def test_general():
for condition_custom in [{}, {"x_order": OrderNCHW}]:
condition = dict(condition_default)
condition.update(condition_custom)
vx = np.random.rand(2, 3, 4, 5) - 0.5
vy = 1 / (1 + np.exp(-vx))
x = Variable(vx.shape, order=OrderNHWC)
y, = Sigmoid(None)(x)
x.change_order(condition["x_order"])
y.change_order(condition["y_order"])
generate_kernel_test_case(
description=f"Sigmoid: " +
(", ".join([f"{k}={v}" for k, v in condition_custom.items()])),
backend=condition["backend"],
graph=Graph([x], [y]),
inputs={
x: ConstantVariable(vx, OrderNHWC).change_order(x.order).data
},
expected={
y: ConstantVariable(vy, OrderNHWC).change_order(y.order).data
},
raise_skip=False)
raise SkipTest
def do_activation(activation: any, x: Variable) -> Variable:
if activation is keras.activations.relu:
return Relu(None)(x)[0]
elif activation is keras.activations.sigmoid:
return Sigmoid(None)(x)[0]
elif activation is keras.activations.hard_sigmoid:
return HardSigmoid(None)(x)[0]
elif activation is keras.activations.softplus:
return Softplus(None, beta=1.0)(x)[0]
elif activation is keras.activations.softsign:
return Softsign(None)(x)[0]
elif activation is keras.activations.softmax:
return Softmax(None, axis=x.order.axes[-1])(x)[0]
elif activation is keras.activations.elu:
return Elu(None)(x)[0]
elif activation is keras.activations.tanh:
return Tanh(None)(x)[0]
elif activation is keras.activations.linear:
return x
else:
raise NotImplementedError(
f"[KerasConverter] Unknown activation: {activation}")
def template(x_order=OrderNHWC, y_order=OrderNHWC, description: str = ""):
vx = np.random.rand(2, 3, 4, 5) - 0.5
vy = 1 / (1 + np.exp(-vx))
x = Variable(vx.shape, order=OrderNHWC)
y, = Sigmoid(None)(x)
x.change_order(x_order)
y.change_order(y_order)
generate_kernel_test_case(
description=f"Sigmoid {description}",
graph=Graph([x], [y]),
inputs={
x: np.transpose(vx, [OrderNHWC.axes_dict[a] for a in x.order.axes])
},
expected={
y: np.transpose(vy, [OrderNHWC.axes_dict[a] for a in y.order.axes])
},
)
def template(r=1.0, x_order=OrderNHWC, y_order=OrderNHWC, description: str = ""):
vx = (np.random.rand(2, 3, 4, 5) - 0.5) * r
vy = 1 / (1 + np.exp(-vx))
# This produces very small positive value (< 1e-7) when vx is negative large.
# Actual implementation uses tanh(0.5f * x0) * 0.5f + 0.5f
# In the case tanh is used, the result saturates to 0.0 when vs is negative large.
# ABS_EPS is set to allow such case.
x = Variable(vx.shape, order=OrderNHWC)
y, = Sigmoid(None)(x)
x.change_order(x_order)
y.change_order(y_order)
generate_kernel_test_case(
description=f"Sigmoid {description}",
graph=Graph([x], [y]),
inputs={x: np.transpose(vx, [OrderNHWC.axes_dict[a] for a in x.order.axes])},
expected={y: np.transpose(vy, [OrderNHWC.axes_dict[a] for a in y.order.axes])},
ABS_EPS=1e-7
)
def _convert_sigmoid(converter: ONNXConverter, onnx_op: INodeProto):
x0 = converter.get_variable(onnx_op.input[0])
y, = Sigmoid(None)(x0)
converter.set_variable(onnx_op.output[0], y)
def _convert_sigmoid(converter: ChainerConverter,
c_op: "chainer.functions.Sigmoid"):
x = converter.get_variable(c_op.inputs[0])
y, = Sigmoid(None)(x)
converter.set_variable(c_op.outputs[0](), y)