Passage

Passage copied to clipboard

Initialize LSTM forget gate with one

1

This paper found they got significantly better results on a range of tasks if the forget gate for LSTM is initialized with one. http://www.jmlr.org/proceedings/papers/v37/jozefowicz15.pdf

ma2rten

I've been trying to get a simple text generator similar to the result in this blog post: [http://karpathy.github.io/2015/05/21/rnn-effectiveness/](url). Is there anyone who can come up with an example of doing...

slyons

Dear contributors, Thanks a ton for putting this library together. I based my classification model on the sentiment.py example. I find that my (Embedding + GatedRecurrent / LstmRecurrent + Dense)...

umas

Use as a Tagging Model?

3

This is more of a feature request. I'd love to try to use an LTSM model as as tagging model. I have tagged words for my training data (not POS...

simonhughes22

Implement learning rate schedule

1

I was able to get better results with SGD on my own dataset with this library, if I use SGD and half the learning rate after each epoch, than using...

ma2rten

Theano Error: 'TensorVariable' object has no attribute 'cast'

3

Hi, I'm trying to run the "example" on my own data. After fitting the tokenizer, I get a big, long list of error messages from Theano. Background: Windows 8.1. Anaconda...

ddofer

Understanding Multiclass classification problem

1

Here is the thing. I have 3 class labels in my data. The predict function returns an array of shape (N, 3) where N is the size of the train...

naeemulhassan

Model instantiation is very slow

1

While trying out the example provided in the Readme, I noticed that this line executes very slowly: ``` model = RNN(layers=layers, cost='BinaryCrossEntropy') ``` Profiling shows that this line takes around...

adithyarao

RNN.predict should return labels, not probabilties

5

There's a slight incompatibility with sklearn in the `RNN.predict` method: this one should return predicted class labels. `predict_proba` is the name of the method that returns probabilities. In Passage's case...

dnouri

LSTM example rise a `dtype` difference error

2

Hello, I just used exactly the same example in Passage/mnist.py The only modification is to change `GatedRecurrent` into `LstmRecurrent`: ``` python import ... ... trX, teX, trY, teY = load_mnist()...

sjhddh