Pankaj Daga

Any news/update on this? Would be great to try this model for outdoor scenes.

Dropout probabilistically keeps a neuron activated usually only during training time. I guess the code here is for inference, where the dropout keep probability is usually set to 1.0

This seems to happen only on Windows platform. I tested it on 64-bit Win 10 with Julia 0.5.1. Tested it on Ubuntu 16.04 64 bit and it is working fine.

> I‘ve implemented the lstm autoencoder model in pytorch and it seems to work great with machine data. I‘m now validating the model... Did you use a Sequence2Sequence like model...

More than happy! However, there are a few things that would need to change, and perhaps if you could suggest a direction. So another thing in the code that is...

Is there a way to specify the NMS parameters on the pytorch hub model?