How to visualize the segmentation network performance output ?

[arunumd]

Hi @yanx27 first of all thank you for this helpful work. I was first following the official tensorflow repository by the original authors. But it didn't work well for me. I later moved to your repository (PyTorch implementation) and I was able to do the training process without issues. I just have one question about the visualization. I was of the assumption that the show3d_balls.py file is supposed to help us visualize the output of segmentation like the way you have shown in the README.md file. But I find that the visualization code is not complete yet. Please correct me if I am wrong. What did you do to visualize the results of training, the way you have shown in the README.md file ? Did you use any external tools ?

[neverstoplearn]

i meet the same problem have you solve it? thanks.

[arunumd]

I was not able to find out a way to visualize the results using this repository. I have found a more helpful repository where you just set the model path and other essential arguments to the visualizer and visualize it. The repository I am talking about is this one here => https://github.com/fxia22/pointnet.pytorch.git

[XGuider]

Hi, visual code was not found? Can you be more detailed?---->https://github.com/fxia22/pointnet.pytorch.git

[XGuider]

@arunumd

[BlurryLight]

@XGuider
https://github.com/fxia22/pointnet.pytorch/blob/master/utils/show_seg.py
it's not hard to follow that file and the code in this project to write a visualizer. What you need to do is to get the points pred result,namely pred_choice in code, with the eval model and draw it using the showpoints function.

Pointnet_Pointnet2_pytorch/utils.py

Line 98 in 31deedb

def test_partseg(model, loader, catdict, num_classes = 50,forpointnet2=False):

My code is here but it still needs to be modified to work well with your code.
https://github.com/BlurryLight/Pointnet_Pointnet2_pytorch/blob/master/visualizer/show_part_seg_pointnet.py

[XGuider]

yes，thnx you so much! i get .

…

------------------ Original ------------------ From: "Nightwatch";<notifications@github.com>; Send time: Monday, Nov 25, 2019 1:42 PM To: "yanx27/Pointnet_Pointnet2_pytorch"<Pointnet_Pointnet2_pytorch@noreply.github.com>; Cc: "973279990"<973279990@qq.com>; "Mention"<mention@noreply.github.com>; Subject: Re: [yanx27/Pointnet_Pointnet2_pytorch] How to visualize thesegmentation network performance output ? (#25) @XGuider https://github.com/fxia22/pointnet.pytorch/blob/master/utils/show_seg.py it's not hard to follow that file and the code in this project to write a visualizer. What you need to do is to get the points pred result,namely pred_choice in code, with the eval model and draw it using the showpoints function. https://github.com/yanx27/Pointnet_Pointnet2_pytorch/blob/31deedb10b85ec30178df57a6389b2f326f7c970/utils.py#L98 My code is here but it still needs to be modified to work well with your code. https://github.com/BlurryLight/Pointnet_Pointnet2_pytorch/blob/master/visualizer/show_part_seg_pointnet.py — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.