nianticlabs/monodepth2

Issues

• Run on Google Colab, but out of System RAM

  #491 opened 10 months ago by Holy-Egg
  1

• obtained some very strange depth maps

  #483 opened a year ago by lhx0416
  5

• training my custom dataset problem

  #504 opened 3 months ago by Linengyao
  0

• How monocular depth estimation specifically guides subsequent processes such as robot navigation?

  #503 opened 3 months ago by guotong1988
  0

• What is the principle, I can not understand. Why does the design of self-supervised loss functions achieve monocular depth estimation?

  #502 opened 3 months ago by guotong1988
  0

• Questions about pose estimation

  #496 opened 7 months ago by own295554312
  2

• the eval file about 'gt_depths.npz'

  #489 opened a year ago by sunny-zzw
  1

• RuntimeError: CuDNN error: CUDNN_STATUS_SUCCESS

  #493 opened 9 months ago by kuacboss
  3

• onnx

  #475 opened a year ago by QZZZZZYF
  1

• Write split file

  #482 opened a year ago by hieuvo218
  2

• RuntimeError: The size of tensor a (319) must match the size of tensor b (639) at non-singleton dimension 3

  #499 opened 5 months ago by Saahil18
  0

• Regarding the patent and license

  #498 opened 6 months ago by anthonygofin
  1

• Different evaluation criteria for Monodepth2 M and S

  #497 opened 6 months ago by hwlf
  0

• How to setup already trained computer vision model Ultralytics YOLOv8 with monodepth2

  #495 opened 8 months ago by coderMichaelLapshyn2345
  1

• Negative loss

  #447 opened 2 years ago by nishavarghese15
  4

• How to obtain reconstructed image and loss for a single demo image

  #494 opened 8 months ago by vittoria310
  0

• The requested array has an inhomogeneous shape after 1 dimensions.

  #481 opened a year ago by 757787182
  5

• The new constraint about pose is not useful?

  #492 opened 10 months ago by Zhangwenyao1
  0

• Run on Google Colab,

  #490 opened 10 months ago by Holy-Egg
  0

• Questions about the meaning of grid in the F.grid_sample function

  #488 opened a year ago by pnpmpnp
  0

• Why is smooth_loss divided by 2**scale?

  #487 opened a year ago by Shaw-Way
  0

• question for the Data Preparation

  #486 opened a year ago by dsfdwsfsdf
  0

• I don't know if auto mask works well.

  #471 opened 2 years ago by WonJunPark
  2

• Question about image resolution

  #485 opened a year ago by jimmyfyx
  0

• The difference in the intrinsic matrix affects the results

  #484 opened a year ago by jn660
  0

• Network inference time problem

  #480 opened a year ago by mrwen-hard
  0

• Can't run the initial training

  #479 opened a year ago by dttran0
  0

• What are the units in which the results are predicted

  #476 opened a year ago by JerryPW
  2

• A problem when I train my repo code

  #477 opened a year ago by Jamesgender
  1

• ONNX model converter

  #458 opened 2 years ago by GinkgoX
  3

• finetune on custom dataset with provided model

  #474 opened 2 years ago by adam99goat
  1

• While reading groundtruth depth-map, why is it required to divide by 256 after converting PIL.Image to np.array ?

  #473 opened 2 years ago by compvision-developer
  2

• Pose (decoder) network - forward method mismatch of convolutional operation (pconv0, table 5 on paper)

  #472 opened 2 years ago by giannisbdk
  2

• Conversion from Disparity to Depth in Monocular Training

  #465 opened 2 years ago by zzzzzyh111
  2

• How to train on custom dataset

  #448 opened 2 years ago by mengpengfei
  5

• RuntimeError: cublas runtime error : the GPU program failed to execute at C:/ProgramData/Miniconda3/conda-bld/pytorch_1533090623466/work/aten/src/THC/THCBlas.cu:411

  #452 opened 2 years ago by giuseppecialdella
  4

• The result is very bad on lane line

  #451 opened 2 years ago by mengpengfei
  8

• Huge depth difference between lane line and road

  #453 opened 2 years ago by lmomoy
  1

• Pose Network 0.01 scale factor

  #455 opened 2 years ago by nfrankisrg
  2

• Train a monocular video

  #456 opened 2 years ago by pg37013
  1

• Loss calculation

  #457 opened 2 years ago by CC-Xiaoyu
  1

• point cloud

  #459 opened 2 years ago by Ronald-Kray
  1

• estimation of metric distance from the depth map using a regression model

  #460 opened 2 years ago by hosseinv
  1

• 2 questions about stereo training and monocular training.

  #461 opened 2 years ago by dicaleon
  1

• depth10k issue

  #462 opened 2 years ago by siefeldiin22
  1

• About the test set used for demo

  #466 opened 2 years ago by thom966
  1

• Why is the test result not good after training on the dataset you have created?

  #470 opened 2 years ago by WangGangQiang123
  1

• White predictive mask after several iterations

  #454 opened 2 years ago by jordigc2
  1

• How to Train Monodepth2 on Custom Dataset made by image sequences

  #449 opened 2 years ago by giuseppecialdella
  0

• It is werid to use GT mask for depth_pre in compute_depth_losses

  #450 opened 2 years ago by lmomoy
  1