tensorcircuit-nightly 1.2.0.dev20250326__py3-none-any.whl → 1.4.0.dev20251128__py3-none-any.whl

tensorcircuit/gates.py

@@ -34,6 +34,12 @@ one_state = np.array([0.0, 1.0], dtype=npdtype)
 plus_state = 1.0 / np.sqrt(2) * (zero_state + one_state)
 minus_state = 1.0 / np.sqrt(2) * (zero_state - one_state)
 
+# Common elements as np.ndarray objects
+_i00 = np.array([[1.0, 0.0], [0.0, 0.0]])
+_i01 = np.array([[0.0, 1.0], [0.0, 0.0]])
+_i10 = np.array([[0.0, 0.0], [1.0, 0.0]])
+_i11 = np.array([[0.0, 0.0], [0.0, 1.0]])
+
 # Common single qubit gates as np.ndarray objects
 _h_matrix = 1 / np.sqrt(2) * np.array([[1.0, 1.0], [1.0, -1.0]])
 _i_matrix = np.array([[1.0, 0.0], [0.0, 1.0]])
@@ -229,7 +235,7 @@ def num_to_tensor(*num: Union[float, Tensor], dtype: Optional[str] = None) -> An
     # TODO(@YHPeter): fix __doc__ for same function with different names
 
     l = []
-    if not dtype:
+    if dtype is None:
         dtype = dtypestr
     for n in num:
         if not backend.is_tensor(n):
@@ -245,7 +251,7 @@ array_to_tensor = num_to_tensor
 
 
 def gate_wrapper(m: Tensor, n: Optional[str] = None) -> Gate:
-    if not n:
+    if n is None:
         n = "unknowngate"
     m = m.astype(npdtype)
     return Gate(deepcopy(m), name=n)
@@ -255,7 +261,7 @@ class GateF:
     def __init__(
         self, m: Tensor, n: Optional[str] = None, ctrl: Optional[List[int]] = None
     ):
-        if not n:
+        if n is None:
             n = "unknowngate"
         self.m = m
         self.n = n
@@ -310,7 +316,7 @@ class GateF:
 
             return Gate(cu, name="c" + self.n)
 
-        if not self.ctrl:
+        if self.ctrl is None:
             ctrl = [1]
         else:
             ctrl = [1] + self.ctrl
@@ -330,7 +336,7 @@ class GateF:
             # TODO(@refraction-ray): ctrl convention to be finally determined
             return Gate(ocu, name="o" + self.n)
 
-        if not self.ctrl:
+        if self.ctrl is None:
             ctrl = [0]
         else:
             ctrl = [0] + self.ctrl
@@ -349,7 +355,7 @@ class GateVF(GateF):
         n: Optional[str] = None,
         ctrl: Optional[List[int]] = None,
     ):
-        if not n:
+        if n is None:
             n = "unknowngate"
         self.f = f
         self.n = n
@@ -483,7 +489,7 @@ def phase_gate(theta: float = 0) -> Gate:
     :rtype: Gate
     """
     theta = array_to_tensor(theta)
-    i00, i11 = array_to_tensor(np.array([[1, 0], [0, 0]]), np.array([[0, 0], [0, 1]]))
+    i00, i11 = array_to_tensor(_i00, _i11)
     unitary = i00 + backend.exp(1.0j * theta) * i11
     return Gate(unitary)
 
@@ -512,7 +518,7 @@ def get_u_parameter(m: Tensor) -> Tuple[float, float, float]:
     return theta, phi, lbd
 
 
-def u_gate(theta: float = 0, phi: float = 0, lbd: float = 0) -> Gate:
+def u_gate(theta: float = 0.0, phi: float = 0.0, lbd: float = 0.0) -> Gate:
     r"""
     IBMQ U gate following the converntion of OpenQASM3.0.
     See `OpenQASM doc <https://openqasm.com/language/gates.html#built-in-gates>`_
@@ -533,12 +539,7 @@ def u_gate(theta: float = 0, phi: float = 0, lbd: float = 0) -> Gate:
     :rtype: Gate
     """
     theta, phi, lbd = array_to_tensor(theta, phi, lbd)
-    i00, i01, i10, i11 = array_to_tensor(
-        np.array([[1, 0], [0, 0]]),
-        np.array([[0, 1], [0, 0]]),
-        np.array([[0, 0], [1, 0]]),
-        np.array([[0, 0], [0, 1]]),
-    )
+    i00, i01, i10, i11 = array_to_tensor(_i00, _i01, _i10, _i11)
     unitary = (
         backend.cos(theta / 2) * i00
         - backend.exp(1.0j * lbd) * backend.sin(theta / 2) * i01
@@ -548,7 +549,7 @@ def u_gate(theta: float = 0, phi: float = 0, lbd: float = 0) -> Gate:
     return Gate(unitary)
 
 
-def r_gate(theta: float = 0, alpha: float = 0, phi: float = 0) -> Gate:
+def r_gate(theta: float = 0.0, alpha: float = 0.0, phi: float = 0.0) -> Gate:
     r"""
     General single qubit rotation gate
 
@@ -582,7 +583,7 @@ def r_gate(theta: float = 0, alpha: float = 0, phi: float = 0) -> Gate:
 # r = r_gate
 
 
-def rx_gate(theta: float = 0) -> Gate:
+def rx_gate(theta: float = 0.0) -> Gate:
     r"""
     Rotation gate along :math:`x` axis.
 
