Functions — github.com/aianaconda/TensorFlow2x_Engineering

hub / github.com/aianaconda/TensorFlow2x_Engineering_Implementation / functions

Functions413 in github.com/aianaconda/TensorFlow2x_Engineering_Implementation

⨍ Functions 413◇ Types & classes 46

↓ 34 callersMethodeval

(self, sess, feed_dict)

code/代码5-9 MKRmodel.py:163

↓ 23 callersMethodget_next

(self)

code/代码8-10 mydataset.py:38

↓ 18 callersMethodpredict

(self, input_array)

code/代码7-9 yolov3.py:42

↓ 5 callersFunctiongetone

(dataset)

code/代码4-8 将内存数据转成DataSet数据集.py:35

↓ 4 callersFunctionGdec

(zs, _a, dim=64, n_layers=5, shortcut_layers=1, inject_layers=0, is_training=True)

code/代码8-11 AttGANmodels.py:26

↓ 4 callersFunction_sigmoid

(x)

code/代码7-9 yolov3.py:146

↓ 4 callersFunctionget_feed_dict_for_rs

(model, data, start, end)

code/代码5-10 train.py:73

↓ 4 callersMethodload_weights

(self, model, skip_detect_layer=False)

code/代码7-10 weights.py:27

↓ 4 callersFunctionsavefeature

(classdir,filename,obj)

code/代码9-3 feature_extractor.py:71

↓ 4 callersFunctionshowone

(one_element,datasetname)

code/代码4-8 将内存数据转成DataSet数据集.py:47

↓ 4 callersFunctionto_minmax

(centroid_boxes)

code/代码7-6 box.py:169

↓ 3 callersFunctionGenc

(x, dim=64, n_layers=5, is_training=True)

code/代码8-11 AttGANmodels.py:12

↓ 3 callersFunctionM

Modified cost for logarithmic updates

code/代码9-1 Sinkhorn.py:30

↓ 3 callersFunctionNN_search

(x,center)

code/代码9-5 ZSL_test.py:51

↓ 3 callersMethod__init__

(self, filters, layer_idx, name="")

code/代码7-8 yolohead.py:77

↓ 3 callersMethod__init__

(self ,intermediate_dim,latent_dim, **kwargs)

code/代码8-6 更合理的类封装方式.py:39

↓ 3 callersMethod__init__

(self)

code/代码7-7 darknet53.py:14

↓ 3 callersFunction_concat

(z, z_, _a)

code/代码8-11 AttGANmodels.py:30

↓ 3 callersFunction_get_initializer

(embedding_dimension, embedding_values)

code/代码5-5 序列特征工程.py:38

↓ 3 callersMethod_read_bytes

(self, size)

code/代码7-10 weights.py:59

↓ 3 callersMethod_root_tag

(self, fname)

code/代码7-4 annotation.py:218

↓ 3 callersMethodas_centroid

(self)

code/代码7-6 box.py:44

↓ 3 callersFunctiondeprocess_image

(img)

code/代码8-9 使用deblur模型.py:16

↓ 3 callersFunctiongline

(filelist)

code/代码6-1 NLP文本预处理.py:21

↓ 3 callersFunctioninput_fn

估算器的输入函数.

code/代码5-6 用wide_deep模型预测人口收入.py:140

↓ 3 callersFunctioninput_fn

估算器的输入函数.

code/代码5-7 用梯度提升树模型预测人口收入.py:156

↓ 3 callersFunctionpreprocess_input

(image, net_size)

code/代码7-9 yolov3.py:149

↓ 3 callersFunctionsamplingfun

(z_mean, z_log_var)

code/代码8-4 在动态图中实现变分自编码.py:43

↓ 3 callersFunctionsummary

(tensor_collection, summary_type=['mean', 'stddev', 'max', 'min', 'sparsity', 'histogram'],

code/代码8-12 trainattgan.py:157

↓ 3 callersFunctiontrain_generator

()

code/代码8-14 MINE.py:17

↓ 2 callersFunctionD

(x, n_att, dim=64, fc_dim=MAX_DIM, n_layers=5)

code/代码8-11 AttGANmodels.py:59

↓ 2 callersFunctionGenerateData

(datasize = 100 )

code/代码3-3 用估算器框架训练一个回归模型.py:13

↓ 2 callersFunctionGenerateData

(datasize = 100 )

code/代码3-8 用估算器框架分布式训练ps.py:28

↓ 2 callersFunctionGenerateData

(batchsize=100)

