Points visualization

[Mark-Laohu]

你好，请问learned anchor points更新后的可视化图Figure 2（b）是怎么可视化出来的，不是被embedding了吗

[tangjiuqi097]

Hi, we visualize the final self.position as the learned anchor points, which have self.num_position points and each of them has two dimensions (x, y). You can also create them by the nn.Parameter(torch.FloatTensor(self.num_position, 2)) instead of the nn.Embedding(self.num_position, 2), which may be easier to understand.

[Mark-Laohu]

谢谢回答，learned points生成我大概明白了，就是我想问的是learned points在训练后能可视化出来吗，paper中给的是初始化得到的图还是训练后得到的可视化图啊?

[tangjiuqi097]

The figure in paper is the final learned anchor points after training. You can visualize the model.transformer.position.weight in the checkpoint we provide.

[Mark-Laohu]

好的，非常感谢！

[github-actions[bot]]

This issue is not active for a long time and it will be closed in 5 days. Feel free to re-open it if you have further concerns.