MCPcopy Create free account

hub / github.com/buaacxf/VIPTR / types & classes

Types & classes124 in github.com/buaacxf/VIPTR

⨍ Functions 373◇ Types & classes 124
↓ 16 callersClassDropPath
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
modules/SVTR.py:67
↓ 5 callersClassConvBNLayer
modules/SVTR.py:38
↓ 4 callersClassAlignCollate
dataset.py:290
↓ 4 callersClassDWConv2d
modules/VIPTRv1-T_ch.py:24
↓ 4 callersClassDWConv2d
modules/VIPTRv2T_ch.py:23
↓ 4 callersClassDWConv2d
modules/VIPTRv1.py:24
↓ 4 callersClassDWConv2d
modules/VIPTRv2.py:23
↓ 3 callersClassFeedForward
modules/VIPTRv1-T_ch.py:315
↓ 3 callersClassFeedForward
modules/VIPTRv1.py:315
↓ 3 callersClassFeedForward
modules/VIPTRv2.py:308
↓ 3 callersClassGRCL
modules/feature_extraction.py:66
↓ 3 callersClassLoadDatasetLmdb
dataload/loader.py:30
↓ 3 callersClassModel
model.py:23
↓ 3 callersClassWarpMLS
dataload/aug/warp_mls.py:6
↓ 2 callersClassAttnLabelConverter
Convert between text-label and text-index
utils.py:103
↓ 2 callersClassAverager
Compute average for torch.Tensor, used for loss average.
utils.py:150
↓ 2 callersClassBidirectionalLSTM
modules/sequence_modeling.py:39
↓ 2 callersClassCSWinBlock
modules/VIPTRv2.py:661
↓ 2 callersClassCTCLabelConverter
Convert between text-label and text-index
utils.py:5
↓ 2 callersClassConvBNLayer
modules/VIPTRv1-T_ch.py:39
↓ 2 callersClassConvBNLayer
modules/VIPTRv2T_ch.py:37
↓ 2 callersClassConvBNLayer
modules/VIPTRv1.py:39
↓ 2 callersClassConvBNLayer
modules/VIPTRv2.py:37
↓ 2 callersClassFeedForward
modules/VIPTRv2T_ch.py:308
↓ 2 callersClassLayerScale
modules/VIPTRv2T_ch.py:387
↓ 2 callersClassOSRA_Block
modules/VIPTRv2.py:462
↓ 2 callersClassSVTRNet
modules/SVTR.py:388
↓ 2 callersClassSubSample
modules/SVTR.py:341
↓ 2 callersClassVIPTRNet
modules/VIPTRv2.py:945
↓ 2 callersClassVTPTRNet
modules/VIPTRv1-T_ch.py:881
↓ 2 callersClassVTPTRNet
modules/VIPTRv1.py:881
↓ 1 callersClassAttention
modules/SVTR.py:139
↓ 1 callersClassAttention
modules/VIPTRv1-T_ch.py:334
↓ 1 callersClassAttention
modules/VIPTRv2T_ch.py:327
↓ 1 callersClassAttention
modules/VIPTRv1.py:334
↓ 1 callersClassAttention
modules/prediction.py:7
↓ 1 callersClassAttention
modules/VIPTRv2.py:326
↓ 1 callersClassAttentionCell
modules/prediction.py:61
↓ 1 callersClassBasicLayer
modules/VIPTRv1-T_ch.py:753
↓ 1 callersClassBasicLayer
modules/VIPTRv2T_ch.py:682
↓ 1 callersClassBasicLayer
modules/VIPTRv1.py:753
↓ 1 callersClassBasicLayer
modules/VIPTRv2.py:739
↓ 1 callersClassBatch_Balanced_Dataset
dataset.py:17
↓ 1 callersClassCSWinBlock
modules/VIPTRv1-T_ch.py:673
↓ 1 callersClassCSWinBlock
modules/VIPTRv2T_ch.py:602
↓ 1 callersClassCSWinBlock
modules/VIPTRv1.py:673
↓ 1 callersClassCTCLabelConverterForBaiduWarpctc
Convert between text-label and text-index for baidu warpctc
utils.py:56
↓ 1 callersClassConfig
Config
dataload/dataAug.py:187
↓ 1 callersClassConvMixer
modules/SVTR.py:112
↓ 1 callersClassCosineAnnealingLR
optimizer.py:109
↓ 1 callersClassDCTC
modules/dctc_loss.py:7
