MCPcopy Create free account

hub / github.com/csxmli2016/MARCONetPlusPlus / functions

Functions135 in github.com/csxmli2016/MARCONetPlusPlus

⨍ Functions 135◇ Types & classes 38
↓ 10 callersMethod__init__
(self, num_in, block, layers)
networks/transocr_arch.py:42
↓ 7 callersMethod__init__
(self, in_channel, style_dim, upsample=True, blur_kernel=[1, 3, 3, 1])
networks/prior_arch.py:288
↓ 6 callersFunctionadaptive_instance_normalization
(prior_feat, lq_feat)
networks/helper_arch.py:50
↓ 5 callersMethod_make_layer
(self, block, planes, blocks, stride=1)
networks/psp_encoder_arch.py:87
↓ 5 callersMethod_make_layer
(self, block, planes, blocks, stride=1)
networks/w_encoder_arch.py:70
↓ 5 callersFunctiondownload_file_from_github
Load file form http url, will download models if necessary. Reference: https://github.com/1adrianb/face-alignment/blob/master/face_alignment/util
utils/download_github.py:6
↓ 4 callersMethod_make_layer
(self, block, inplanes, planes, blocks)
networks/transocr_arch.py:78
↓ 4 callersFunctionconv2d_gradfix
( transpose, weight_shape, stride, padding, output_padding, dilation, groups )
op/conv2d_gradfix.py:104
↓ 4 callersFunctionensure_tuple
(xs, ndim)
op/conv2d_gradfix.py:95
↓ 3 callersFunctionget_parameter_details
(net)
models/TextEnhancement.py:42
↓ 2 callersFunctionGroupNorm
(in_channels)
networks/helper_arch.py:6
↓ 2 callersFunctionGroupNorm
(in_channels)
networks/w_encoder_arch.py:140
↓ 2 callersMethod__init__
(self, nf, gc=32, bias=True)
networks/rrdbnet2_arch.py:39
↓ 2 callersMethod_process_text_line
Process a single text line region for text enhancement. Args: img: Input text image
models/TextEnhancement.py:208
↓ 2 callersFunctioncalc_mean_std_4D
(feat, eps=1e-6)
networks/helper_arch.py:40
↓ 2 callersFunctioncalc_output_padding
(input_shape, output_shape)
op/conv2d_gradfix.py:122
↓ 2 callersFunctioncould_use_op
(input)
op/conv2d_gradfix.py:78
↓ 2 callersFunctionfused_leaky_relu
(input, bias=None, negative_slope=0.2, scale=2 ** 0.5)
op/fused_act.py:110
↓ 2 callersFunctionget_alphabet
(alpha_path)
utils/utils_transocr.py:97
↓ 2 callersFunctionmkdir
(path)
utils/utils_image.py:33
↓ 2 callersFunctionswish
(x)
networks/helper_arch.py:11
↓ 2 callersFunctionuint2tensor4
(img)
utils/utils_image.py:74
↓ 1 callersMethod__init__
(self, inplanes, planes, stride=1, downsample=None)
networks/psp_encoder_arch.py:17
↓ 1 callersMethod__init__
(self, block=BasicBlock, layers=[3, 4, 6, 6, 3], strides=[2,1,2,1,2])
networks/w_encoder_arch.py:33
↓ 1 callersMethod_check_outliers_pad
(self, crop_feature, start, end, max_lr_width, center_loc, extend_W)
networks/psp_encoder_arch.py:111
↓ 1 callersFunction_get_paths_from_images
(path)
utils/utils_image.py:22
↓ 1 callersFunction_upsample_add
Upsample and add two feature maps. Args: x: (Variable) top feature map to be upsampled. y: (Variable) lateral feature map. Ret
networks/psp_encoder_arch.py:271
↓ 1 callersFunctionattention
(query, key, value, mask=None, dropout=None, align=None)
networks/transocr_arch.py:195
↓ 1 callersFunctionclones
(module, N)
networks/transocr_arch.py:130
↓ 1 callersFunctionconv1x1
(in_planes, out_planes, stride=1)
networks/psp_encoder_arch.py:259
↓ 1 callersFunctionconv1x1
(in_planes, out_planes, stride=1)
networks/w_encoder_arch.py:144
↓ 1 callersFunctionconv3x3
3x3 convolution with padding
networks/psp_encoder_arch.py:263
↓ 1 callersFunctionconv3x3
3x3 convolution with padding
networks/w_encoder_arch.py:148
↓ 1 callersFunctionget_image_paths
(dataroot)
utils/utils_image.py:15
↓ 1 callersFunctionget_yolo_ocr_xloc
Detect character bounding boxes and recognize characters in an image using YOLO and OCR. Parameters: img_path (str): Path to the inp
utils/yolo_ocr_xloc.py:7
↓ 1 callersMethodhandle_texts
Parameters: img: RGB 0~255.
models/TextEnhancement.py:89
↓ 1 callersFunctionimread_uint
(path, n_channels=3)
utils/utils_image.py:48
↓ 1 callersFunctioninference
(input_path=None, output_path=None, aligned=False, bg_sr=False, scale_factor=2, save_text=False, device=None)
test_marconetplus.py:15
↓ 1 callersFunctioninitialize_weights
(net_l, scale=1)
networks/module_util.py:7
↓ 1 callersFunctionis_image_file
(filename)
utils/utils_image.py:11
↓ 1 callersFunctionnetwork_param
(net)
networks/helper_arch.py:59
↓ 1 callersFunctionstr2idx
(text)
models/TextEnhancement.py:36
↓ 1 callersFunctionsubsequent_mask
(size)
networks/transocr_arch.py:189
↓ 1 callersFunctiontensor2numpy
(tensor)
models/TextEnhancement.py:48
↓ 1 callersFunctiontensor2uint
(img)
