onnx 1.16.0__cp38-cp38-win32.whl → 1.16.2__cp38-cp38-win32.whl

onnx/backend/test/case/node/dequantizelinear.py

@@ -202,7 +202,7 @@ class DequantizeLinear(Base):
         # scalar zero point and scale
         x = make_tensor("x", TensorProto.UINT4, [5], [0, 1, 7, 10, 15])
         x_scale = np.float32(2)
-        x_zero_point = make_tensor("zero_point", TensorProto.UINT4, (1,), [1])
+        x_zero_point = make_tensor("x_zero_point", TensorProto.UINT4, (1,), [1])
         y = np.array([-2, 0, 12, 18, 28], dtype=np.float32)
 
         expect(
@@ -224,7 +224,7 @@ class DequantizeLinear(Base):
         # scalar zero point and scale
         x = make_tensor("x", TensorProto.INT4, [5], [0, 1, 7, -4, -8])
         x_scale = np.float32(2)
-        x_zero_point = make_tensor("zero_point", TensorProto.INT4, (1,), [1])
+        x_zero_point = make_tensor("x_zero_point", TensorProto.INT4, (1,), [1])
         y = np.array([-2, 0, 12, -10, -18], dtype=np.float32)
 
         expect(

onnx/backend/test/case/node/quantizelinear.py

@@ -73,7 +73,7 @@ class QuantizeLinear(Base):
 
         x = np.array([0.0, 1.0, 2.0, 100000.0, 200.0]).astype(np.float32)
         y_scale = np.float32(2)
-        y_zero_point = make_tensor("zero_point", TensorProto.FLOAT8E4M3FN, [1], [0])
+        y_zero_point = make_tensor("y_zero_point", TensorProto.FLOAT8E4M3FN, [1], [0])
         y = make_tensor("y", TensorProto.FLOAT8E4M3FN, [5], [0, 0.5, 1, 448, 96])
 
         expect(
@@ -93,7 +93,7 @@ class QuantizeLinear(Base):
 
         x = np.array([0.0, 1.0, 2.0, 100000.0, 200.0]).astype(np.float32)
         y_scale = np.float32(2)
-        y_zero_point = make_tensor("zero_point", TensorProto.FLOAT8E5M2, [1], [0.0])
+        y_zero_point = make_tensor("y_zero_point", TensorProto.FLOAT8E5M2, [1], [0.0])
         y = make_tensor("y", TensorProto.FLOAT8E5M2, [5], [0, 0.5, 1, 49152, 96])
 
         expect(
@@ -230,7 +230,7 @@ class QuantizeLinear(Base):
 
         y_scale = np.asarray([2.0, 3.0, 4.0], dtype=np.float32)
         y_zero_point = make_tensor(
-            "zero_point", TensorProto.UINT4, y_scale.shape, np.ones_like(y_scale)
+            "y_zero_point", TensorProto.UINT4, y_scale.shape, np.ones_like(y_scale)
         )
         y = make_tensor(
             "y", TensorProto.UINT4, x.shape, [1, 2, 3, 5, -1, -1, 3, 4, 4, 5, 5, 11]
@@ -262,7 +262,7 @@ class QuantizeLinear(Base):
 
         y_scale = np.asarray([2.0, 3.0, 4.0], dtype=np.float32)
         y_zero_point = make_tensor(
-            "zero_point", TensorProto.INT4, y_scale.shape, np.ones_like(y_scale)
+            "y_zero_point", TensorProto.INT4, y_scale.shape, np.ones_like(y_scale)
         )
         y = make_tensor(
             "y", TensorProto.INT4, x.shape, [1, 2, 3, 5, -8, -6, 3, 4, 4, 5, 5, 7]

onnx/backend/test/data/node/test_dequantizelinear_int4/test_data_set_0/input_2.pb

@@ -1,2 +1 @@
-
*

B
-zero_point
+
*

Bx_zero_point

onnx/backend/test/data/node/test_dequantizelinear_uint4/test_data_set_0/input_2.pb

@@ -1,2 +1 @@
-
*

B
-zero_point
+
*

Bx_zero_point

onnx/backend/test/data/node/test_quantizelinear_int4/test_data_set_0/input_2.pb

@@ -1,2 +1 @@
-*
B
-zero_point
+*
By_zero_point

onnx/backend/test/data/node/test_quantizelinear_uint4/test_data_set_0/input_2.pb

@@ -1,2 +1 @@
-*
B
-zero_point
+*
By_zero_point

onnx/backend/test/runner/__init__.py

@@ -10,7 +10,6 @@ import os
 import re
 import shutil
 import sys
-import tarfile
 import tempfile
 import time
 import unittest
@@ -238,8 +237,7 @@ class Runner:
             )
             urlretrieve(model_test.url, download_file.name)
             print("Done")
-            with tarfile.open(download_file.name) as t:
-                t.extractall(models_dir)
+            onnx.utils._extract_model_safe(download_file.name, models_dir)
         except Exception as e:
             print(f"Failed to prepare data for model {model_test.model_name}: {e}")
             raise

onnx/common/version.h

@@ -9,6 +9,6 @@
 namespace ONNX_NAMESPACE {
 
 // Represents the most recent release version. Updated with every release.
-constexpr const char* LAST_RELEASE_VERSION = "1.16.0";
+constexpr const char* LAST_RELEASE_VERSION = "1.16.2";
 
 } // namespace ONNX_NAMESPACE

onnx/defs/math/old.cc

@@ -2322,10 +2322,15 @@ ONNX_OPERATOR_SET_SCHEMA(
             auto transBAttr = ctx.getAttribute("transB");
             bool transB = transBAttr ? static_cast<int>(transBAttr->i()) != 0 : false;
 