@@ -603,7 +604,7 @@ def rx_gate(theta: float = 0) -> Gate:
 # rx = rx_gate
 
 
-def ry_gate(theta: float = 0) -> Gate:
+def ry_gate(theta: float = 0.0) -> Gate:
     r"""
     Rotation gate along :math:`y` axis.
 
@@ -624,7 +625,7 @@ def ry_gate(theta: float = 0) -> Gate:
 # ry = ry_gate
 
 
-def rz_gate(theta: float = 0) -> Gate:
+def rz_gate(theta: float = 0.0) -> Gate:
     r"""
     Rotation gate along :math:`z` axis.
 
@@ -645,7 +646,7 @@ def rz_gate(theta: float = 0) -> Gate:
 # rz = rz_gate
 
 
-def rgate_theoretical(theta: float = 0, alpha: float = 0, phi: float = 0) -> Gate:
+def rgate_theoretical(theta: float = 0.0, alpha: float = 0.0, phi: float = 0.0) -> Gate:
     r"""
     Rotation gate implemented by matrix exponential. The output is the same as `rgate`.
 
@@ -723,7 +724,7 @@ def iswap_gate(theta: float = 1.0) -> Gate:
 # iswap = iswap_gate
 
 
-def cr_gate(theta: float = 0, alpha: float = 0, phi: float = 0) -> Gate:
+def cr_gate(theta: float = 0.0, alpha: float = 0.0, phi: float = 0.0) -> Gate:
     r"""
     Controlled rotation gate. When the control qubit is 1, `rgate` is applied to the target qubit.
 
@@ -775,7 +776,7 @@ def random_two_qubit_gate() -> Gate:
     return Gate(deepcopy(unitary), name="R2Q")
 
 
-def any_gate(unitary: Tensor, name: str = "any") -> Gate:
+def any_gate(unitary: Tensor, name: str = "any", dim: Optional[int] = None) -> Gate:
     """
     Note one should provide the gate with properly reshaped.
 
@@ -783,6 +784,8 @@ def any_gate(unitary: Tensor, name: str = "any") -> Gate:
     :type unitary: Tensor
     :param name: The name of the gate.
     :type name: str
+    :param dim: The dimension of the gate.
+    :type dim: int
     :return: the resulted gate
     :rtype: Gate
     """
@@ -791,7 +794,10 @@ def any_gate(unitary: Tensor, name: str = "any") -> Gate:
         unitary.tensor = backend.cast(unitary.tensor, dtypestr)
         return unitary
     unitary = backend.cast(unitary, dtypestr)
-    unitary = backend.reshape2(unitary)
+    if dim is None or dim == 2:
+        unitary = backend.reshape2(unitary)
+    else:
+        unitary = backend.reshaped(unitary, dim)
     # nleg = int(np.log2(backend.sizen(unitary)))
     # unitary = backend.reshape(unitary, [2 for _ in range(nleg)])
     return Gate(unitary, name=name)
@@ -864,6 +870,43 @@ def exponential_gate_unity(
     return Gate(mat, name="exp1-" + name)
 
 
+def su4_gate(theta: Tensor, name: str = "su(4)") -> Gate:
+    r"""
+    Two-qubit general SU(4) gate.
+
+    :param theta: the angle tensor (15 components) of the gate.
+    :type theta: Tensor
+    :param name: the name of the gate.
+    :type name: str
+    :return: a gate object.
+    :rtype: Gate
+    """
+    theta = num_to_tensor(theta)
+    pauli_ops = array_to_tensor(
+        _ix_matrix,
+        _iy_matrix,
+        _iz_matrix,
+        _xi_matrix,
+        _xx_matrix,
+        _xy_matrix,
+        _xz_matrix,
+        _yi_matrix,
+        _yx_matrix,
+        _yy_matrix,
+        _yz_matrix,
+        _zi_matrix,
+        _zx_matrix,
+        _zy_matrix,
+        _zz_matrix,
+    )
+    generator = backend.sum(
+        backend.stack([theta[i] * pauli_ops[i] for i in range(15)]), axis=0
+    )
+    mat = backend.expm(-1j * generator)
+    mat = backend.reshape2(mat)
+    return Gate(mat, name=name)
+
+
 exp1_gate = exponential_gate_unity
 # exp1 = exponential_gate_unity
 rzz_gate = partial(exp1_gate, unitary=_zz_matrix, half=True)
@@ -968,6 +1011,7 @@ def meta_vgate() -> None:
         "rzz",
         "rxx",
         "ryy",
+        "su4",
     ]:
         for funcname in [f, f + "gate"]:
             setattr(thismodule, funcname, GateVF(getattr(thismodule, f + "_gate"), f))

tensorcircuit/interfaces/jax.py

@@ -5,9 +5,6 @@ Interface wraps quantum function as a jax function
 from typing import Any, Callable, Tuple, Optional, Union, Sequence
 from functools import wraps, partial
 
