skaae

import scipy.io
import lasagne
import theano
import theano.tensor as T
import numpy as np
import time

import logging

logger = logging.getLogger('')

skaae

class ElemwiseMergeLayer(MergeLayer):
    """
    This layer performs an elementwise merge of its input layers.
    It requires all input layers to have the same output shape.

    Parameters
    -----------
    incomings : a list of :class:`Layer` instances or tuples
        the layers feeding into this layer, or expected input shapes,
        with all incoming shapes being equal

skaae

Function profiling
==================
  Message: /home/soren/Documents/experiments/TRANSFORMER_NET/grutranstest.py:271
  Time in 5 calls to Function.__call__: 1.034791e+01s
  Time in Function.fn.__call__: 1.034693e+01s (99.991%)
  Time in thunks: 1.022032e+01s (98.767%)
  Total compile time: 4.257923e+01s
    Number of Apply nodes: 1224
    Theano Optimizer time: 1.321189e+01s
       Theano validate time: 8.471053e-01s

skaae

--[[ A Confusion Matrix class

Example:

    conf = optim.ConfusionMatrix( {'cat','dog','person'} )   -- new matrix
    conf:zero()                                              -- reset matrix
    for i = 1,N do
        conf:add( neuralnet:forward(sample), label )         -- accumulate errors
    end
    print(conf)                                              -- print matrix

skaae

import numpy as np
import theano
import theano.tensor as T
import lasagne.nonlinearities as nonlinearities
import lasagne.init as init
from lasagne.utils import unroll_scan

from lasagne.layers import *
import lasagne.layers.helper as helper

skaae

with open("/home/lpp/.bashrc", 'r') as f:
     lines = f.readlines()

with open('junk.txt', 'w') as f:
     f.write("".join(lines[1:5]


####### OR######

skaae

class GruDenseLayer(lasagne.layers.Layer):
    def __init__(self, incoming, num_units,
                 b_resetgate=None,
                 b_updategate=None,
                 b_hidden_update=None,
                 W_resetgate=init.GlorotUniform(),
                 W_updategate=init.GlorotUniform(),
                 W_hidden_update=init.GlorotUniform(),
                 **kwargs):
        super(GruDenseLayer, self).__init__(incoming, **kwargs)

skaae

# Initialize column sums
column_sums = [0., 0.]

# Iterate over all rows
for row in row_list:
    # For each of the two column values, add to the corresponding sum
    column_sums[0] += row[0]
    column_sums[1] += row[1]

# Calculate the average by dividing by the length

skaae

def read_fasta(fasta_filename):
    '''Function to parse a fasta sequence file'''

    # Initialize dictionary
    fasta_dict = {}

    # Open file and iterate over lines
    for line in open(fasta_filename): 

        # Remove newline and other whitespace from end of line

skaae

def find_prot(fasta_dict, protein_name):
    '''Function to find protein in fasta_dictionary'''

    # Check if fasta_dict contains the protein name key
    if protein_name in fasta_dict:

        # Return biological sequence
        return fasta_dict[protein_name]

    else: