visualization

[wwwwerfvgv]

I have some issues with the visualization of the prediction trajectory. How do you draw a trajectory like a diagram in a paper? Can you share with me the code for the trajectory visualization? Thank you!

[cunjunyu]

You may download the original dataset here: https://ethz.ch/content/dam/ethz/special-interest/itet/cvl/vision-dam/documents/ewap_dataset_light.tgz

It contains a transformation matrix and allows you to transform the point to the image frame.

[wwwwerfvgv]

您可以在此处下载原始数据集：https://ethz.ch/content/dam/ethz/special-interest/itet/cvl/vision-dam/documents/ewap_dataset_light.tgz

它包含一个变换矩阵，并允许您将点变换到图像帧。 Thanks for your reply. I would like to know whether this visualization uses the output compressed package to visualize the trajectory. If so, how is it done?

[cunjunyu]

In the package, there is a transformation matrix for each map, probably called H.txt. The transformation matrix allows you to transform the point from the world frame to the image frame.

[wwwwerfvgv]

在包中，每个映射都有一个转换矩阵，可能称为 H.txt。变换矩阵允许您将点从世界帧转换为图像帧。 def save_model(self, epoch):

    model_path = self.args.save_dir + '/' + self.args.train_model + '/' + self.args.train_model + '_' + \
                 str(epoch) + '.tar'
    torch.save({
        'epoch': epoch,
        'state_dict': self.net.state_dict(),
        'optimizer_state_dict': self.optimizer.state_dict()
    }, model_path)

Thanks for your reply.Is it directly using the parameters saved by the save_model above for visualization? If so, how is it done?