wassname

from keras import backend as K

def jaccard_distance_loss(y_true, y_pred, smooth=100):
    """
    Jaccard = (|X & Y|)/ (|X|+ |Y| - |X & Y|)
            = sum(|A*B|)/(sum(|A|)+sum(|B|)-sum(|A*B|))
    
    The jaccard distance loss is usefull for unbalanced datasets. This has been
    shifted so it converges on 0 and is smoothed to avoid exploding or disapearing
    gradient.

sonots

# A trick to embed preprocessors in cython
cdef extern from *:
     cdef void EMIT_IF_PYTHON_VERSION_HEX_LT_37 "#if PY_VERSION_HEX < 0x03070000 //" ()
     cdef void EMIT_ELSE "#else //" ()
     cdef void EMIT_ENDIF "#endif //" ()

EMIT_IF_PYTHON_VERSION_HEX_LT_37()

EMIT_ELSE()

JohanAR

#ifndef _POLYNOMIAL_REGRESSION_H
#define _POLYNOMIAL_REGRESSION_H  __POLYNOMIAL_REGRESSION_H
/**
 * PURPOSE:
 *
 *  Polynomial Regression aims to fit a non-linear relationship to a set of
 *  points. It approximates this by solving a series of linear equations using 
 *  a least-squares approach.
 *
 *  We can model the expected value y as an nth degree polynomial, yielding

wolterlw

/* 
parameter JSON
{
  "num_layers": 5,
  "min_scale": 0.1171875,
  "max_scale": 0.75,
  "input_size_height": 256,
  "input_size_width": 256,
  "anchor_offset_x": 0.5,
  "anchor_offset_y": 0.5,