Show and Tell: Image captioning open sourced in TensorFlow

Re:Show and Tell: Image captioning open sourced in TensorFlow by angerbot on Thursday September 22, 2016 @06:01PM (#12560706)

I hadn't considered that (this is really out of my depth). Any ideas on what the actual size of a trained model would be to distribute? Taking 150G on the user's hard drive is out as well, probably.

[ Parent | on HN ]

Re:Show and Tell: Image captioning open sourced in TensorFlow by dharma1 on Thursday September 22, 2016 @07:41PM (#12561260)

Depends on the model and dataset, inceptionv3 trained on imagenet is about 150mb but you can quantise the weights to 8bit and prune it much smaller without affecting perf much

[ Parent | on HN ]