def grad(self, inputs, outputs_gradients):
grad = [
[
disconnected_type(),
] * 4,
] * 3
return grad
def grad(self, inputs, output_gradients):
num_ins = len(inputs)
if num_ins == 3:
x, v, sorter = inputs
else:
x, v = inputs
x_grad = gradient._float_zeros_like(x)
v_grad = gradient._float_zeros_like(v)
if num_ins == 3:
return [x_grad, v_grad, disconnected_type()]
else:
return [x_grad, v_grad]
def grad(self, inp, grads): x, w, xq, xmin, xmax, wq, wmin, wmax, z = inp gz, = grads # quantizing Output's gradient gzmax = 8.* T.std(gz) gzmin = -gzmax # gzq = gz gzq = quantizer(gz,new_min=gzmin,new_max=gzmax, stochastic=True) # Inputs' gradient # Low precision dot product gxq = T.dot(T.cast(gzq,'float32'),T.cast(wq.T,'float32')) gxq = unquantizer(gzq, wq.T, gxq, x_min = gzmin, x_max=gzmax, y_min=wmin, y_max=wmax) gx = gxq # Weights' gradient # Low precision dot product gwq = T.dot(T.cast(xq.T,'float32'),T.cast(gzq,'float32')) gwq = unquantizer(xq.T, gzq, gwq, x_min = xmin, x_max=xmax, y_min=gzmin, y_max=gzmax) gw = gwq return gx, gw, gxq, disconnected_type(), disconnected_type(), gwq, disconnected_type(), disconnected_type(), gz
def grad(self, *args, **kwargs):
return disconnected_type(), disconnected_type()
def grad(self, inputs, outputs_gradients):
# The gradient of all outputs is 0 w.r.t to all inputs
return [disconnected_type(),]*5
def grad(self, *args, **kwargs):
return disconnected_type(), disconnected_type()
def grad(self, inputs, outputs_gradients):
# The gradient of all outputs is 0 w.r.t to all inputs
return [disconnected_type(),]*5
def grad(self, inputs, outputs_gradients):
grad_0 = disconnected_type()
grad_1 = disconnected_type()
return [grad_0, grad_1]
def grad(self, inputs, outputs_gradients):
grad_0 = self(*inputs)[1]
grad_1 = disconnected_type()
grad_2 = disconnected_type()
return [grad_0, grad_1, grad_2]
