Computes and stores the average and current value. Code imported from https://github.com/pytorch/examples/blob/master/imagenet/main.py#

Basic convolutional block: convolution + batch normalization + relu. Args (following http://pytorch.org/docs/master/nn.html#torch.nn.Conv2d):

Basic convolutional block: convolution + batch normalization + relu. Args (following http://pytorch.org/docs/master/nn.html#torch.nn.Conv2d):

Image Person ReID Dataset

Write console output to external text file. Code imported from https://github.com/Cysu/open-reid/blob/master/reid/utils/logging.py.

Args: in_channels (int): number of input channels. s1_channels (int): number of 1-by-1 filters for squeeze layer. e1_chan

Cross entropy loss with label smoothing regularizer. Reference: Szegedy et al. Rethinking the Inception Architecture for Computer Vision. CVP

Args: in_channels (int): number of input channels out_channels (int): number of output channels AFTER concatenation

Basic convolutional block: convolution + batch normalization + relu. Args (following http://pytorch.org/docs/master/nn.html#torch.nn.Conv2d):

Basic convolutional block: convolution (bias discarded) + batch normalization + relu6. Args (following http://pytorch.org/docs/master/nn.html

Video Person ReID Dataset. Note batch data has shape (batch, seq_len, channel, height, width).

Harmonious Attention (Sec. 3.1)

Args: in_channels (int): number of input channels out_channels (int): number of output channels AFTER concatenation

Basic convolutional block: convolution (bias discarded) + batch normalization + relu6. Args (following http://pytorch.org/docs/master/nn.html

NASNetAMobile (4 @ 1056)

Randomly sample N identities, then for each identity, randomly sample K instances, therefore batch size is N*K. Code imported from https

Triplet loss with hard positive/negative mining. Reference: Hermans et al. In Defense of the Triplet Loss for Person Re-Identification. arXiv

Center loss. Reference: Wen et al. A Discriminative Feature Learning Approach for Deep Face Recognition. ECCV 2016. Args:

Channel Attention (Sec. 3.1.I.2)

Preprocessing layers.

Saliency-based learning fusion layer (Sec.3.2)

Hard Attention (Sec. 3.1.II)

Image Person ReID Dataset

Multi-scale stream layer A (Sec.3.1)

Multi-scale stream layer B (Sec.3.1)

Reduction layer (Sec.3.1)

This model is not used

Ring loss. Reference: Zheng et al. Ring loss: Convex Feature Normalization for Face Recognition. CVPR 2018.

Soft Attention (Sec. 3.1.I) Aim: Spatial Attention + Channel Attention Output: attention maps with shape identical to input.

Spatial Attention (Sec. 3.1.I.1)

Selectable global pooling layer with dynamic input kernel size

Base class for bottlenecks that implements `forward()` method.

CUHK01 Reference: Li et al. Human Reidentification with Transferred Metric Learning. ACCV 2012. URL: http://www.ee.cuhk.edu.hk/~xgw

CUHK03 Reference: Li et al. DeepReID: Deep Filter Pairing Neural Network for Person Re-identification. CVPR 2014. URL: http://www.e

DukeMTMCVidReID Reference: Wu et al. Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learni

DukeMTMC-reID Reference: 1. Ristani et al. Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. ECCVW 2016.

GRID Reference: Loy et al. Multi-camera activity correlation analysis. CVPR 2009. URL: http://personal.ie.cuhk.edu.hk/~ccloy/downlo

Harmonious Attention Convolutional Neural Network Reference: Li et al. Harmonious Attention Network for Person Re-identification. CVPR 2

MSMT17 Reference: Wei et al. Person Transfer GAN to Bridge Domain Gap for Person Re-Identification. CVPR 2018. URL: http://www.pkuv

Market1501 Reference: Zheng et al. Scalable Person Re-identification: A Benchmark. ICCV 2015. URL: http://www.liangzheng.org/Projec

MARS Reference: Zheng et al. MARS: A Video Benchmark for Large-Scale Person Re-identification. ECCV 2016. URL: http://www.liangzhen

MobileNetV2 Reference: Sandler et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks. CVPR 2018.

Multiscale deep neural network. Reference: Qian et al. Multi-scale Deep Learning Architectures for Person Re-identification. ICCV 2017.

PRID2011 Reference: Hirzer et al. Person Re-Identification by Descriptive and Discriminative Classification. SCIA 2011. URL: https:

PRID450S Reference: Roth et al. Mahalanobis Distance Learning for Person Re-Identification. PR 2014. URL: https://www.tugraz.at/ins

With a probability, first increase image size to (1 + 1/8), and then perform random crop. Args: height (int): target height.