cbaziotis

class SelfAttention(nn.Module):
    def __init__(self, attention_size, batch_first=False, non_linearity="tanh"):
        super(SelfAttention, self).__init__()

        self.batch_first = batch_first
        self.attention_weights = Parameter(torch.FloatTensor(attention_size))
        self.softmax = nn.Softmax(dim=-1)

        if non_linearity == "relu":
            self.non_linearity = nn.ReLU()

BrikerMan

from gensim.models import KeyedVectors

# Load gensim word2vec
w2v_path = '<Gensim File Path>'
w2v = KeyedVectors.load_word2vec_format(w2v_path)

import io

# Vector file, `\t` seperated the vectors and `\n` seperate the words
"""

nigeljyng

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.

nicor88

#!/usr/bin/env bash
set -x -e

JUPYTER_PASSWORD=${1:-"myJupyterPassword"}
NOTEBOOK_DIR=${2:-"s3://myS3Bucket/notebooks/"}

# home backup
if [ ! -d /mnt/home_backup ]; then
  sudo mkdir /mnt/home_backup
  sudo cp -a /home/* /mnt/home_backup

cbaziotis

from keras import backend as K, initializers, regularizers, constraints
from keras.engine.topology import Layer


def dot_product(x, kernel):
    """
    Wrapper for dot product operation, in order to be compatible with both
    Theano and Tensorflow
    Args:

ameasure

from keras.engine.topology import Layer
from keras import initializations
from keras import backend as K

class Attention(Layer):
    '''Attention operation for temporal data.
    # Input shape
        3D tensor with shape: `(samples, steps, features)`.
    # Output shape
        2D tensor with shape: `(samples, features)`.

mbollmann

class AttentionLSTM(LSTM):
    """LSTM with attention mechanism

    This is an LSTM incorporating an attention mechanism into its hidden states.
    Currently, the context vector calculated from the attended vector is fed
    into the model's internal states, closely following the model by Xu et al.
    (2016, Sec. 3.1.2), using a soft attention model following
    Bahdanau et al. (2014).

    The layer expects two inputs instead of the usual one:

joelouismarino

from __future__ import print_function
import imageio
from PIL import Image
import numpy as np
import keras

from keras.layers import Input, Dense, Conv2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D, Dropout, Flatten, Concatenate, Reshape, Activation
from keras.models import Model
from keras.regularizers import l2
from keras.optimizers import SGD

bsweger

Useful Pandas Snippets

A personal diary of DataFrame munging over the years.

Data Types and Conversion

Convert Series datatype to numeric (will error if column has non-numeric values)
(h/t @makmanalp)

SavvyGuard

import boto
import boto.s3

import os.path
import sys

# Fill these in - you get them when you sign up for S3
AWS_ACCESS_KEY_ID = ''
AWS_ACCESS_KEY_SECRET = ''
# Fill in info on data to upload