-import jax
-from jax import custom_vjp
-
 from ..cons import backend
 from .tensortrans import general_args_to_backend
 
@@ -22,6 +19,8 @@ def jax_wrapper(
     ] = None,
     output_dtype: Optional[Union[Any, Sequence[Any]]] = None,
 ) -> Callable[..., Any]:
+    import jax
+
     @wraps(fun)
     def fun_jax(*x: Any) -> Any:
         def wrapped_fun(*args: Any) -> Any:
@@ -129,6 +128,9 @@ def create_jax_function(
     output_shape: Optional[Union[Tuple[int, ...], Tuple[()]]] = None,
     output_dtype: Optional[Any] = None,
 ) -> Callable[..., Any]:
+    import jax
+    from jax import custom_vjp
+
     if jit:
         fun = backend.jit(fun)
 

tensorcircuit/interfaces/tensortrans.py

@@ -132,13 +132,17 @@ def general_args_to_backend(
         target_backend = backend
     elif isinstance(target_backend, str):
         target_backend = get_backend(target_backend)
+    try:
+        t = backend.tree_map(target_backend.from_dlpack, caps)
+    except TypeError:
+        t = backend.tree_map(target_backend.from_dlpack, args)
+
     if dtype is None:
-        return backend.tree_map(target_backend.from_dlpack, caps)
+        return t
     if isinstance(dtype, str):
         leaves, treedef = backend.tree_flatten(args)
         dtype = [dtype for _ in range(len(leaves))]
         dtype = backend.tree_unflatten(treedef, dtype)
-    t = backend.tree_map(target_backend.from_dlpack, caps)
     t = backend.tree_map(target_backend.cast, t, dtype)
     return t
 

tensorcircuit/interfaces/torch.py

@@ -69,12 +69,14 @@ def torch_interface(
         @staticmethod
         def forward(ctx: Any, *x: Any) -> Any:  # type: ignore
             # ctx.xdtype = [xi.dtype for xi in x]
-            ctx.xdtype = backend.tree_map(lambda s: s.dtype, x)
+            ctx.save_for_backward(*x)
+            x_detached = backend.tree_map(lambda s: s.detach(), x)
+            ctx.xdtype = backend.tree_map(lambda s: s.dtype, x_detached)
             # (x, )
             if len(ctx.xdtype) == 1:
                 ctx.xdtype = ctx.xdtype[0]
-            ctx.device = (backend.tree_flatten(x)[0][0]).device
-            x = general_args_to_backend(x, enable_dlpack=enable_dlpack)
+            ctx.device = (backend.tree_flatten(x_detached)[0][0]).device
+            x = general_args_to_backend(x_detached, enable_dlpack=enable_dlpack)
             y = fun(*x)
             ctx.ydtype = backend.tree_map(lambda s: s.dtype, y)
             if len(x) == 1:
@@ -88,6 +90,9 @@ def torch_interface(
 
         @staticmethod
         def backward(ctx: Any, *grad_y: Any) -> Any:
+            x = ctx.saved_tensors
+            x_detached = backend.tree_map(lambda s: s.detach(), x)
+            x_backend = general_args_to_backend(x_detached, enable_dlpack=enable_dlpack)
             if len(grad_y) == 1:
                 grad_y = grad_y[0]
             grad_y = backend.tree_map(lambda s: s.contiguous(), grad_y)
@@ -96,7 +101,12 @@ def torch_interface(
             )
             # grad_y = general_args_to_numpy(grad_y)
             # grad_y = numpy_args_to_backend(grad_y, dtype=ctx.ydtype)  # backend.dtype
-            _, g = vjp_fun(ctx.x, grad_y)
+            if len(x_backend) == 1:
+                x_backend_for_vjp = x_backend[0]
+            else:
+                x_backend_for_vjp = x_backend
+
+            _, g = vjp_fun(x_backend_for_vjp, grad_y)
             # a redundency due to current vjp API
 
             r = general_args_to_backend(

tensorcircuit/keras.py

@@ -24,7 +24,7 @@ class QuantumLayer(Layer):  # type: ignore
         initializer: Union[Text, Sequence[Text]] = "glorot_uniform",
         constraint: Optional[Union[Text, Sequence[Text]]] = None,
         regularizer: Optional[Union[Text, Sequence[Text]]] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> None:
         """
         `QuantumLayer` wraps the quantum function `f` as a `keras.Layer`
@@ -103,7 +103,7 @@ class QuantumLayer(Layer):  # type: ignore
         inputs: tf.Tensor,
         training: Optional[bool] = None,
         mask: Optional[tf.Tensor] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> tf.Tensor:
         # input_shape = list(inputs.shape)
         # inputs = tf.reshape(inputs, (-1, input_shape[-1]))
@@ -154,7 +154,7 @@ class HardwareLayer(QuantumLayer):
         inputs: tf.Tensor,
         training: Optional[bool] = None,
         mask: Optional[tf.Tensor] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> tf.Tensor:
         if inputs is None:  # not possible
             result = self.f(*self.pqc_weights, **kwargs)