tobias-fischer / ensemble-event-vpr Goto Github PK

Hi, thanks for your wonderful work on event representation. But I still can't understand how to get the fused event representation. That is to say, how the Eq. (3) is computed?

According to the algorithm described in Section III, I can't find related context for this part. Thanks for your attention and looking forward to your reply.

Hi, thank you for sharing your great work! We want to train the model from scratch and see how it works, however, we find that you directly share the trained checkpoints without the training code. Can you share this part so we can learn about your work more in detail?

Thanks for your your wonderful work！
Can you share the data select from DDD17 if convenient?

Hi, I am using the scripts to generate video/frame files while the default paths and file names don't seem to work with the jupyter notebook code. I have been sorting this by rearranging the files but some follow-up errors popup, could you show me how the files are organized on your local machine?

Hi,when I run the code in [Brisbane Event VPR.ipynb, after get the best match according to gps and timestamps, the function get_image_sets_on_demand will be used to getting the image. But there is an Indexerror.

To figure out this problem, I print the shape of image_paths_combined1[subfolder] and timestamps_combined1[subfolder], their shape seems unmatched which results in the problem.

could you show me how the figure out this problem?