code/代码4-1 将模拟数据制作成内存对象数据集.py:14

↓ 2 callersFunctionGenerateData

(datasize = 100 )

code/代码3-10 用估算器框架进行分布式训练worker.py:28

↓ 2 callersFunctionGenerateData

(datasize = 100 )

code/代码3-9 用估算器框架进行分布式训练chief.py:27

↓ 2 callersFunctionGenerateData

(datasize = 100 )

code/代码3-4 为估算器添加钩子.py:13

↓ 2 callersFunctionGenerateData

(datasize = 100 )

code/代码3-7 用估算器框架进行分布式训练.py:13

↓ 2 callersFunctionGenerateData

(training_epochs,batchsize=100)

code/代码4-2 带迭代的模拟数据集.py:14

↓ 2 callersMethodGlobalD

(self, y, M)

code/代码8-15 DIM.py:127

↓ 2 callersMethodLocalD

(self, x)

code/代码8-15 DIM.py:121

↓ 2 callersMethodMask

(self, inputs, seq_len, mode='mul')

code/代码6-3 keras注意力机制模型.py:62

↓ 2 callersMethodPriorD

(self, x)

code/代码8-15 DIM.py:124

↓ 2 callersMethod__init__

(self, nb_head, size_per_head, **kwargs)

code/代码6-3 keras注意力机制模型.py:41

↓ 2 callersMethod__init__

(self ,intermediate_dim,original_dim,latent_dim,**kwargs)

code/代码8-5 以类的方式封装模型损失函数.py:73

↓ 2 callersFunction_interval_overlap

(interval_a, interval_b)

code/代码7-6 box.py:126

↓ 2 callersFunction_processimg

(imgname)

code/代码8-8 训练deblur.py:49

↓ 2 callersFunction_processimg

(imgname)

code/代码8-9 使用deblur模型.py:32

↓ 2 callersFunction_summary

(tensor, name, summary_type)

code/代码8-12 trainattgan.py:161

↓ 2 callersMethod_tree

(self, fname)

code/代码7-4 annotation.py:223

↓ 2 callersFunctionavgfeature

(all_features)

code/代码9-3 feature_extractor.py:63

↓ 2 callersFunctionbuild_estimator

按照指定的模型生成估算器对象.

code/代码5-6 用wide_deep模型预测人口收入.py:110

↓ 2 callersFunctionbuild_estimator

按照指定的模型生成估算器对象.

code/代码5-7 用梯度提升树模型预测人口收入.py:120

↓ 2 callersFunctionbuild_model_columns

生成wide和deep模型的特征列集合.

code/代码5-6 用wide_deep模型预测人口收入.py:38

↓ 2 callersFunctionbuild_model_columns

生成wide和deep模型的特征列集合.

code/代码5-7 用梯度提升树模型预测人口收入.py:38

↓ 2 callersMethodcall

(self, input_tensor, training=False)

code/代码7-9 yolov3.py:46

↓ 2 callersFunctioncentroid_box_iou

(box1, box2)

code/代码7-6 box.py:125

↓ 2 callersFunctioncost_matrix

(x,y)

code/代码9-1 Sinkhorn.py:11

↓ 2 callersFunctioncreate_pipeline

(filename, batch_size, num_epochs=None)

code/代码4-4 将Excel文件制作成内存对象数据集.py:24

↓ 2 callersFunctiondataset

parse dataset.

code/代码4-11 将图片文件制作成Dataset数据集TFa.py:78

↓ 2 callersFunctiondataset

parse dataset.

code/代码9-2 finetune_resnet.py:48

↓ 2 callersFunctiondataset

parse dataset.

code/代码4-10 将图片文件制作成Dataset数据集-TFa.py:78

↓ 2 callersFunctiondataset

parse dataset.

code/代码7-3 用ResNet识别橘子和苹果.py:82

↓ 2 callersFunctiondataset

parse dataset.

