersMethodcollaborative_training

(self)

src/engine_normal.py:291

↓ 1 callersFunctiongenerate_bal_private_data

Input: -- N_parties : int, number of collaboraters in this activity; -- classes_in_use: array or generator, the classes of EMNIST-letter

src/data_utils.py:215

↓ 1 callersFunctionget_cosdist

(a,b)

src/engine_topk.py:117

↓ 1 callersFunctionget_cosdist

(a,b)

src/engine_cos.py:118

↓ 1 callersFunctionget_models_logits

(raw_logits, threshold, N_models)

src/engine_topk.py:134

↓ 1 callersFunctionget_models_logits

(raw_logits, weight_alpha, N_models, penalty_ratio)

src/engine_kt_pfl.py:98

↓ 1 callersFunctionget_models_logits

(raw_logits, threshold, N_models)

src/engine_cos.py:135

↓ 1 callersFunctionmain

参数导入

src/FedMD_main.py:39

↓ 1 callersFunctionmain

参数导入

src/KT-pFL.py:38

↓ 1 callersFunctionmain

参数导入

src/KT-pFL_topk.py:38

↓ 1 callersFunctionmain

显示图像

src/data_utils.py:353

↓ 1 callersFunctionmain

参数导入

src/KT-pFL_cos.py:38

↓ 1 callersFunctionpartitionOfK

(numbers, start, end, k)

src/engine_topk.py:96

↓ 1 callersFunctionplot_all

(root='../save/')

src/plot_data.py:24

↓ 1 callersFunctionpredict

(model,dataarray,device)

src/engine_topk.py:186

↓ 1 callersFunctionpredict

(model,dataarray,device,T)

src/engine_kt_pfl.py:197

↓ 1 callersFunctionpredict

(model,dataarray,device)

src/engine_cos.py:212

↓ 1 callersFunctionpredict

(model,dataarray,device)

src/engine_normal.py:109

↓ 1 callersFunctionpretrain

第一步，预训练

src/FedMD_main.py:19

↓ 1 callersFunctionpretrain

第一步，预训练

src/KT-pFL.py:19

↓ 1 callersFunctionpretrain

第一步，预训练

src/KT-pFL_topk.py:19

↓ 1 callersFunctionpretrain

第一步，预训练

src/KT-pFL_cos.py:19

↓ 1 callersFunctionread_cifa_data

()

src/model_utils.py:79

FunctionSoftCrossEntropy

(inputs, target, reduction='average')

src/engine_topk.py:25

FunctionSoftCrossEntropy

(inputs, target, reduction='average')

src/engine_kt_pfl.py:24

FunctionSoftCrossEntropy

(inputs, target, reduction='average')

src/engine_cos.py:26

FunctionSoftCrossEntropy

(inputs, target, reduction='average')

src/engine_normal.py:33

FunctionSoftCrossEntropy_without_logsoftmax

(inputs, target, reduction='average')

src/engine_normal.py:24

(self, parties, public_dataset, private_data, total_private_data, private_te

src/engine_topk.py:257

Method__init__

(self, parties, public_dataset, private_data, total_private_data, private_te

src/engine_kt_pfl.py:268

Method__init__

(self, parties, public_dataset, private_data, total_private_data, private_te

src/engine_cos.py:283

(self,n_classes,n1 = 128, n2=192, n3=256, dropout_rate = 0.2,fc=100)

src/new_model.py:25

Method__init__

(self,n_classes,n1 = 128, n2=256, dropout_rate = 0.2, fc=100)

src/new_model.py:42

Method__init__

(self, in_channels, out_channels, stride=1)

src/new_model.py:68

Method__init__

(self, in_channels, out_channels, stride=1)

src/new_model.py:98

Method__init__

(self, block, num_block, num_classes=100)

src/new_model.py:124

Method__init__

(self, in_channels, out_channels, stride, t=6, num_classes=100)

src/new_model.py:223

Method__init__

(self, num_classes=100)

src/new_model.py:254

Method__init__

(self, in_channels, out_channels, stride)

src/new_model.py:341

Method__init__

(self, ratio=1, num_classes=16)

src/new_model.py:400

Method__init__

(self, parties, public_dataset, private_data, total_private_data, private_te

src/engine_normal.py:187

Method__init__

(self, clients, params)

src/model_utils.py:321

(self,input = 3, output = 128,conv_kernel = (3,3),conv_padding=(1,1),con_strides = (1,1), poo

src/model.py:50

Method__init__

(self,n_classes,n1 = 128, n2=192, n3=256, dropout_rate = 0.2,fc=100)

src/model.py:66

Method__init__

(self,n_classes,n1 = 128, n2=256, dropout_rate = 0.2, fc=100)

(self, num_classes=10)

src/model.py:121

Method__init__

(self, in_channels, out_channels, stride=1)

src/model.py:166

Method__init__

(self, block, num_block, num_classes=10)

src/model.py:194

next →1–100 of 149, ranked by callers