wgcban/ChangeFormer

Issues

• Facing issue in downloading the pre trained model on LEVIR dataset

  #110 opened 3 months ago by ayshaashra
  2

• Which algorithm is best for optical data of 1 meter spatial resolution.

  #112 opened 2 months ago by GISScience
  0

• Compatibility issues of CUDA

  #98 opened 7 months ago by ayshaashra
  3

• I need to download preprocessed DSIFN-CD-256 These both links points to same dataset LEVIR-CD-256 please update it

  #111 opened 3 months ago by ayshaashra
  0

• About Focal loss

  #109 opened 4 months ago by kirin-from-16
  0

• Hi, are you interested in participating in the Open-CD TRP program?

  #107 opened 4 months ago by likyoo
  4

• Run the data evaluation file

  #108 opened 5 months ago by BenyaminMoadab
  0

• output is good but metrics do not make sense

  #106 opened 5 months ago by juanfelipegiraldoc
  1

• error link for dataset

  #105 opened 6 months ago by sundongwei
  2

• Something about the pretrained_changeformer.pt file.

  #99 opened 7 months ago by liberty-MCYE
  3

• Both processed dataset links go to the DropBox of LEVIR-CD256.

  #104 opened 7 months ago by sahin01
  2

• Question..

  #103 opened 7 months ago by chartgod
  0

• Is it possible to detect multiple classes?

  #102 opened 7 months ago by chartgod
  4

• What can we do to improve our model on our dataset ?

  #101 opened 7 months ago by daotv119x
  0

• Some questions about image alignment

  #76 opened 8 months ago by DoongLi
  22

• training on LEVIR-CD

  #100 opened 8 months ago by DerowPeng
  6

• The pretrained_changeformer.pt file cannot be downloaded. The URL is invalid.

  #96 opened 8 months ago by wujiang0156
  3

• (change-detection) C:\Users\Administrator\ChangeFormer>pip install -r requirements.txt ERROR: Invalid requirement: '_libgcc_mutex=0.1=main' (from line 16 of requirements.txt) Hint: = is not a valid operator. Did you mean == ?

  #97 opened 8 months ago by ayshaashra
  3

• Can I ask you about input image regularization?

  #95 opened 9 months ago by StorywithLove
  0

• While multiclass, ValueError: cannot reshape array of size 10 into shape (2,2)@wangqingl If you have 10 classes you need to write separate visualizer to visualize all the classes. Since, you removed `pred * 255` your values the `output.png` will be between 0 and 9 - hence you see dark (or black) output. You need to write the visualizer such that it will assign different color values for each predicted output class.

  #93 opened 10 months ago by StorywithLove
  3

• models模块

  #92 opened 10 months ago by kk-kaii
  3

• After setting HalfTensor in order to trained 1024*1024 images, the G_loss of the model is nan.

  #91 opened a year ago by StorywithLove
  1

• How to get this model trained on multiple machines in a distributed manner(like DistributedDataParallel)?

  #90 opened a year ago by StorywithLove
  3

• Loss function

  #89 opened a year ago by wangqingl
  4

• Hello, if I am using a dataset with a size of 512, can I still use your pre trained model?

  #81 opened a year ago by wangqingl
  4

• multi-class datasets issues

  #88 opened a year ago by wangqingl
  2

• Visualizing the inference results

  #80 opened a year ago by hamzagorgulu
  3

• 代码复现

  #79 opened a year ago by wusuowei666
  1

• Inference-issue

  #85 opened a year ago by osamaa1111
  3

• Something for ‘update the best model’

  #86 opened a year ago by Tom-Dongfang
  2

• Does the "predict. py" file exist？

  #87 opened a year ago by FENGJIANJUN99
  1

• Is it feasible to replace the three channel images used for training with six channel images in this model?

  #84 opened a year ago by FENGJIANJUN99
  4

• Hello, Why does your pre trained model occupy over 460 megabytes of memory, while mine only has over 60 megabytes

  #83 opened a year ago by wangqingl
  5

• Hello, If I use my own dataset for training, how should I generate files in the list folder?

  #82 opened a year ago by wangqingl
  4

• Calculation of evaluation index

  #78 opened a year ago by For-Isolate
  7

• python demo_LEVIR.py

  #77 opened a year ago by work1-shekhaman
  1

• the preatrain model load issue

  #70 opened a year ago by money6651626
  3

• About processed dataset download

  #73 opened a year ago by Ozone-oo
  1

• can't download pretrained model pt

  #75 opened a year ago by Busky83
  1

• How to output its prediction plot separately for each test image

  #62 opened a year ago by wulei1595
  3

• ModuleNotFoundError: No module named 'datasets.CD_dataset'

  #71 opened a year ago by arianaa30
  4

• Change detection on indoor environments?

  #72 opened a year ago by arianaa30
  1

• About Dataset Download

  #67 opened a year ago by fbx666
  0

• Getting blank mask while testing pre-trained model with custom image

  #69 opened a year ago by SouravSarkar865
  5

• Query regarding role of label images in the samples_LEVIR folder for making predictions.

  #68 opened a year ago by SouravSarkar865
  2

• Model Unpickling error in Google Colab

  #66 opened a year ago by SouravSarkar865
  4

• why cancel BN and last relu in ResidualBlock？

  #65 opened a year ago by yangjian1218
  4

• Missing key(s) in state_dict for BASE_Transformer.

  #64 opened 2 years ago by itstatev
  2

• License Term

  #63 opened 2 years ago by zaidbhat1234
  1

• 训练过程中的测试结果和单独测试的结果不一致

  #61 opened 2 years ago by IceHowe
  0