code/代码4-12 在动态图里读取Dataset数据集.py:95

↓ 2 callersFunctiongen_labels

(id_df, seq_length, label)

code/代码5-12 预测飞机发动机的剩余使用寿命-TF2.py:115

↓ 2 callersFunctiongenerator_model

(image_shape,istrain = True)

code/代码8-7 deblurmodel.py:47

↓ 2 callersFunctionget_attributes

(url,function=None)

code/代码9-4 ZSL_train.py:75

↓ 2 callersMethodget_label

(self)

code/代码7-6 box.py:33

↓ 2 callersMethodget_labels

(self, annotation_file)

code/代码7-4 annotation.py:195

↓ 2 callersFunctionget_user_record

(data, is_train)

code/代码5-10 train.py:118

↓ 2 callersMethodget_variables

(self, layer_idx, suffix=None)

code/代码7-9 yolov3.py:51

↓ 2 callersFunctiongetcost

(x,y)

code/代码3-1 从动态图种获取变量.py:33

↓ 2 callersFunctiongetcost

(x,y)

code/代码2-2 用动态图训练一个具有保存检查点功能的回归模型.py:32

↓ 2 callersFunctiongetdataset

(features)

code/代码6-8 迁移训练BERT模型对中文分类.py:52

↓ 2 callersFunctiongetone

(dataset)

code/代码4-11 将图片文件制作成Dataset数据集TFa.py:123

↓ 2 callersFunctiongetone

(dataset)

code/代码4-10 将图片文件制作成Dataset数据集-TFa.py:123

↓ 2 callersFunctiongetone

(dataset)

code/代码4-9 from_tensor_slices的注意事项.py:17

↓ 2 callersFunctiongrad

( inputs, targets)

code/代码3-1 从动态图种获取变量.py:42

↓ 2 callersFunctionimgs_input_fn

(dataset)

code/代码9-2 finetune_resnet.py:73

↓ 2 callersFunctionimgs_input_fn

(dataset)

code/代码7-3 用ResNet识别橘子和苹果.py:151

↓ 2 callersMethodimread

(self, img_file, boxes)

code/代码7-4 annotation.py:21

↓ 2 callersFunctionload_sample

递归读取文件。只支持一级。返回文件名、数值标签、数值对应的标签名

code/代码4-11 将图片文件制作成Dataset数据集TFa.py:15

↓ 2 callersFunctionload_sample

递归读取文件。只支持一级。返回文件名、数值标签、数值对应的标签名

code/代码4-10 将图片文件制作成Dataset数据集-TFa.py:15

↓ 2 callersFunctionload_sample

递归读取文件。只支持一级。返回文件名、数值标签、数值对应的标签名

code/代码4-12 在动态图里读取Dataset数据集.py:22

↓ 2 callersFunctionloss_fn

(list_y_trues, list_y_preds,anchors,image_size)

code/代码7-11 yololoss.py:123

↓ 2 callersFunctionlse

(A)

code/代码9-1 Sinkhorn.py:34

↓ 2 callersFunctionmydataset

(positive_data_file,negative_data_file)

code/代码6-1 NLP文本预处理.py:18

↓ 2 callersMethodnext_batch

(self)

code/代码7-5 generator.py:36

↓ 2 callersFunctionparse_annotation

(ann_fname, img_dir, labels_naming=[])

code/代码7-4 annotation.py:149

↓ 2 callersFunctionread_and_decode

(filenames,flag = 'train',batch_size = 3)

code/代码4-5 将图片文件制作成TFRecord数据集.py:63

↓ 2 callersFunctionread_file

(path)

code/代码6-8 迁移训练BERT模型对中文分类.py:29

↓ 2 callersFunctionshowimg

(index,label,img,ntop)

code/代码4-11 将图片文件制作成Dataset数据集TFa.py:114

↓ 2 callersFunctionshowimg

(index,label,img,ntop)

code/代码4-10 将图片文件制作成Dataset数据集-TFa.py:114

↓ 2 callersFunctionshowimg

(index,label,img,ntop)

code/代码7-3 用ResNet识别橘子和苹果.py:120

↓ 2 callersFunctionto_range

(images, min_value=0.0, max_value=1.0, dtype=None)

code/代码8-12 trainattgan.py:251

↓ 2 callersFunctiontrain_input_fn

(train_data, batch_size)

code/代码3-3 用估算器框架训练一个回归模型.py:22

↓ 1 callersFunctionGenerateData

(datasize = 100 )

code/代码3-6 将估算器模型转为静态图模型.py:14

↓ 1 callersFunctionGenerateData

(datasize = 100 )

code/代码4-8 将内存数据转成DataSet数据集.py:14

↓ 1 callersFunctionKM

(features)

code/代码9-3 feature_extractor.py:142

↓ 1 callersFunctionWDVSc

定义损失函数

code/代码9-4 ZSL_train.py:39

next →1–100 of 413, ranked by callers