MCPcopy Create free account

hub / github.com/SeanChenxy/TSSD-OTA / functions

Functions139 in github.com/SeanChenxy/TSSD-OTA

⨍ Functions 139◇ Types & classes 39
Method__init__
(self, mean)
utils/augmentations.py:313
Method__init__
(self, swaps)
utils/augmentations.py:358
Method__init__
(self)
utils/augmentations.py:377
Method__init__
(self, size=300, mean=(104, 117, 123))
utils/augmentations.py:401
Method__init__
(self, size=300, mean=(104, 117, 123))
utils/augmentations.py:420
Method__init__
(self, root, image_sets, transform, dataset_name='MOT17Det', seq_len=8, skip=False)
data/mot.py:15
Method__init__
(self, size, mean)
data/__init__.py:17
Method__init__
(self, class_to_ind=None, keep_difficult=False, dataset_name='VOC0712')
data/voc0712.py:114
Method__init__
(self, root, image_sets, transform=None, target_transform=None, dataset_name='VOC0712', set_f
data/voc0712.py:176
Method__init__
(self, dim, cuda=True)
layers/modules/attention_loss.py:7
Method__init__
(self,n_channels, scale)
layers/modules/l2norm.py:8
Method__init__
(self, num_classes, overlap_thresh, prior_for_matching, bkg_label, neg_mining, neg_pos, neg_o
layers/modules/multibox_loss.py:121
Method__init__
(self, num_classes, bkg_label, top_k, conf_thresh, nms_thresh, tub=0, tub_thresh=1.0, tub_generate_score=0.7)
layers/functions/detection.py:15
Method__init__
(self, cfg)
layers/functions/prior_box.py:14
Method__len__
(self)
data/mot.py:56
Method__len__
(self)
data/voc0712.py:224
Functioncenter_size
Convert prior_boxes to (cx, cy, w, h) representation for comparison to center-size form ground truth data. Args: boxes: (tensor) poin
layers/box_utils.py:16
Functionconv_weights_init
(m)
train.py:235
Functiondetection_collate
Custom collate fn for dealing with batches of images that have a different number of associated object annotations (bounding boxes). Argument
data/voc0712.py:411
Methodforward
(self, feats)
ssd.py:151
Methodforward
(self, input_, prev_state)
ssd.py:169
Methodforward
(self, input, hidden)
ssd.py:230
Methodforward
(self, tx, state=None, init_tub=False)
ssd.py:295
Methodforward
(self, att_map, masks=None, viz=False)
layers/modules/attention_loss.py:16
Methodforward
(self, x)
layers/modules/l2norm.py:19
Methodforward
Multibox Loss Args: predictions (tuple): A tuple containing loc preds, conf preds, and prior boxes from SSD net.
layers/modules/multibox_loss.py:47
Methodforward
(self, seq_predictions, targets)
layers/modules/multibox_loss.py:143
Methodforward
Args: loc_data: (tensor) Loc preds from loc layers Shape: [batch,num_priors*4] conf_data: (tensor) Sh
layers/functions/detection.py:37
Methodforward
(self)
layers/functions/prior_box.py:33
Functionhalf_decode
Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo
layers/box_utils.py:159
Methodinit_state
(self, input_)
ssd.py:207
Methodload_weights
(self, base_file)
ssd.py:422
Functionorthogonal_weights_init
(m)
train.py:240
Methodpull_anno
Returns the original annotation of image at index Note: not using self.__getitem__(), as any transformations passed in could mess up
data/voc0712.py:380
Methodpull_tensor
Returns the original image at an index in tensor form Note: not using self.__getitem__(), as any transformations passed in could mess
data/voc0712.py:397
Functionseq_detection_collate
Custom collate fn for dealing with batches of images that have a different number of associated object annotations (bounding boxes). Argument
data/voc0712.py:432
Functionstr2bool
(v)
eval.py:33
Functionstr2bool
(v)
train.py:18
Functionweights_init
(m)
train.py:230
← previous101–139 of 139, ranked by callers