lk251

Data instead of JSON - anyone wanna work on this with me?

6

Is this because Decodable wasn't available before? I'd like swifter to produce a Data instance which I can use JSONDecoder with. Anyone wanna collaborate on this? not sure how to...

People testing the demo may accidentally put their consumerkey and consumersecret in these version controlled files. This will avoid that.

It seems that the way to go is using the search api with a since_id set to the target tweet's id, then checking the in_reply_to_tweet_id parameter. However, in the standard...

lstm with return_seq = True as input to a fully_connected, unintended behaviour?

1

[g = tflearn.lstm(g, 1024, return_seq=True) g = tflearn.dropout(g, 0.85) g = tflearn.fully_connected(g, len(char_idx), activation='softmax')](url) This shouldn't work, should it? On GPU tensorflow, it doesn't complain, (and training converged). On the...

New error on train, possibly caused by beam-search-decoder bugfix

4

when running python main.py --config cornell-movie-dialogs --mode train_and_evaluate I get the error message > load vocab ... > vocab size: 41676 > make Training data and Test data Start.... >...

Significant overfit on default hyperparameters on cornell-movie-dialogs config

2

Running: python main.py --config cornell-movie-dialogs --mode train to the end (100000 steps) will result in a training loss of about 2.6, test loss of 8.4. Which hyperparameters did you use?...

Feature proposal: Use multiple GPUs

10

Anyone interested in implementing this? Please let me know, I'd like to help.

Thank you!

hi! this looks cool, wanted to try it but i couldn't find the xcode project file, to open and run this using xcode could you upload the complete project, or...