Jagged edges in the output the masks about transfiner HOT 14 CLOSED

Hi @lkeab without the background removed, these edges are not noticeable. I don't see the jagged edges even with my inference, atleast they are not noticeable this way I think.

I simply do this to remove the background, so I don't think it is an issue with the background removal process.

from PIL import Image
img = Image.open(src_img_path)

np_img = np.copy(np.asarray(img))
neg_mask = ~mask
np_img[neg_mask] = 255
plt.imshow(np_img)

I wasn't setting VIS_PERIOD if it is not the default. I have set it now and I can confirm that the code is going to dilating step. Though, I am not sure if the output is any different.. I also tried with 7x7 kernel.. not much improvement.

I see below logs during inference, not sure if they are of any significance

fpn input shapes: {'res2': ShapeSpec(channels=256, height=None, width=None, stride=4), 'res3': ShapeSpec(channels=512, height=None, width=None, stride=8), 'res4': ShapeSpec(channels=1024, height=None, width=None, stride=16), 'res5': ShapeSpec(channels=2048, height=None, width=None, stride=32)}
/home/ubuntu/vangap/transfiner/detectron2/structures/image_list.py:99: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  max_size = (max_size + (stride - 1)) // stride * stride
/home/ubuntu/miniconda3/envs/transfiner/lib/python3.7/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at  ../aten/src/ATen/native/TensorShape.cpp:2228.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
dilating---------------------------------------
/home/ubuntu/vangap/transfiner/detectron2/modeling/roi_heads/mask_head.py:60: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  dim_t = temperature ** (2 * (dim_t // 2) / num_pos_feats)

from transfiner.

Hi, have this line triggered during the inference process? You can try to increase the dilation kernel range to reduce the artifacts. This is the result of the woman running on my local machine.

from transfiner.

I did't observe this warning when running my code.

from transfiner.

Could there be an issue with the pytorch/cuda versions?
I am using all the latest versions, and on A100.

from transfiner.

Not sure. I am using the NVIDIA TITAN RTX, Pytorch 1.7.1 and Cuda 11.0.

from transfiner.

If you don't mind, is it possible to provide mask object for one of these images(and details on which model and setttings are used) or provide an option in huggingspaces to download it?

I would like to compare it with what I am seeing and confirm if it's an env issue or something else.

from transfiner.

Hi, I am currently out for a traveling. I think one validation method is to that you report your AP results for our pretrained model (for example r50-fpn-1x) running on your machine. If it is exactly the same, then I think it can exclude the environment factors.

from transfiner.

Hi @lkeab without the background removed, these edges are not noticeable. I don't see the jagged edges even with my inference, atleast they are not noticeable this way I think.

I simply do this to remove the background, so I don't think it is an issue with the background removal process.

from PIL import Image
img = Image.open(src_img_path)

np_img = np.copy(np.asarray(img))
neg_mask = ~mask
np_img[neg_mask] = 255
plt.imshow(np_img)

I wasn't setting VIS_PERIOD if it is not the default. I have set it now and I can confirm that the code is going to dilating step. Though, I am not sure if the output is any different.. I also tried with 7x7 kernel.. not much improvement.

I see below logs during inference, not sure if they are of any significance

fpn input shapes: {'res2': ShapeSpec(channels=256, height=None, width=None, stride=4), 'res3': ShapeSpec(channels=512, height=None, width=None, stride=8), 'res4': ShapeSpec(channels=1024, height=None, width=None, stride=16), 'res5': ShapeSpec(channels=2048, height=None, width=None, stride=32)}
/home/ubuntu/vangap/transfiner/detectron2/structures/image_list.py:99: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  max_size = (max_size + (stride - 1)) // stride * stride
/home/ubuntu/miniconda3/envs/transfiner/lib/python3.7/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at  ../aten/src/ATen/native/TensorShape.cpp:2228.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
dilating---------------------------------------
/home/ubuntu/vangap/transfiner/detectron2/modeling/roi_heads/mask_head.py:60: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  dim_t = temperature ** (2 * (dim_t // 2) / num_pos_feats)

I encountered the same warnings! My env setting: ubuntu 20.04, python 3.7.13, pytorch 1.11.0, cuda 11.3.

from transfiner.

@anl13 Do you also see the jagged edges?

from transfiner.

@vanga Yes, I observed exactly the same results. In fact, I have removed these warnings by replacing a//b with torch.div(a, b, rounding_mode='floor'). However, there is no help. See result below. By the way, my GPU for test is Nvidia Titan X.

from transfiner.

@lkeab Can we keep this open until thee is a closure? considering it is not just me?

w.r.t checking AP results, could you please share some pointers on how I can do that?

from transfiner.

Hi, for checking AP results, you can report the inference results on coco val set using our provided pretrained model, such as R50-FPN-1x or 3X. I will also look into this to see whether can help fix it. It's not that noticeable when drawing masks directly on images.

from transfiner.

Hi, we also updated the code. Please try the latest version to see whether it helps or not. These are the results obtained by me.

from transfiner.

Here are my results with updated code. There are improvements compared with previous code. I test three pretrained models for human segmentation.

model: output_3x_transfiner_r101_deform.pth:

model: output_3x_transfiner_r101.pth:

model: output_3x_transfiner_r50.pth:

from transfiner.