onnx 1.16.1__cp311-cp311-win_amd64.whl → 1.17.0__cp311-cp311-win_amd64.whl

onnx/reference/ops/op_batch_normalization.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 
@@ -51,7 +51,18 @@ def _batchnorm_training_mode(
 
 
 class BatchNormalization_6(OpRun):
-    def _run(self, x, scale, bias, mean, var, epsilon=None, is_test=None, momentum=None, spatial=None):  # type: ignore
+    def _run(
+        self,
+        x,
+        scale,
+        bias,
+        mean,
+        var,
+        epsilon=None,
+        is_test=None,
+        momentum=None,
+        spatial=None,  # noqa: ARG002
+    ):  # type: ignore
         if is_test:
             res = _batchnorm_test_mode(x, scale, bias, mean, var, epsilon=epsilon)
         else:

onnx/reference/ops/op_bernoulli.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 from onnx.helper import np_dtype_to_tensor_dtype
 from onnx.reference.ops._op_common_random import _CommonRandom

onnx/reference/ops/op_bitshift.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_bitwise_and.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_bitwise_not.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_bitwise_or.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_bitwise_xor.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_blackman_window.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_cast.py

@@ -1,11 +1,20 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 
 from onnx import subbyte
+from onnx._custom_element_types import (
+    bfloat16,
+    float8e4m3fn,
+    float8e4m3fnuz,
+    float8e5m2,
+    float8e5m2fnuz,
+    int4,
+    uint4,
+)
 from onnx.helper import (
     float32_to_bfloat16,
     float32_to_float8e4m3,
@@ -18,15 +27,6 @@ from onnx.numpy_helper import (
     float8e5m2_to_float32,
 )
 from onnx.onnx_pb import TensorProto
-from onnx.reference.custom_element_types import (
-    bfloat16,
-    float8e4m3fn,
-    float8e4m3fnuz,
-    float8e5m2,
-    float8e5m2fnuz,
-    int4,
-    uint4,
-)
 from onnx.reference.op_run import OpRun
 
 
@@ -94,6 +94,7 @@ def cast_to(x, to, saturate):  # noqa: PLR0911
             for i in range(y.shape[0]):
                 el = subbyte.float32_to_4bit_unpacked(xf[i], signed=signed)
                 y[i] = el
+            # This operator preduces a tensor with the same shape for INT4.
             return y.reshape(x.shape)
 
     f8back = {

onnx/reference/ops/op_cast_like.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 from onnx.helper import np_dtype_to_tensor_dtype
 from onnx.onnx_pb import TensorProto

onnx/reference/ops/op_ceil.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_celu.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_center_crop_pad.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_clip.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_col2im.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 
@@ -62,7 +62,9 @@ def _col2im_shape_check_2d(X, output_shape, kernel_shape, dilations, pads, strid
         )
 
 
-def _col2im_naive_implementation_2d(res, image_shape, kernel_shape, dilations, pads, strides):  # type: ignore
+def _col2im_naive_implementation_2d(
+    res, image_shape, kernel_shape, dilations, pads, strides
+):  # type: ignore
     # source: https://github.com/pytorch/pytorch/blob/master/aten/src/ATen/native/im2col.h
 
     n_dims = len(pads) // 2
@@ -142,7 +144,9 @@ def _col2im_shape_check(X, output_shape, kernel_shape, dilations, pads, strides)
         )
 
 
-def col2im_naive_implementation(data, image_shape, kernel_shape, dilations, pads, strides):  # type: ignore
+def col2im_naive_implementation(
+    data, image_shape, kernel_shape, dilations, pads, strides
+):  # type: ignore
     """Naive implementation for `col2im`."""
     n_dims = len(pads) // 2
     new_pads = np.array([(pads[i], pads[i + n_dims]) for i in range(n_dims)])
@@ -181,7 +185,9 @@ def col2im_naive_implementation(data, image_shape, kernel_shape, dilations, pads
 
 
 class Col2Im(OpRun):
-    def _run(self, data, image_shape, block_shape, dilations=None, pads=None, strides=None):  # type: ignore
+    def _run(
+        self, data, image_shape, block_shape, dilations=None, pads=None, strides=None
+    ):  # type: ignore
         if dilations is None:
             dilations = [1 for s in image_shape]
         if pads is None:

onnx/reference/ops/op_compress.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_concat.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_concat_from_sequence.py

