Functions — github.com/WenjiaWang0312/TextZoom

hub / github.com/WenjiaWang0312/TextZoom / functions

Functions304 in github.com/WenjiaWang0312/TextZoom

⨍ Functions 304◇ Types & classes 87

↓ 17 callersMethodeval

(self, model, val_loader, image_crit, index, aster, aster_info)

src/interfaces/super_resolution.py:121

↓ 13 callersMethodencode

Support batch or single str. Args: text (str or list of str): texts to convert. Returns: torch.IntTensor [le

src/utils/util.py:46

↓ 11 callersFunctionget_str_list

(output, target, dataset=None)

src/utils/metrics.py:20

↓ 10 callersFunctionstr_filt

(str_, voc_type)

src/utils/util.py:12

↓ 9 callersFunctionbuf2PIL

(txn, key, type='RGB')

src/dataset/dataset.py:41

↓ 9 callersMethoddecode

Decode encoded texts back into strs. Args: torch.IntTensor [length_0 + length_1 + ... length_{n - 1}]: encoded texts.

src/utils/util.py:70

↓ 8 callersFunctionwriteCache

(env, cache)

src/dataset/create_lmdb.py:56

↓ 7 callersFunctioncreateDataset

Create LMDB dataset for CRNN training. ARGS: outputPath : LMDB output path imagePathList : list of image path labelList

src/dataset/create_lmdb.py:184

↓ 6 callersFunction_lexicon_search

(lexicon, word)

src/utils/metrics.py:71

↓ 6 callersFunctionconv3x3_block

3x3 convolution with padding

src/model/recognizer/stn_head.py:14

↓ 6 callersMethodparse_aster_data

(self, imgs_input)

src/interfaces/base.py:307

↓ 5 callersMethod__init__

(self, imgH, nc, nclass, nh, BidirDecoder=False, CUDA=True)

src/model/moran/asrn_res.py:216

↓ 5 callersMethod_make_layer

(self, planes, blocks, stride)

src/model/recognizer/resnet_aster.py:99

↓ 5 callersMethod_make_layer

(self,c_in,c_out,stride,repeat=3)

src/model/moran/asrn_res.py:198

↓ 4 callersMethod__init__

(self, )

src/model/net.py:111

↓ 4 callersMethod__init__

(self, scale_factor=2, width=128, height=32, STN=False, srb_nums=5, mask=True, hidden_units=32)

src/model/tsrn.py:18

↓ 4 callersMethod__init__

(self, nf, gc=32)

src/model/rrdb.py:41

↓ 4 callersFunction_normalize_text

(text)

src/utils/metrics.py:15

↓ 4 callersMethodadd

(self, v)

src/utils/util.py:114

↓ 4 callersFunctionto_numpy

(tensor)

src/utils/labelmaps.py:63

↓ 3 callersMethodAster_init

(self)

src/interfaces/base.py:295

↓ 3 callersMethod__init__

(self, root=None, voc_type='upper', max_len=31, test=True)

src/dataset/dataset.py:51

↓ 3 callersMethod__init__

(self, scale_factor=2, STN=False, width=128, height=32, mask=False)

src/model/srresnet.py:14

↓ 3 callersMethod__init__

(self, nf, gc=32)

src/model/esrgan.py:42

↓ 3 callersMethod__init__

(self, nChannels, nDenselayer, growthRate)

src/model/rdn.py:36

↓ 3 callersFunctioncreate_window

(window_size, channel)

src/utils/ssim_psnr.py:23

↓ 3 callersMethodgenerator_init

(self)

src/interfaces/base.py:116

↓ 3 callersFunctionmain

()

src/utils/calculate_PSNR_SSIM.py:12

↓ 3 callersMethodparse_crnn_data

(self, imgs_input)

src/interfaces/base.py:287

↓ 3 callersMethodparse_moran_data

(self, imgs_input)

src/interfaces/base.py:264

↓ 3 callersFunctionssim

(img1, img2)

src/utils/calculate_PSNR_SSIM.py:78

↓ 3 callersFunctionto_contiguous

(tensor)

