Dan Erez

> Oh, Jesus! > Come to see what I have found here! > https://sites.google.com/view/tensorflow-example-java-api/complete-guide-to-train-yolo/convert-darknet-weights-to-pb-file so we don't have to go into the link that may break one day : >...

***face palm**** thanks @shalin51

I also get something similar - I am using python 3.6 , tensorflow + keras ( almost latest versions of each ). I am trying to train with squeezenet with...

Depending on the network - it can many layers with a large latent space. networks can very quickly reach gigabytes of ram. If you want the updates to happen only...

@brimoor thanks for the detailed answer. i was thinking that the data itself would be by reference and not duplicated. if it is duplicated i would think that filtering only...

if it's simple I don't mind trying to contribute it.

thank you very much for getting back to me. After some fighting I was able to train for rigid objects. I also tried adding a second yolo layer at high...

Hi @spaul13 , If my memory serves me it took me way way more than 1000 iterations. Notice that there is a warm up period in which training is very...

@jerybai1995 did you ever write a 1d version ? pelase share :)

@Anirudh257 this was a 2.5 years ago - naturally I've moved on to other things. I don't think I ever got it to work for 1d. I recommend you look...