↓ 1 callersClassFeedForwardNetwork
modules/VIPTRv1-T_ch.py:268
↓ 1 callersClassFeedForwardNetwork
modules/VIPTRv2T_ch.py:262
↓ 1 callersClassFeedForwardNetwork
modules/VIPTRv1.py:268
↓ 1 callersClassFeedForwardNetwork
modules/VIPTRv2.py:262
↓ 1 callersClassGRCL_unit
modules/feature_extraction.py:95
↓ 1 callersClassGridGenerator
Grid Generator of RARE, which produces P_prime by multipling T with P
modules/transformation.py:86
↓ 1 callersClassIdentity
modules/SVTR.py:80
↓ 1 callersClassLePEAttention
modules/VIPTRv1-T_ch.py:587
↓ 1 callersClassLePEAttention
modules/VIPTRv2T_ch.py:515
↓ 1 callersClassLePEAttention
modules/VIPTRv1.py:587
↓ 1 callersClassLePEAttention
modules/VIPTRv2.py:574
↓ 1 callersClassLmdbDataset
dataset.py:129
↓ 1 callersClassLocalizationNetwork
Localization Network of RARE, which predicts C' (K x 2) from I (I_width x I_height)
modules/transformation.py:42
↓ 1 callersClassMHSA_Block
modules/VIPTRv1-T_ch.py:367
↓ 1 callersClassMHSA_Block
modules/VIPTRv1.py:367
↓ 1 callersClassMHSA_Block
modules/VIPTRv2.py:358
↓ 1 callersClassMaSA
modules/VIPTRv1-T_ch.py:211
↓ 1 callersClassMaSA
modules/VIPTRv2T_ch.py:206
↓ 1 callersClassMaSA
modules/VIPTRv1.py:211
↓ 1 callersClassMaSA
modules/VIPTRv2.py:206
↓ 1 callersClassMaSAd
modules/VIPTRv1-T_ch.py:137
↓ 1 callersClassMaSAd
modules/VIPTRv2T_ch.py:133
↓ 1 callersClassMaSAd
modules/VIPTRv1.py:137
↓ 1 callersClassMaSAd
modules/VIPTRv2.py:133
↓ 1 callersClassMlp
modules/SVTR.py:88
↓ 1 callersClassNormalizePAD
dataset.py:270
↓ 1 callersClassOSRA_Attention
modules/VIPTRv1-T_ch.py:412
↓ 1 callersClassOSRA_Attention
modules/VIPTRv1.py:412
↓ 1 callersClassOSRA_Attention
modules/VIPTRv2.py:402
↓ 1 callersClassOSRA_Block
modules/VIPTRv1-T_ch.py:473
↓ 1 callersClassOSRA_Block
modules/VIPTRv2T_ch.py:398
↓ 1 callersClassOSRA_Block
modules/VIPTRv1.py:473
↓ 1 callersClassPatchEmbed
Image to Patch Embedding
modules/SVTR.py:264
↓ 1 callersClassPatchEmbed
modules/VIPTRv1-T_ch.py:852
↓ 1 callersClassPatchEmbed
modules/VIPTRv2T_ch.py:739
↓ 1 callersClassPatchEmbed
modules/VIPTRv1.py:852
↓ 1 callersClassPatchEmbed
modules/VIPTRv2.py:916
↓ 1 callersClassRelPos2d
modules/VIPTRv1-T_ch.py:70
↓ 1 callersClassRelPos2d
modules/VIPTRv1.py:70
↓ 1 callersClassRelPos2d
modules/VIPTRv2.py:67
↓ 1 callersClassResNet
modules/feature_extraction.py:153
↓ 1 callersClassResNet_FeatureExtractor
FeatureExtractor of FAN (http://openaccess.thecvf.com/content_ICCV_2017/papers/Cheng_Focusing_Attention_Towards_ICCV_2017_paper.pdf)
modules/feature_extraction.py:54
↓ 1 callersClassResizeNormalize
dataset.py:256
↓ 1 callersClassRetBlock
modules/VIPTRv1-T_ch.py:514
↓ 1 callersClassRetBlock
modules/VIPTRv1.py:514
↓ 1 callersClassRetBlock
modules/VIPTRv2.py:505
↓ 1 callersClassSTNHead
modules/stn_head.py:23
↓ 1 callersClassTPSSpatialTransformer
modules/tps_spatial_transformer.py:52
↓ 1 callersClassTPS_SpatialTransformerNetwork
Rectification Network of RARE, namely TPS based STN
modules/transformation.py:8
next →1–100 of 124, ranked by callers