src/model/recognizer/sequenceCrossEntropyLoss.py:8

↓ 2 callersMethodCRNN_init

(self)

src/interfaces/base.py:279

↓ 2 callersMethodMORAN_init

(self)

src/interfaces/base.py:244

↓ 2 callersFunctionPIL2buf

(im)

src/dataset/create_lmdb.py:36

↓ 2 callersMethod__init__

(self, scale_factor=2)

src/model/edsr.py:36

↓ 2 callersMethod__init__

(self, scale_factor=2, in_planes=3, STN=False, width=128, height=32)

src/model/lapsrn.py:58

↓ 2 callersMethod__init__

(self, sDim, xDim, yDim, attDim)

src/model/attention_recognition_head.py:230

↓ 2 callersMethod__init__

(self, sDim, xDim, yDim, attDim)

src/model/recognizer/attention_recognition_head.py:235

↓ 2 callersFunction_ssim

(img1, img2, window, window_size, channel, size_average=True)

src/utils/ssim_psnr.py:30

↓ 2 callersFunctionbgr2ycbcr

same as matlab rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

src/utils/calculate_PSNR_SSIM.py:122

↓ 2 callersFunctioncompute_partial_repr

(input_points, control_points)

src/model/recognizer/tps_spatial_transformer.py:25

↓ 2 callersFunctionconv1x1

1x1 convolution

src/model/recognizer/resnet_aster.py:18

↓ 2 callersFunctionconv_block

(in_channels, out_channels, kernel_size=3, stride=1, dilation=1, groups=1, bias=True, act_type=

src/model/esrgan.py:89

↓ 2 callersFunctionconv_block

(in_channels, out_channels, kernel_size=3, stride=1, dilation=1, groups=1, bias=True, act_type=

src/model/rrdb.py:84

↓ 2 callersFunctioncreateDataset_detection

Create LMDB dataset for CRNN training. ARGS: outputPath : LMDB output path imagePathList : list of image path labelList

src/dataset/create_lmdb.py:69

↓ 2 callersMethodget_test_data

(self, dir_)

src/interfaces/base.py:100

↓ 2 callersMethodgradient_map

(x)

src/loss/image_loss.py:39

↓ 2 callersMethodgradient_map

(self, x)

src/loss/gradient_loss.py:21

↓ 2 callersMethodinit_weights

(self, module)

src/model/recognizer/stn_head.py:56

↓ 2 callersMethodmake_layer

(self, block)

src/model/lapsrn.py:101

↓ 2 callersMethodsave_checkpoint

(self, netG, epoch, iters, best_acc_dict, best_model_info, is_best, converge_list)

src/interfaces/base.py:226

↓ 2 callersMethodtensor_size

(t)

src/loss/percptual_loss.py:46

↓ 1 callersMethod__init__

(self, scale_factor=2, in_planes=3, width=32, height=128, STN=False)

src/model/vdsr.py:22

↓ 1 callersMethod__init__

(self, imgH, nc, nclass, nh, n_rnn=2, leakyRelu=False)

src/model/crnn/crnn.py:25

↓ 1 callersMethod__init__

(self, inplanes, planes, stride=1, downsample=None)

src/model/recognizer/resnet_aster.py:39

↓ 1 callersMethod__init__

(self, config, args)

src/interfaces/base.py:33

↓ 1 callersMethod__init__

(self, gradient=True, loss_weight=[20, 1e-4])

src/loss/image_loss.py:11

↓ 1 callersMethod__init__

(self, tv_loss_weight=1)

src/loss/percptual_loss.py:31

↓ 1 callersMethod__len__

(self)

src/dataset/voc_data.py:57

↓ 1 callersFunction_assert_no_grad

(variable)

src/model/recognizer/sequenceCrossEntropyLoss.py:14

↓ 1 callersMethodbeam_search

(self, x, beam_width, eos)

src/model/recognizer/attention_recognition_head.py:68

↓ 1 callersFunctionbuf2PIL

(txn, key, type='RGB', degree=0)

src/dataset/create_lmdb.py:25

↓ 1 callersFunctionbuild_output_control_points

(num_control_points, margins)

