Monk comments

Results 12 comments of


                                            Monk

RuntimeError: CUDA out of memory. Tried to allocate 900.00 MiB (GPU 0; 10.92 GiB total capacity; 7.83 GiB already allocated; 711.50 MiB free; 9.66 GiB reserved in total by PyTorch)

@EricHuiK Do you get solution

Train on a custom dataset

@swarmt If you check the masks, it has a label ID from 0 to 21. Since you want to train the model for 16 labels, so change the label Id...

Problem with train_generator: list index out of range

@thepate94227 Download the SegmentationClassAug folder from https://www.dropbox.com/s/oeu149j8qtbs1x0/SegmentationClassAug.zip

@michacohen JPEGImages folder has 17125 images and SegmentationClassAug 12301 masks. So before the training, keep only those images having mask pairs. Download the SegmentationClassAug folder from https://www.dropbox.com/s/oeu149j8qtbs1x0/SegmentationClassAug.zip

Inclination is incorrect

@bertjiazheng I checked the 2D lines, getting it wrong. Could you please help, check it once why the output layout is not inclined.

Inclination is incorrect

@CYang0515 I tried out on NYU303 as well as custom test set but it didnt worked for me. You have given the padding of (480, 640, 3) to the input...

Inclination is incorrect

In nyu303 dataset the fullres image size is (480,640,3) and cropped image size is (427,561,3). I checked on nyu303 images and the result is doesn't have correct alignment. In the...

Inclination is incorrect

Thanks for updating the repo. The NYU303 test set results look promising but it fails in some cases. In the result, the predicted wall is not correct. Is it because...

Having a hard time getting the right output as explained in the paper.

@CYang0515 I am facing the same issue, the layout inclination are going off. Can you walk us through how to replicate the same result?

Too fast to ID switch

@ninghongbo123 how could I modify point 4 (age