@@ -1,16 +1,16 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
+from __future__ import annotations
 
-
-from typing import Any, List
+from typing import Any
 
 import numpy as np
 
 from onnx.reference.op_run import OpRun
 
 
-def _concat_from_sequence(seq: List[Any], axis: int, new_axis: int = 0) -> np.ndarray:
+def _concat_from_sequence(seq: list[Any], axis: int, new_axis: int = 0) -> np.ndarray:
     if new_axis == 1:
         seq2 = [s[..., np.newaxis] for s in seq]
         res = np.concatenate(seq2, axis=-1)

onnx/reference/ops/op_constant.py

@@ -1,11 +1,11 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 
-from onnx.reference.custom_element_types import (
+from onnx._custom_element_types import (
     bfloat16,
     float8e4m3fn,
     float8e4m3fnuz,

onnx/reference/ops/op_constant_of_shape.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_conv.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 
@@ -124,9 +124,9 @@ def _conv_implementation(  # type: ignore
         if B is not None:
             res[:, :, :] += B.reshape((1, -1, 1))  # type: ignore
 
-        for n in range(0, sN):
+        for n in range(sN):
             for nw in range(W.shape[0]):
-                for c in range(0, sC):
+                for c in range(sC):
                     w = W[nw : nw + 1, c : c + 1]
                     for io in range(bh, eh, sth):
                         hr = (io - bh) // sth
@@ -171,9 +171,9 @@ def _conv_implementation(  # type: ignore
         if B is not None:
             res[:, :, :, :] = B.reshape((1, -1, 1, 1))  # type: ignore
 
-        for n in range(0, sN):
+        for n in range(sN):
             for nw in range(W.shape[0]):
-                for c in range(0, sC):
+                for c in range(sC):
                     w = W[nw : nw + 1, c : c + 1]
                     for io in range(bh, eh, sth):
                         hr = (io - bh) // sth
@@ -189,11 +189,13 @@ def _conv_implementation(  # type: ignore
                             iw1, iw2 = max(0, j + ow), min(j + ow + kw, sW)
                             img = X[n : n + 1, c : c + 1, ih1:ih2, iw1:iw2]
                             if img.shape != w.shape:
-                                jh1, jh2 = max(-oh - i, 0), min(
-                                    kh, kh + sH - (i + oh + kh)
+                                jh1, jh2 = (
+                                    max(-oh - i, 0),
+                                    min(kh, kh + sH - (i + oh + kh)),
                                 )
-                                jw1, jw2 = max(-ow - j, 0), min(
-                                    kw, kw + sW - (j + ow + kw)
+                                jw1, jw2 = (
+                                    max(-ow - j, 0),
+                                    min(kw, kw + sW - (j + ow + kw)),
                                 )
                                 w_ = w[:1, :1, jh1:jh2, jw1:jw2]
                                 if img.shape != w_.shape:
@@ -229,9 +231,9 @@ def _conv_implementation(  # type: ignore
         if B is not None:
             res[:, :, :, :, :] = B.reshape((1, -1, 1, 1, 1))  # type: ignore
 
