Tal Weiss
Tal Weiss
Ugly as hell, but I managed to work around with this on_match function: ``` def on_match_kill_last_token(_matcher, _doc, current_id, matches): match_id, match_start, match_end = matches[current_id] matches[current_id] = (match_id, match_start, match_end -...
Wow, I've never seen it "forget" this badly. That said, even at iteration 165, you see the training accuracy is at 0.9845 - while the validation accuracy is stuck at...
I added saving the model after each epoch. On Feb 28, 2017 1:48 AM, "Parth Mehta" wrote: > @vinnitu Adding this at the end of for loop > in iterate_training...
Nope. Not ok. In a later revision of the code which I have not yet released we moved to batches (new feature from Keras) that enable us to train without...
CHARS? Please elaborate.
It actually looks ok for a first iteration. May the network be ever converging in your favor.
I changed the code to do iterative training with a generator. It now runs nicely on my laptop without needing to limit the amount of data! You might still need...
I just moved to the news.2013.en.shuffled (much larger) - I'll update the code to reflect that. It is so large that I split the epochs to mini-epochs that cover about...
If I recall correctly, the trailing periods are how I used to signal the end of the sequence and they should be stripped off. Also - I don't remember if...
Hi there, I made many changes to the code while experimenting. Most of my experiments were with private data which I cannot share, but I tried to copy code changes...