mwy001

This is a dead (and incomplete) project. My suggestion is that just stop trying it anymore.

> > Have followed the steps to train the model on the HEVI features and ego-motion files provided by the author. Now I have: > > > > * fol_epoch_091_loss_0.0113.pt...

I also see this. Does it happen when you toggle the device's network connection? (Turn off the wifi connection, when turn it on again)

The "peers" message (notify peer about the other peers) returned from the WS server may include the calling/current peer. It should be excluded. I have a possible fix for this:...

@Bellisario Thanks for the comments. Pull request created: https://github.com/RobinLinus/snapdrop/pull/528

The issue is related to the linuxserver/docker-snapdrop's default nginx config, which will resolve all clients' IP to the IP address of reverse proxy , check this: https://github.com/linuxserver/docker-snapdrop/pull/4/commits/d07b0fcb01ceed78ccdeabb1e746c2d0304839ec#diff-b798d7ad17e8cc7e11749264de70d9201e8767881b0df5980369a5e2edc6f804

Add the console log:

@Cogito2012 How much time does it cost to train the UString model on crash dataset with your hardware setting? (command: "bash run_train_test.sh train 0 crash 10" with default epoch=30)