-        for n in range(0, sN):
+        for n in range(sN):
             for nw in range(W.shape[0]):
-                for c in range(0, sC):
+                for c in range(sC):
                     w = W[nw : nw + 1, c : c + 1]
                     for io in range(bh, eh, sth):
                         hr = (io - bh) // sth
@@ -253,14 +255,17 @@ def _conv_implementation(  # type: ignore
                                 iz1, iz2 = max(0, z + oz), min(z + oz + kz, sZ)
                                 img = X[n : n + 1, c : c + 1, ih1:ih2, iw1:iw2, iz1:iz2]
                                 if img.shape != w.shape:
-                                    jh1, jh2 = max(-oh - i, 0), min(
-                                        kh, kh + sH - (i + oh + kh)
+                                    jh1, jh2 = (
+                                        max(-oh - i, 0),
+                                        min(kh, kh + sH - (i + oh + kh)),
                                     )
-                                    jw1, jw2 = max(-ow - j, 0), min(
-                                        kw, kw + sW - (j + ow + kw)
+                                    jw1, jw2 = (
+                                        max(-ow - j, 0),
+                                        min(kw, kw + sW - (j + ow + kw)),
                                     )
-                                    jz1, jz2 = max(-oz - z, 0), min(
-                                        kz, kz + sZ - (z + oz + kz)
+                                    jz1, jz2 = (
+                                        max(-oz - z, 0),
+                                        min(kz, kz + sZ - (z + oz + kz)),
                                     )
                                     w_ = w[:1, :1, jh1:jh2, jw1:jw2, jz1:jz2]
                                     if img.shape != w_.shape:

onnx/reference/ops/op_conv_integer.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_conv_transpose.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 
@@ -24,8 +24,6 @@ class ConvTranspose(OpRun):
         pads=None,
         strides=None,
     ):
-        if group != 1:
-            raise RuntimeError(f"group={group} != 1 is not implemented yet.")
         if dilations is None:
             dilations = [1 for s in X.shape[2:]]
         if kernel_shape is None:
@@ -103,8 +101,41 @@ class ConvTranspose(OpRun):
                         res += B[c]
                     final[image_id, c, ...] = res[...]
         else:
-            raise NotImplementedError(
-                f"Implementation for group={group} > 1 is not available yet."
-            )
+            final = np.zeros((X.shape[0], num_output_channels, *output_shape))
+            output_array = []
+
+            for group_id in range(group):
+                group_X = X[:, group_id * C // group : (group_id + 1) * C // group, ...]
+                group_W = W[
+                    group_id
+                    * num_output_channels
+                    // group : (group_id + 1)
+                    * num_output_channels
+                    // group,
+                    ...,
+                ]
+
+                group_output = self._run(
+                    group_X,
+                    group_W,
+                    B=B,
+                    auto_pad=auto_pad,
+                    dilations=dilations,
+                    group=1,
+                    kernel_shape=kernel_shape,
+                    output_padding=output_padding,
+                    output_shape=output_shape,
+                    pads=pads,
+                    strides=strides,
+                )
+                group_output = np.array(group_output[0])
+                output_array.append(group_output)
+
+            for image_id in range(X.shape[0]):
+                for group_id in range(group):
+                    group_output = output_array[group_id]
+                    final[image_id, group_id : (group_id + 1), ...] = group_output[
+                        image_id, ...
+                    ]
 
         return (final.astype(X.dtype),)  # type: ignore[union-attr]

onnx/reference/ops/op_cos.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_cosh.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_cum_sum.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_deform_conv.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 #
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_depth_to_space.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_dequantize_linear.py

@@ -1,16 +1,12 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
-
-from typing import Optional
+from __future__ import annotations
 
 import numpy as np
 
 from onnx import TensorProto
-from onnx.helper import np_dtype_to_tensor_dtype
-from onnx.numpy_helper import float8e4m3_to_float32, float8e5m2_to_float32
-from onnx.reference.custom_element_types import (
+from onnx._custom_element_types import (
     float8e4m3fn,
     float8e4m3fnuz,
     float8e5m2,
@@ -18,6 +14,8 @@ from onnx.reference.custom_element_types import (
     int4,
     uint4,
 )
+from onnx.helper import np_dtype_to_tensor_dtype
+from onnx.numpy_helper import float8e4m3_to_float32, float8e5m2_to_float32
 from onnx.reference.op_run import OpRun
 from onnx.reference.ops.op_quantize_linear import reshape_input
 
