ChuhuaW/SGNet.pytorch

Issues

• Big gap between my reproduction and paper's results in JAAD

  #28 opened 2 years ago by CrisCloseTheDoor
  3

• JAAD/PIE checkpoints

  #25 opened 2 years ago by Serenfang
  1

• Why to diff bbox at t from future bbox's of prediction length in "get_target" function of file "jaad_data_layer.py"

  #32 opened 2 years ago by siddiqian-at-ceme
  0

• Additional Features for JAAD/PIE

  #31 opened 2 years ago by siddiqian-at-ceme
  0

• Visualization Code Needed for JAAD and PIE as shown in the paper.

  #30 opened 2 years ago by siddiqian-at-ceme
  0

• SGNet on custom data

  #26 opened 2 years ago by ScorcaF
  1

• Cannot reproduce deterministic results

  #21 opened 3 years ago by HRHLALALA
  7

• ETH/UCY visualization code

  #29 opened 2 years ago by atanas1054
  0

• Deterministic Training of PIE/JAAD

  #13 opened 3 years ago by KSXGroup
  9

• Could you please offer a trained JAAD deterministic model weight?

  #27 opened 2 years ago by CrisCloseTheDoor
  0

• Choosing epochs based on test results?

  #24 opened 3 years ago by thisishale
  2

• training on nuScenes dataset

  #22 opened 3 years ago by orhuntamyigit
  2

• Checkpoints for JAAD/PIE Stochastic prediction

  #23 opened 3 years ago by werdnabae
  0

• has the file of train_deterministic.py been delete from git

  #4 opened 3 years ago by SimonQi1
  5

• Deterministic training and evaluation codes for PIE and JAAD

  #18 opened 3 years ago by thisishale
  1

• CPU RAM usage increasing for every epoch

  #16 opened 3 years ago by GuttinRibeiro
  4

• Questions on PIE

  #17 opened 3 years ago by chrisphum
  1

• Model Selection based on test results?

  #20 opened 3 years ago by PipoC96
  1

• Failed to reproduce results and Bugs in related Trajectron++ code

  #19 opened 3 years ago by MeiliMa
  1

• Paper question: 1.5 second MSE of PIE on JAAD dataset

  #15 opened 3 years ago by segermans
  1

• Slightly weird validation curve

  #14 opened 3 years ago by segermans
  1

• Trained the model with original codes and settings, but cannot obtain the results in the paper.

  #6 opened 3 years ago by Infinitywxh
  4

• when training

  #10 opened 3 years ago by f777777
  1

• Pre training model

  #9 opened 3 years ago by S1tephen
  4

• Computing power and time needed

  #12 opened 3 years ago by KSXGroup
  0

• Visualization is not ideal(JAAD)

  #11 opened 3 years ago by wuyuanmm
  4

• Run train_cave.py on win10, why there is no result?

  #5 opened 3 years ago by yanshuaibupt
  4

• Hi, it should be my fault, I didn't find nuscenes.prediction in the from nuscenes.prediction import convert_local_coords_to_global

  #8 opened 3 years ago by S1tephen
  1

• Hi, it should be my fault, I didn't find nuscenes.prediction in the from nuscenes.prediction import convert_local_coords_to_global

  #7 opened 3 years ago by S1tephen
  0

• Where is tools/jaad/train_deterministic.py

  #3 opened 3 years ago by WangLi2019Gt
  0

• paper code

  #1 opened 4 years ago by guoyage
  6

• When I can see your code?

  #2 opened 3 years ago by daeunni
  3