Changing layer_size cannot predict sentences

[Fancy7777]

when I change the layer_size to another value, it gives this error for generating sentences. Any idea? I checked the source code. It seems this is not implemented.

what(): Dimensions of parameter /_3 looked up from file ({128,128}) do not match parameters to be populated ({512,128})

[liesun1994]

That's , in my opinion , a minor bug .
Here you can not change layer_size into other value .
I am puzzled too . May something wrong with populate .

[Fancy7777]

Yes. I do check the code. There are no options listed to change the layer_siza. However, to balance the layer size and hidden unit size and etc is kinda essential to my model. Hmmm are u thinking to update maybe? kun wang <notifications@github.com>于2017年10月31日 周二19:22写道：

…

That's , in my opinion , a minor bug . Here you can not change layer_size into other value . I am puzzled too . May something wrong with populate . — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#31 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AK2TRjtB1yOSD-hpBhddFDdb54T4aUxbks5sxtjFgaJpZM4QJ3Mw> .

[liesun1994]

@Fancy7777 I think the code will not be updated in the soon later . The author is foucusing on dynet . Issues listed in lamtram may not be solved in time . But you know, several months passed after last commit ......

[Fancy7777]

Lol. True. Thanks for the response anyway kun wang <notifications@github.com>于2017年10月31日 周二19:33写道：

…

@Fancy7777 <https://github.com/fancy7777> I think the code will not be updated in the soon later . The author is foucusing on dynet . Issues listed in lamtram may not be solved in time . But you know, several months passed after last commit ...... — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#31 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AK2TRkYK_NwUHuK1aZFOKan8wLa34EWbks5sxttngaJpZM4QJ3Mw> .

[liesun1994]

Hello, I solved the problem by changing macros.cc layer_size == $value, where the $value is what you want to changed.