Functions — github.com/RolandGao/RegSeg

CodeHub MCPcopy Create free account

hub / github.com/RolandGao/RegSeg / functions

Functions296 in github.com/RolandGao/RegSeg

⨍ Functions 296◇ Types & classes 63

↓ 1 callersFunctionget_epochs_to_save

↓ 1 callersMethodget_link

(self, layer, base_ch, growth_rate, grmul)

competitors_models/hardnet.py:34

↓ 1 callersMethodget_link

(self, layer, base_ch, growth_rate, grmul)

competitors_models/hardnet.py:172

↓ 1 callersFunctionget_lr_function

(config,total_iterations)

train_utils.py:9

↓ 1 callersFunctionget_mapillary

(root, batch_size, train_min_size, train_max_size, train_crop_size, val_input_size,val_label_size, aug_mode, n

↓ 1 callersFunctionget_optimizer

train_utils.py:48

↓ 1 callersFunctionget_val_dataset

train_utils.py:65

↓ 1 callersFunctionload_coco_json

(json_file, image_dir)

datasets/coco.py:8

↓ 1 callersFunctionmax_memory_used

benchmark.py:106

↓ 1 callersFunctionmemory_used

benchmark.py:103

↓ 1 callersFunctionpoly_lr_scheduler

(current_iter, total_iters,warmup_iters,warmup_factor,p=0.9)

lr_schedulers.py:5

↓ 1 callersFunctionpooled_class_centroids_all

Calculate class centroids for all classes for all images for all tiles. items: list of (image_fn, label_fn) tile size: size of tile r

datasets/class_uniform_sampling.py:112

↓ 1 callersFunctionrand_augment_both

Applies random augmentation to an image.

↓ 1 callersFunctionrandom_resizes_random_crops

precise_iou.py:175

↓ 1 callersFunctionreduce_mask

datasets/mapillary.py:6

↓ 1 callersFunctionreproducibility

precise_iou.py:171

↓ 1 callersFunctionsave_cityscapes_results

(config,pred_dir)

↓ 1 callersFunctionsave_results

(pred_dir,file_name, output)

↓ 1 callersFunctionshow_camvid_mask

(images,colors)

↓ 1 callersFunctionshow_cityscapes_model

↓ 1 callersFunctionshow_files

(model,files,device,show_mask,num_images=5,images_per_line=2,mixed_precision=False)

↓ 1 callersFunctionshow_mapillary_mask

(images,reduced=False)

↓ 1 callersFunctionstep_lr_scheduler

(current_iter, total_iters,warmup_iters,warmup_factor)

lr_schedulers.py:26

↓ 1 callersFunctiontrain_main

↓ 1 callersFunctiontrain_multiple

↓ 1 callersFunctiontrain_one_epoch

(model, loss_fun, optimizer, loader, lr_scheduler, print_every, mixed_precision, scaler)

↓ 1 callersFunctiontraining_techniques

precise_iou.py:179

↓ 1 callersFunctionvalidate_main

↓ 1 callersFunctionvisualize_aug

Visualize augmentation by applying random augmentations.

↓ 1 callersFunctionvisualize_ops

Visualize ops by applying each op by varying amounts.

↓ 1 callersFunctionvisualize_opsXops

(im, ops, magnitude)

(self, image, label)

transforms.py:19

(self, image, target)

transforms.py:34

(self, image, target)

transforms.py:48

(self, image, label)

transforms.py:60

(self, image, target)

transforms.py:68

(self, image, target)

transforms.py:83

(self, image, target)

transforms.py:108

(self, image, target)

transforms.py:119

(self, image, target)

transforms.py:135

(self, image, target)

transforms.py:149

(self, image, target)

transforms.py:167

(self, image, label)

transforms.py:210

(self, image, label)

transforms.py:234

(self, image, label)

transforms.py:267

(self, image, target)

transforms.py:289

Method__getitem__

datasets/voc12.py:36

Method__getitem__

datasets/camvid.py:41

Method__getitem__

datasets/coco.py:88

Method__getitem__

Args: index (int): Index Returns: tuple: (image, target) where target is a tuple of all target types if targe

datasets/cityscapes.py:129

Method__getitem__

datasets/mapillary.py:45

(self, num_classes, exclude_classes)

(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, dilation=1, groups=1, b

(self, w_in, w_se)

(self, in_channels, out_channels, stride=1, avg_downsample=False)

(self,w,dilations,group_width,stride,bias)

(self,w,stride,dilation,groups,bias)

(self, in_channels, out_channels, dilations,group_width, stride,attention="se")

(self, num_classes,channels,inter_channels=128)

(self, num_classes,channels)

(self, num_classes,channels)

(self, num_classes, channels)

(self, num_classes, channels)

(self, num_classes, channels)

(self, num_classes, channels)

(self, transforms)

transforms.py:16

(self,N,M,ops,prob,fill,ignore_value)

transforms.py:40

(self, mean, std)

transforms.py:56

(self,val_input_size,val_label_size)

transforms.py:65

(self, min_size, max_size, sampling_mode)

transforms.py:76

(self,brightness=0.2, contrast=0.2, saturation=(0.5,4), hue=0.2, prob=0.5)

transforms.py:105

(self,factor, prob=0.5)

transforms.py:116

(self,factor, prob=0.5)

transforms.py:132

(self,factor, prob=0.5)

transforms.py:146

(self,degrees,mean,ignore_value, prob,expand=False)

transforms.py:161

(self,crop_h, crop_w, pad_value, ignore_label, random_pad)

transforms.py:204

(self, crop_h, crop_w, pad_value, ignore_label, random_pad, edge_aware)

transforms.py:226

(self, crop_h, crop_w, edge_aware)

transforms.py:262

(self, flip_prob)

transforms.py:286

(self, inplane, outplane)

competitor_blocks.py:38

(self, in_chan, out_chan)

competitor_blocks.py:74

(self, in_chan, out_chan)

competitor_blocks.py:85

(self, in_chan, out_chan)

competitor_blocks.py:102

(self,in_channels, out_channels, kernel_size, stride, padding, dilation=1, deformable_groups=1)

competitor_blocks.py:117

(self, in_nc=128, out_nc=128)

competitor_blocks.py:139

(self, num_classes, channels)

competitor_blocks.py:153

(self, num_classes, channels, fpn_dim=64, fpn_dsn=False)

competitor_blocks.py:181

(self, num_classes, channels)

competitor_blocks.py:208

(self, min_K, loss_th, ignore_index)

(self, name, num_classes, pretrained="", ablate_decoder=False,change_num_classes=False)

(self, in_channels, out_channels, kernel=3, stride=1, dropout=0.1)

competitors_models/hardnet.py:10

(self, in_channels, growth_rate, grmul, n_layers, dwconv=False)

competitors_models/hardnet.py:56

(self, in_channels, growth_rate, grmul, n_layers, keepBase=False, residual_out=False)

competitors_models/hardnet.py:194

(self, in_channels, out_channels)

competitors_models/hardnet.py:240

(self, n_classes=19)

competitors_models/hardnet.py:257

(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, dilation=1, groups=1, b

competitors_models/DDRNet_Reimplementation.py:15

(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, dilation=1, groups=1, b

competitors_models/DDRNet_Reimplementation.py:32

← previous next →101–200 of 296, ranked by callers