def delta_outputSoftMax(self, calculated, correct):
derivative = calculated.copy()
cp.apply_scalar_functor(derivative, cp.scalar_functor.EXP)
sums = cp.dev_tensor_float(calculated.shape[1])
cp.fill(sums,0)
cp.reduce_to_row(sums, derivative, cp.reduce_functor.ADD)
cp.apply_scalar_functor(sums,cp.scalar_functor.ADD,0.1/derivative.shape[0])
rv = cp.transposed_view(derivative)
cp.matrix_divide_col(rv,sums)
cp.apply_binary_functor(derivative, correct, cp.binary_functor.AXPBY, -1.,1.)
sums.dealloc()
return derivative
def delta_outputSoftMax(self, calculated, correct):
derivative = calculated.copy()
cp.apply_scalar_functor(derivative, cp.scalar_functor.EXP)
sums = cp.dev_tensor_float(calculated.shape[1])
cp.fill(sums, 0)
cp.reduce_to_row(sums, derivative, cp.reduce_functor.ADD)
cp.apply_scalar_functor(sums, cp.scalar_functor.ADD,
0.1 / derivative.shape[0])
rv = cp.transposed_view(derivative)
cp.matrix_divide_col(rv, sums)
cp.apply_binary_functor(derivative, correct, cp.binary_functor.AXPBY,
-1., 1.)
sums.dealloc()
return derivative
def normalize_minmax(self,batch):
""" normalize by subtracting min and dividing by range"""
cp.matrix_plus_col(batch,self.negative_min)
cp.matrix_divide_col(batch,self.range)
def normalize_zmuv(self,batch):
""" Zero Mean, Unit Variance based on recorded statistics """
cp.matrix_plus_col(batch,self.negative_mean)
cp.matrix_divide_col(batch,self.std)
def normalize_minmax(self, batch):
""" normalize by subtracting min and dividing by range"""
cp.matrix_plus_col(batch, self.negative_min)
cp.matrix_divide_col(batch, self.range)
def normalize_zmuv(self, batch):
""" Zero Mean, Unit Variance based on recorded statistics """
cp.matrix_plus_col(batch, self.negative_mean)
cp.matrix_divide_col(batch, self.std)