NVlabs/DG-Net

Issues

• why detach the gradient of appearance codes?

  #80 opened 6 months ago by SDret
  4

• test_2label报错 yaml.load()缺少 loader

  #79 opened a year ago by taqta
  2

• 基于teacher model训练，使用数据集MSMT，方便提供下config嘛

  #57 opened 4 years ago by wqq19930507
  9

• online feeding and identity supervision

  #78 opened a year ago by Wooks-git
  3

• appearance code and structure code

  #77 opened 2 years ago by Wooks-git
  1

• ModuleNotFoundError: No module named 'torch.utils.hipify'

  #45 opened 4 years ago by Dtappledoghuati
  6

• 如何采用训练好的模型去生成图片

  #65 opened 2 years ago by SeibertronSS
  1

• how does two different networks extract appearance and clothing separately?

  #76 opened 2 years ago by lakshaydulani
  0

• Run DG-Net on Nvidia Jetson Nano

  #34 opened 4 years ago by pablovicentem
  2

• IndexError:Dimension out of range(excepted to be in range of [-1,0],but got 1)

  #75 opened 2 years ago by aiqiangbrave
  4

• Why the "val" data-set is subset of "train" data-set?

  #36 opened 4 years ago by bhooshan-supe-gmail
  12

• 关于inception score

  #73 opened 2 years ago by zichihuanian
  1

• 关于FID计算

  #74 opened 2 years ago by zichihuanian
  4

• A question about the ”appearance code”

  #55 opened 3 years ago by BoomShakaY
  3

• when I run train.py, print there error message. Can you help to solve the issue? Thank you !

  #72 opened 3 years ago by yuanqs
  1

• Out of memory error while training the model

  #71 opened 3 years ago by Haneesha123
  1

• test_folder

  #70 opened 3 years ago by bixiaopeng0
  1

• How to use DG-Net for vehicle reid?

  #69 opened 3 years ago by twj1999
  2

• Doubt about dis_opt and gen_opt

  #68 opened 3 years ago by songbo0925
  2

• in trainer.py /gen_update(), i cannot understand "encoder is tuned, input is fixed" and "encoder is fixed, input is tuned"

  #67 opened 3 years ago by wdf19961118
  1

• Can you share the trained models on the dataset MSMT17 and the dataset MSMT17?

  #52 opened 4 years ago by Be-yourself-zxy
  2

• How to test accuracy.

  #66 opened 3 years ago by LiMxStar
  1

• doubt about a loss in the ‘gen_update’

  #63 opened 3 years ago by 5Yesterday
  2

• DG-Net_Trainer类的forward函数的一个疑问

  #64 opened 4 years ago by RuriApoka
  1

• From my training logs, the TEACHER is always 0. Is that normal?

  #47 opened 4 years ago by y122302868
  3

• Change the data set to train

  #62 opened 4 years ago by zbx-hue
  3

• Failed to converge

  #60 opened 4 years ago by iyu-Fang
  9

• Train fp16 interrupt

  #61 opened 4 years ago by 5Yesterday
  3

• 请问这个GEN只针对market数据吗

  #56 opened 4 years ago by guanyonglai
  6

• What should I do if I want to switch to another dataset, such as Duke and MSMT17?Does the teacher model need to be retrained?

  #46 opened 4 years ago by Be-yourself-zxy
  5

• how to train a teacher model

  #50 opened 4 years ago by ganyibo
  1

• Can you share the trained models on the dataset DukeMTMC-reID?

  #51 opened 4 years ago by YuanXinCherry
  2

• Question about alpha

  #54 opened 4 years ago by exityan
  1

• issue with 'net_last.pth'

  #58 opened 4 years ago by khodabakhshih
  5

• A question about setting f=f.detach() in ft_netAB

  #59 opened 4 years ago by RainbowShirlley
  1

• A question about the loss (6) in the paper

  #53 opened 4 years ago by Xiaofu233
  1

• Reconstruction id embedding loss after detach

  #49 opened 4 years ago by juliendenize
  7

• How is it made sure that the image returned from train_loader_a and train_loader_b is of different identity?

  #42 opened 4 years ago by chaitrasj
  1

• Interpreting the results of the score in evaluate_gpu.py

  #48 opened 4 years ago by ksuhartono97
  2

• Some questions about the appearance space and the structure space

  #37 opened 4 years ago by SY-Xuan
  8

• The training settings and teacher models of training in DukeMTMC and MSMT17.

  #44 opened 4 years ago by KiritoHugh
  1

• How to change image name output in 'test_folder.py'

  #43 opened 4 years ago by pydxflwb
  2

• using feature matrix to calculate loss?

  #41 opened 4 years ago by yian2271368
  4

• did you resize MSMT17 images to the same size while you training them?

  #38 opened 4 years ago by yian2271368
  8

• Some questions about the model structure and the reappearance of the results.

  #39 opened 4 years ago by Liu-1994
  4

• Some questions about the detach of the f in the ft_netAB

  #40 opened 4 years ago by Liu-1994
  6

• Regarding sampling code for visualisation of images

  #35 opened 4 years ago by asthaverma13
  2

• When I use another dataset，The generated data is not as much as the original data

  #32 opened 4 years ago by CWF-999
  1

• someone use this repository in industrial circles？

  #33 opened 4 years ago by bujianyiwang
  0

• size mismatch

  #31 opened 4 years ago by 869250498
  7