src/model/recognizer/tps_spatial_transformer.py:41

↓ 1 callersFunctioncalculate_psnr

(img1, img2)

src/utils/calculate_PSNR_SSIM.py:68

↓ 1 callersFunctioncalculate_ssim

calculate SSIM the same outputs as MATLAB's img1, img2: [0, 255]

src/utils/calculate_PSNR_SSIM.py:101

↓ 1 callersFunctioncheckImageIsValid

(imageBin)

src/dataset/create_lmdb.py:45

↓ 1 callersFunctionconv3x3

3x3 convolution with padding

src/model/recognizer/resnet_aster.py:12

↓ 1 callersFunctioncreate_from_lmdb

()

src/dataset/create_lmdb.py:479

↓ 1 callersFunctioncrop_rect

(list_bbox)

src/dataset/crop_800k.py:37

↓ 1 callersMethodcumsum

(sequence)

src/dataset/dataset.py:284

↓ 1 callersMethoddemo

(self)

src/interfaces/super_resolution.py:260

↓ 1 callersFunctiongaussian

(window_size, sigma)

src/utils/ssim_psnr.py:18

↓ 1 callersFunctionget_torch_version

Find pytorch version and return it as integers for major and minor versions

src/utils/utils_moran.py:144

↓ 1 callersMethodget_train_data

(self)

src/interfaces/base.py:68

↓ 1 callersFunctionget_upsample_filter

Make a 2D bilinear kernel suitable for upsampling

src/model/lapsrn.py:10

↓ 1 callersMethodget_val_data

(self)

src/interfaces/base.py:89

↓ 1 callersFunctionget_vocabulary

voc_type: str: one of 'LOWERCASE', 'ALLCASES', 'ALLCASES_SYMBOLS'

src/utils/labelmaps.py:6

↓ 1 callersFunctiongrid_sample

(input, grid, canvas = None)

src/model/recognizer/tps_spatial_transformer.py:13

↓ 1 callersFunctiongt_box

(contours)

src/dataset/crop_800k.py:26

↓ 1 callersMethodinit_stn

(self, stn_fc2)

src/model/recognizer/stn_head.py:70

↓ 1 callersFunctionmain

(config, args)

src/main.py:10

↓ 1 callersFunctionmain

(args)

src/dataset/crop_800k.py:57

↓ 1 callersFunctionmake_layer

(block, n_layers)

src/model/esrgan.py:9

↓ 1 callersFunctionmake_layer

(block, n_layers)

src/model/rrdb.py:8

↓ 1 callersMethodmake_layer

(self, block, num_of_layer)

src/model/vdsr.py:50

↓ 1 callersMethodmake_layer

(self, block, num_of_layer)

src/model/edsr.py:72

↓ 1 callersMethodoptimizer_init

(self, model)

src/interfaces/base.py:164

↓ 1 callersFunctionrand_crop

(im)

src/dataset/voc_data.py:24

↓ 1 callersFunctionrand_crop

(im)

src/dataset/create_lmdb.py:17

↓ 1 callersMethodreset

(self)

src/utils/utils_moran.py:126

↓ 1 callersMethodreset

(self)

src/utils/utils_crnn.py:109

↓ 1 callersMethodreset

(self)

src/utils/util.py:125

↓ 1 callersMethodscan

(self, text)

src/utils/utils_moran.py:28

↓ 1 callersFunctionsp_noise

(image, prob)

src/dataset/voc_data.py:32

↓ 1 callersFunctiont_split

(txt)

src/dataset/crop_800k.py:14

↓ 1 callersMethodtest

(self)

src/interfaces/super_resolution.py:174

↓ 1 callersMethodtrain

(self)

src/interfaces/super_resolution.py:29

↓ 1 callersMethodtripple_display

(self, image_in, image_out, image_target, pred_str_lr, pred_str_sr, label_strs, index)

src/interfaces/base.py:170

FunctionAccuracy

(output, target, dataset=None)

src/utils/metrics.py:80

next →1–100 of 304, ranked by callers