Language-Modeling-GatedCNN

Language-Modeling-GatedCNN copied to clipboard

I have used the code to run in Python notebook. Tensorflow 1.12. I love this piece of implementation - straightforward step-by-step logic of CNN. It is so much more transparent...

RadekSadowski

only sentences with a fixed size are chosen?

2

LHRYANG

While training the model can see all words (beside the last one)

11

Lets say a sentence in the data set is (1,2,3,4) Then prepare_data function will create: X = (1,2,3) Y = (2,3,4) While predicting 2 and 3 your model can copy...

talbaumel

Could you please provide the log for training with the default configuration?

3

I train the model with the provided dataset and configuration. And the initial loss is huge, e.g. 8~9e+10. I think there is something wrong with my training. Could you please...

Jar7

model performance and training speed

1

Hi, anantzoid, Could you please provide some more information about convergence of the model? e.g.: How long will the training procedure take? What device do you use? How about the...

ruanchong

It takes 50 seconds to handle one batch (do forward / backwards pass) for the model with default settings. I use Titan X. Is it ok, if not, what may...

borisovyy

can you paste the result. tks very much.

moveforever

is the dimension of convolution output same with the embeddings size ??

3

I noted that `h, res_input = embed, embed` and `fanin_depth = h.get_shape()[-1] ` is the dimension of convolution output same with the embeddings size ?? why ?

meshiguge