Ben Johnson
Ben Johnson
Thanks! (I had thought it was a python layer, so I was looking in the wrong places..)
Interesting. Is there a dataset you use to test your implementations of these things? Something synthetic or MNIST or something? On Mon, May 8, 2017 at 9:45 PM Jie Zhang...
Thanks! I assume the values for word and window size are tuned via cross validation in that notebook? __Edit:__ I also notice that the numbers you're getting there are almost...
Digging into this deeper -- seems like using batch statistics vs running statistics make a fair bit of difference in the convergence of the model. Do you have a good...
I think @LiheYoung is correct -- w/ `DistributedDataParallel` you launch N copies of the program. If you don't set the seed, then `np.random` will sample the dataset differently, and you...
In my experiment, performance w/o the seed is substantially better than w/ a seed. I only ran once, so perhaps this is random variation, but I'm guessing this is due...
OK great thanks. Are you able to give some more details about the experimental setup for those numbers? I have the following files for the `youtube` dataset: ``` ~/.graphvite/dataset/youtube/ ├──...
If I had to guess w/o digging through your code (yet :) )-- I'm guessing that you convert `youtube_label.txt` to a `(num_labeled_examples, num_labels)` binary matrix, then use `k%` of the...
Great thanks everyone!
Thanks!