The visualization is terrible

[vipcxj]

Is this effect normal?

python run.py -k cpn_ft_h36m_dbb -c checkpoint --evaluate pretrained_h36m_cpn.bin --render --viz-subject S11 --viz-action Walking --viz-camera 0 --viz-video "/root/datasets/human3.6m/S11/Videos/Walking.54138969.mp4" --viz-output output.gif --viz-size 3 --viz-downsample 2 --viz-limit 60

This is the command.

[PrAYtele]

Same problem,It's normal,because the model's output is just gt+noise
anim_output = {'Reconstruction': ground_truth + np.random.normal(loc=0.0, scale=0.1, size=[ground_truth.shape[0], 17, 3])}

[JinluZhang1126]

I have repaired this issue, please check again.

[wenwen12321]

Is this effect normal?

python run.py -k cpn_ft_h36m_dbb -c checkpoint --evaluate pretrained_h36m_cpn.bin --render --viz-subject S11 --viz-action Walking --viz-camera 0 --viz-video "/root/datasets/human3.6m/S11/Videos/Walking.54138969.mp4" --viz-output output.gif --viz-size 3 --viz-downsample 2 --viz-limit 60

This is the command.

@JinluZhang1126
Hi author,

I can only output about a two-second .gif file the same as this result.
How could I output a longer .gif file just like the result of your Github main page providing??

[sumonky]

Same problem,It's normal,

[jianlai123-123]

Hello, may I ask if you have successfully obtained longer outputs? If so, could you please share how you resolved it? Looking forward to your reply. Thank you. @wenwen12321