DannyWeitekamp

import numba 
import numpy as np
import numba
from numba import types, jit,njit, generated_jit
from numba import deferred_type, optional
from numba import void,b1,u1,u2,u4,u8,i1,i2,i4,i8,f4,f8,c8,c16
from numba.typed import List, Dict
from numba.types import ListType, unicode_type, UnicodeType
from numba.cpython.unicode import _empty_string, _set_code_point, _get_code_point, PY_UNICODE_1BYTE_KIND
from numba.extending import overload, overload_method

DannyWeitekamp

from numba import njit, cfunc
from numba.types import unicode_type, i8

import time
class PrintElapse():
    def __init__(self, name):
        self.name = name
    def __enter__(self):
        self.t0 = time.time_ns()/float(1e6)
    def __exit__(self,*args):

DannyWeitekamp

from numba import njit, f8
from numba.typed import List
from numba.extending import models, register_model

class Interval(object):
    """
    A half-open interval on the real number line.
    """
    def __init__(self, lo, hi):
        self.lo = lo

DannyWeitekamp

from numba import njit, f8
from numba.typed import List
from numba.extending import models, register_model



class Interval(object):
    """
    A half-open interval on the real number line.
    """

DannyWeitekamp

# Chris Questions:

# Calling all inputs and outputs 'foas' is a little confusing?
# In training why does HowSearch run at the beginning and then only get used when there are no explanations?

# Nitty Gritty Questions:
# Does the when learner need to include foas & selection in search?
#   -How do we support the possibility that it does/doesn't
#   -are there accuracy/opp differences if only operating on the state without expanding / querying over all the foas/selections?

DannyWeitekamp

import sys, glob, os, re

print(len(sys.argv))
if(len(sys.argv) < 3):
	print("Proper Usage:")
	print("%s <input.brd or folder w/ .brds> <output file or folder>" % sys.argv[0])
	exit()

inp =  os.path.abspath(sys.argv[1]);
out =  os.path.abspath(sys.argv[2]);

DannyWeitekamp

class Attention(Layer):
    def __init__(self,
                 W_regularizer=None, b_regularizer=None,
                 W_constraint=None, b_constraint=None,
                 bias=True, **kwargs):
        """
        Keras Layer that implements an Attention mechanism for temporal data.
        Supports Masking.
        Follows the work of Raffel et al. [https://arxiv.org/abs/1512.08756]
        # Input shape

DannyWeitekamp

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