Here's how I solved it. Based on http://askubuntu.com/a/683947 and http://stackoverflow.com/a/34916570
Download cUrl from http://curl.haxx.se/download.html
Then in your terminal, run these commands
$ tar -xzf curl-***.tar.gz
$ cd curl-*.*.*
from keras import backend as K | |
from keras.engine import InputSpec | |
from keras.engine.topology import Layer | |
import numpy as np | |
class TemporalMaxPooling(Layer): | |
""" | |
This pooling layer accepts the temporal sequence output by a recurrent layer | |
and performs temporal pooling, looking at only the non-masked portion of the sequence. |
class AttentionWithContext(Layer): | |
""" | |
Attention operation, with a context/query vector, for temporal data. | |
Supports Masking. | |
Follows the work of Yang et al. [https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf] | |
"Hierarchical Attention Networks for Document Classification" | |
by using a context vector to assist the attention | |
# Input shape | |
3D tensor with shape: `(samples, steps, features)`. | |
# Output shape |
Here's how I solved it. Based on http://askubuntu.com/a/683947 and http://stackoverflow.com/a/34916570
Download cUrl from http://curl.haxx.se/download.html
Then in your terminal, run these commands
$ tar -xzf curl-***.tar.gz
$ cd curl-*.*.*
I'll assume you are on Linux or Mac OSX. For Windows, replace ~/.vim/
with $HOME\vimfiles\
and forward slashes with backward slashes.
Vim plugins are collections of specialized scripts that you are supposed to put in "standard" locations under your ~/.vim/
directory. Syntax scripts go into ~/.vim/syntax/
, plugin scripts go into ~/.vim/plugin
, documentation goes into ~/.vim/doc/
and so on. That design can lead to a messy config where it quickly becomes hard to manage your plugins.
This is not the place to explain the technicalities behind Pathogen but the basic concept is quite straightforward: each plugin lives in its own directory under ~/.vim/bundle/
, where each directory simulates the standard structure of your ~/.vim/
directory.