hoonkai

@pahique Hi. Can I ask how you did it? I'm having exactly the same problem.

@davinnovation But doesn't `weights=None` initialise the model to random weights? It wouldn't undergo actual training, right?

I get a similar problem too. At first, it gives the following error: ``` [ INFO] [1568627085.505680852]: record_bearing_range: false [ INFO] [1568627085.506049965]: record_beacon_range: false [ INFO] [1568627085.509747725]: rawlog file: 2019_09_16,19_44_45.509685ros_log.rawlog...

I should note that I get that error using the latest branch, melodic, MRPT 1.5, Ubuntu 18.04. I get exactly like @aaravrav142 on 0.1.24 though.

Fixed. I just had to turn down the playback rate.

Hi I'm having the same error. Did you manage to fix it?

Hi > The original had some flag that excluded hard examples. This is true, but the precision I'm getting is substantially lower than the precision I get for hard examples...

@larsmm But as for emergency power off, wouldn't you want to power it off regardless? For instance, when the battery is undercharged.

@btsimonh Hi Are you using the Hall sensors as odometers? Aren't the Hall sensors meant to be used for RPM commutating and not for measuring RPM though? Hall sensors shouldn't...

@p-h-a-i-l Well, I was just thinking that Hall effect sensors are for low RPM commutating and not really for generating tach signals. I've had some less than desirable experiences in...