Dimensions issues with deep learning model

Question

I seem to have some problems understandind how the model described in this paper has been designed

This is what is written about the model dimension..

...In these experiments we used one convolution ply, one poolingply and two fully connected hidden layers on the top. The fullyconnected layers had 1000 units in each. The convolution andpooling parameters were: pooling size of 6, shift size of 2,filtersize of 8, 150 feature maps for FWS..

So according to ^ does the model consist of

Input

Convolution

Pooling

Input being the 150 feature maps (each with shape (8,3)

Covolution being 1d as kernel size is 8

and pooling is with size 6 and stride 2.

What was expected of output would be a shape of (1,"number of filters), but what i get is (14,"number of filters)

Which I understand why i get, but I don't understand how the paper suggest this can give an output shape of (1,"number of filters")

when using 100 filters I get these outputs from each layer

convolution1d give me (33,100)

pooling (14,100)..

Why i expect the output to be 1 instead of 14

The model is supposed to recognise phones, it takes in a 50 frames (150 including deltas) as input, these being a context frame, meaning that these are used as support to detect one single frame... That usually why context windows are used.

It isn't clear what this question is asking I followed you in till the very end what results did you get and what was that not expected — Andrew Charneski, May 22 '17 at 20:01

score -1 · Answer 1 · answered May 23 '17 at 06:04

-1

As I understand from your question, the shape (14,'number of filters) comes out after the pooling layer. That is expected.

What you have to do is to flatten the results in to a single vector before feeding them to the two layer fully connected networks.

Marcin Morzejko's answer to my question in here would help.

answered May 23 '17 at 06:04

noobiejp

107
2
9

1

I don't think "reshaping" the result is a possibility here.. The model proposed isn't suggesting one to alter it, and that may affect the perfomance of the model... – J.Down May 23 '17 at 09:06
1

I don't think reshaping the output is a proper solution.. I would like to have to math correct to avoid messing with things. – I am not Fat May 23 '17 at 09:58

Dimensions issues with deep learning model

1 Answers1