utils/utils_image.py:80
↓ 1 callersFunctionupfirdn2d_native
( input, kernel, up_x, up_y, down_x, down_y, pad_x0, pad_x1, pad_y0, pad_y1 )
op/upfirdn2d.py:168
FunctionGroupNorm
(in_channels)
networks/psp_encoder_arch.py:11
FunctionPYBIND11_MODULE
op/fused_bias_act.cpp:30
FunctionPYBIND11_MODULE
op/upfirdn2d.cpp:29
Method__init__
(self, block=BasicBlock, layers=[3, 4, 6, 6, 3], strides=[(2,2),(1,2),(2,2),(1,2),(2,2)])
networks/psp_encoder_arch.py:45
Method__init__
( self, size=128, style_dim=512, n_mlp=8, class_num=6736, lr_m
networks/prior_arch.py:9
Method__init__
( self, size=128, style_dim=512, n_mlp=8, class_num=6736, chan
networks/prior_arch.py:29
Method__init__
(self)
networks/prior_arch.py:130
Method__init__
(self, in_channels, out_channels, bias=True, bias_init_val=0, lr_mul=1, activation=None)
networks/prior_arch.py:149
Method__init__
(self, class_num, channel, size=4)
networks/prior_arch.py:181
Method__init__
( self, in_channel, out_channel, kernel_size, style_dim, upsam
networks/prior_arch.py:200
Method__init__
( self, in_channel, out_channel, kernel_size, style_dim, demod
networks/prior_arch.py:231
Method__init__
(self, nf=64, gc=32, bias=True)
networks/rrdbnet2_arch.py:14
Method__init__
(self, in_nc, out_nc, nf, nb, gc=32, sf=4, bias=True)
networks/rrdbnet2_arch.py:53
Method__init__
(self, nf=64)
networks/module_util.py:40
Method__init__
(self, inplanes, planes, downsample)
networks/transocr_arch.py:12
Method__init__
(self, d_model, dropout, max_len=7000)
networks/transocr_arch.py:136
Method__init__
(self, h, d_model, dropout=0.1, compress_attention=False)
networks/transocr_arch.py:156
Method__init__
(self, features, eps=1e-6)
networks/transocr_arch.py:214
Method__init__
(self, d_model, d_ff, dropout=0.1)
networks/transocr_arch.py:228
Method__init__
(self, d_model, vocab, norm=False)
networks/transocr_arch.py:240
Method__init__
(self, d_model, vocab)
networks/transocr_arch.py:254
Method__init__
(self, dim, num_heads, ff_dim, dropout)
networks/transocr_arch.py:265
Method__init__
(self)
networks/transocr_arch.py:284
Method__init__
(self, word_n_class=6738, use_bbox=False)
networks/transocr_arch.py:314
Method__init__
(self, in_channels, out_channels=None)
networks/helper_arch.py:15
Method__init__
(self, in_channel=3, dim_channel=256)
networks/sr_arch.py:9
Method__init__
(self, inplanes, planes, stride=1, downsample=None)
networks/w_encoder_arch.py:9
Method__init__
(self, in_channel=3, dim_channel=256)
networks/sr_arch_singlec.py:9
Method__init__
(self, channel, bias=True, negative_slope=0.2, scale=2 ** 0.5)
op/fused_act.py:94
Method__init__
(self, WEncoderPath=None, PriorModelPath=None, SRModelPath=None, YoloPath=None, device='cuda')
models/TextEnhancement.py:55
Method_check_outliers
(self, crop_feature, target_width)
networks/psp_encoder_arch.py:104
Method_check_outliers
(self, crop_feature, target_width)
networks/w_encoder_arch.py:87
Function_upsample_add
Upsample and add two feature maps. Args: x: (Variable) top feature map to be upsampled. y: (Variable) lateral feature map. Ret
networks/w_encoder_arch.py:156
Methodbackward
(ctx, gradgrad_input, gradgrad_bias)
op/fused_act.py:47
Methodbackward
(ctx, grad_output)
op/fused_act.py:80
Methodbackward
(ctx, gradgrad_input)
op/upfirdn2d.py:64
Methodbackward
(ctx, grad_output)
op/upfirdn2d.py:128
Methodbackward
(ctx, grad_output)
op/conv2d_gradfix.py:154
Methodbackward
(ctx, grad_grad_weight)
op/conv2d_gradfix.py:205
Functionconv2d
(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1)
op/conv2d_gradfix.py:22
Functionconv_transpose2d
( input, weight, bias=None, stride=1, padding=0, output_padding=0, groups=1
op/conv2d_gradfix.py:45
Functionconverter
(label)
utils/utils_transocr.py:6
Functionconverter_ocr
(label)
utils/utils_transocr.py:69
Functionconverter_ocr_bbox
(label, loc_str_tuple)
utils/utils_transocr.py:38
Methodforward
(self, x)
networks/psp_encoder_arch.py:29
Methodforward
(self, x, locs)
networks/psp_encoder_arch.py:129
Methodforward
(self, styles, labels, noise)
networks/prior_arch.py:25
Methodforward
( self, styles, labels, noise=None, )
networks/prior_arch.py:95
Methodforward
(self, input)
networks/prior_arch.py:133
Methodforward
(self, x)
networks/prior_arch.py:166
Methodforward
(self, labels)
networks/prior_arch.py:185
Methodforward
(self, input, style, noise=None)
networks/prior_arch.py:222
Methodforward
(self, input, style)
networks/prior_arch.py:263
Methodforward
(self, input, style, skip=None)
networks/prior_arch.py:295
next →1–100 of 135, ranked by callers