keras-language-modeling

keras-language-modeling copied to clipboard

The blog post that you mention in your README does not exist anymore. The link gives `404` error.

ragvri

I could not replicate the results with embedding + maxpooling layer. I ran 3000 epochs. Could you please suggest your parameters for producing following results. Embedding + Max Pooling: -...

raghadeepa

train ConvolutionModel model,it seems failed

1

when i train CNN model,it epochs 2 twice ,the loss value became nan. it seems getting in local minmize. 

snowlord

Example script for AttentionLSTM

2

I am having a bit of trouble understanding how to incorporate the AttentionLSTM layer into my code. In your blog you have said that *"The attentional component can be tacked...

Spider101

@codekansas Can you share your parameter settings for the results shared in `results.notes`?

eshijia

Hi, Could I get attention weight from "K.function([model.layers[0].input], [model.layers['my_attention_lstm_layer'].output])" of attention model?

chungfu27

TypeError: 'NoneType' object is not iterable

2

Train on 16686 samples, validate on 1854 samples Epoch 1/1 16686/16686 [==============================] - 1s - loss: 0.0060 - val_loss: 0.0340Fitting epoch 2000 2016-10-28 07:51:05 -- Epoch 1999 Loss = 0.0060,...

SeekPoint

This statement (https://github.com/codekansas/keras-language-modeling/blob/master/attention_lstm.py#L106) overwrites the trainable_weights of the inner LSTM layer. It should add to the weights of the LSTM Layer instead.

saurabhmathur96

I noticed that you run the attention through a sigmoid because you were having numerical problems: https://github.com/codekansas/keras-language-modeling/blob/master/attention_lstm.py#L54 This may work, but I think that should actually be a softmax. In...

bkj

if I interrupt the training process, can I continue it later?

SeekPoint