@@ -45,9 +43,9 @@ class _CommonDequantizeLinear(OpRun):
         self,
         x: np.ndarray,
         x_scale: np.ndarray,
-        x_zero_point: Optional[np.ndarray] = None,
-        axis: Optional[int] = None,
-        block_size: Optional[int] = None,
+        x_zero_point: np.ndarray | None = None,
+        axis: int | None = None,
+        block_size: int | None = None,
     ):  # type: ignore
         x_type = self.get_x_type(x)
         fp8_type = x_type in {

onnx/reference/ops/op_det.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_dft.py

@@ -82,7 +82,14 @@ def _cifft(
 
 
 class DFT_17(OpRun):
-    def _run(self, x: np.ndarray, dft_length: int | None = None, axis: int = 1, inverse: bool = False, onesided: bool = False) -> tuple[np.ndarray]:  # type: ignore
+    def _run(
+        self,
+        x: np.ndarray,
+        dft_length: int | None = None,
+        axis: int = 1,
+        inverse: bool = False,
+        onesided: bool = False,
+    ) -> tuple[np.ndarray]:  # type: ignore
         # Convert to positive axis
         axis = axis % len(x.shape)
         if dft_length is None:
@@ -95,7 +102,14 @@ class DFT_17(OpRun):
 
 
 class DFT_20(OpRun):
-    def _run(self, x: np.ndarray, dft_length: int | None = None, axis: int = -2, inverse: bool = False, onesided: bool = False) -> tuple[np.ndarray]:  # type: ignore
+    def _run(
+        self,
+        x: np.ndarray,
+        dft_length: int | None = None,
+        axis: int = -2,
+        inverse: bool = False,
+        onesided: bool = False,
+    ) -> tuple[np.ndarray]:  # type: ignore
         # Convert to positive axis
         axis = axis % len(x.shape)
         if dft_length is None:

onnx/reference/ops/op_div.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np
 

onnx/reference/ops/op_dropout.py

@@ -1,9 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
-
-from typing import Optional, Tuple
+from __future__ import annotations
 
 import numpy as np
 from numpy.random import RandomState  # type: ignore
@@ -14,10 +12,10 @@ from onnx.reference.op_run import OpRun
 def _dropout(
     X: np.ndarray,
     drop_probability: float = 0.5,
-    seed: Optional[int] = None,
+    seed: int | None = None,
     training_mode: bool = False,
     return_mask: bool = False,
-) -> Tuple[np.ndarray]:
+) -> tuple[np.ndarray]:
     if drop_probability == 0 or not training_mode:
         if return_mask:
             return X, np.ones(X.shape, dtype=bool)  # type: ignore
@@ -37,10 +35,10 @@ class DropoutBase(OpRun):
     def _private_run(
         self,
         X: np.ndarray,
-        seed: Optional[int] = None,
+        seed: int | None = None,
         ratio: float = 0.5,
         training_mode: bool = False,
-    ) -> Tuple[np.ndarray]:
+    ) -> tuple[np.ndarray]:
         return _dropout(
             X,
             ratio,
@@ -61,5 +59,8 @@ class Dropout_12(DropoutBase):
         ratio = 0.5 if len(inputs) <= 1 else inputs[1]
         training_mode = False if len(inputs) <= 2 else inputs[2]
         return self._private_run(
-            X, seed=seed, ratio=ratio, training_mode=training_mode  # type: ignore
+            X,
+            seed=seed,
+            ratio=ratio,
+            training_mode=training_mode,  # type: ignore
         )

onnx/reference/ops/op_dynamic_quantize_linear.py

@@ -1,7 +1,7 @@
 # Copyright (c) ONNX Project Contributors
 
 # SPDX-License-Identifier: Apache-2.0
-
+from __future__ import annotations
 
 import numpy as np