search

cmhungsteve / SSTDA

[CVPR 2020] Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (PyTorch)
https://arxiv.org/abs/2003.02824
MIT License
154 stars 23 forks source link

Qualitative results #7

Closed houzhijian closed 4 years ago

houzhijian commented 4 years ago

Hi, steve:

Can you share the code or script that you use to produce those visualization results?

cmhungsteve commented 4 years ago

Unfortunately, I don't have the script at my hand. The co-author produced all the visualization results. However, there should be many similar scripts you can find online. You just need to assign each class with the color you want, and then you can convert the frame-level predictions into segmentation visualization.

houzhijian commented 4 years ago

Hi, steve:

Thank you. I figure it out. plt.imshow will work.

wwdok commented 3 years ago

@houzhijian Hi, could you please share the srcipt ? thanks !

houzhijian commented 3 years ago

@wwdok I delete it on my side. You can learn from this

https://github.com/colincsl/TemporalConvolutionalNetworks/blob/cccdf868ed4c7a56745b41d30fd9f1dc637eb3f3/code/utils.py#L12

wwdok commented 3 years ago

@houzhijian OK, thank you ！