Types & classes — github.com/CHENGY12/DMML

CodeHub MCPcopy Create free account

hub / github.com/CHENGY12/DMML / types & classes

Types & classes10 in github.com/CHENGY12/DMML

⨍ Functions 54 ◇ Types & classes 10

↓ 3 callersClassresnet_model

↓ 2 callersClassDukeMTMC_reID

DukeMTMC-reID dataset for person re-identification.

↓ 2 callersClassMarket1501

Market-1501 dataset for person re-identification.

data/market1501.py:9

↓ 2 callersClassTripletLoss

Batch hard triplet loss.

loss/triplet.py:11

↓ 1 callersClassContrastiveLoss

Batch hard contrastive loss.

loss/contrastive.py:10

↓ 1 callersClassDMMLLoss

DMML loss with center support distance and hard mining distance. Args: num_support: the number of support samples per class.

loss/dmml.py:10

↓ 1 callersClassLiftedLoss

loss/lifted.py:7

↓ 1 callersClassNpairLoss

Multi-class N-pair loss. Args: reg_lambda: L2 norm regularization for embedding vectors.

loss/npair.py:6

↓ 1 callersClassRandomErasing

Randomly selects a rectangle region in an image and erases its pixels. 'Random Erasing Data Augmentation' by Zhong et al. See https://ar

data/random_erasing.py:5

↓ 1 callersClassRandomSampler

Randomly sample M classes with K instances in each class.

data/sampler.py:7