+            checkInputRank(ctx, 0, 2);
+            checkInputRank(ctx, 1, 2);
+
+            auto& first_input_shape = getInputShape(ctx, 0);
+            auto& second_input_shape = getInputShape(ctx, 1);
             *ctx.getOutputType(0)->mutable_tensor_type()->mutable_shape()->add_dim() =
-                ctx.getInputType(0)->tensor_type().shape().dim(transA ? 1 : 0);
+                first_input_shape.dim(transA ? 1 : 0);
             *ctx.getOutputType(0)->mutable_tensor_type()->mutable_shape()->add_dim() =
-                ctx.getInputType(1)->tensor_type().shape().dim(transB ? 0 : 1);
+                second_input_shape.dim(transB ? 0 : 1);
           } else if (
               hasInputShape(ctx, 2) &&
               (!ctx.getAttribute("broadcast") || static_cast<int>(ctx.getAttribute("broadcast")->i()) == 0)) {

onnx/defs/quantization/defs.cc

@@ -200,6 +200,9 @@ ONNX_OPERATOR_SET_SCHEMA(
         .SetDoc(DequantizeLinear_ver21_doc)
         .TypeAndShapeInferenceFunction([](ONNX_NAMESPACE::InferenceContext& ctx) {
           propagateElemTypeFromInputToOutput(ctx, 1, 0);
+          if (!hasInputShape(ctx, 0)) {
+            return;
+          }
           auto& input_shape = getInputShape(ctx, 0);
           updateOutputShape(ctx, 0, input_shape);
         }));

onnx/defs/quantization/old.cc

@@ -130,6 +130,9 @@ ONNX_OPERATOR_SET_SCHEMA(
         .SetDoc(DequantizeLinear_ver19_doc)
         .TypeAndShapeInferenceFunction([](ONNX_NAMESPACE::InferenceContext& ctx) {
           propagateElemTypeFromInputToOutput(ctx, 1, 0);
+          if (!hasInputShape(ctx, 0)) {
+            return;
+          }
           auto& input_shape = getInputShape(ctx, 0);
           updateOutputShape(ctx, 0, input_shape);
         }));
@@ -181,7 +184,6 @@ ONNX_OPERATOR_SET_SCHEMA(
           if (!hasInputShape(ctx, 0)) {
             return;
           }
-
           auto& input_shape = getInputShape(ctx, 0);
           updateOutputShape(ctx, 0, input_shape);
         }));

onnx/defs/tensor/old.cc

@@ -1380,7 +1380,7 @@ ONNX_OPERATOR_SET_SCHEMA(
 
 static const char* Slice_ver11_doc = R"DOC(
 Produces a slice of the input tensor along multiple axes. Similar to numpy:
-https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html
+https://numpy.org/doc/stable/reference/routines.indexing.html
 Slices uses `starts`, `ends`, `axes` and `steps` inputs to specify the start and end
 dimension and step for each axis in the list of axes, it uses this information to
 slice the input `data` tensor. If a negative value is passed for any of the
@@ -4443,7 +4443,7 @@ ONNX_OPERATOR_SET_SCHEMA(
 
 static const char* Slice_ver1_doc = R"DOC(
 Produces a slice of the input tensor along multiple axes. Similar to numpy:
-https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html
+https://numpy.org/doc/stable/reference/routines.indexing.html
 Slices uses `axes`, `starts` and `ends` attributes to specify the start and end
 dimension for each axis in the list of axes, it uses this information to
 slice the input `data` tensor. If a negative value is passed for any of the
@@ -4559,7 +4559,7 @@ ONNX_OPERATOR_SET_SCHEMA(
 
 static const char* Slice_ver10_doc = R"DOC(
 Produces a slice of the input tensor along multiple axes. Similar to numpy:
-https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html
+https://numpy.org/doc/stable/reference/routines.indexing.html
 Slices uses `starts`, `ends`, `axes` and `steps` inputs to specify the start and end
 dimension and step for each axis in the list of axes, it uses this information to
 slice the input `data` tensor. If a negative value is passed for any of the

onnx/hub.py

@@ -9,7 +9,6 @@ import hashlib
 import json
 import os
 import sys
-import tarfile
 from io import BytesIO
 from os.path import join
 from typing import IO, Any, Dict, List, Optional, Set, Tuple, cast
@@ -296,6 +295,7 @@ def download_model_with_test_data(
     silent: bool = False,
 ) -> Optional[str]:
     """Downloads a model along with test data by name from the onnx model hub and returns the directory to which the files have been extracted.
+    Users are responsible for making sure the model comes from a trusted source, and the data is safe to be extracted.
 
     Args:
         model: The name of the onnx model in the manifest. This field is
@@ -361,12 +361,14 @@ def download_model_with_test_data(
                 "download the model from the model hub."
             )
 
-    with tarfile.open(local_model_with_data_path) as model_with_data_zipped:
-        # FIXME: Avoid index manipulation with magic numbers
-        local_model_with_data_dir_path = local_model_with_data_path[
-            0 : len(local_model_with_data_path) - 7
-        ]
-        model_with_data_zipped.extractall(local_model_with_data_dir_path)
+    # FIXME: Avoid index manipulation with magic numbers,
+    # remove ".tar.gz"
+    local_model_with_data_dir_path = local_model_with_data_path[
+        0 : len(local_model_with_data_path) - 7
+    ]
+    onnx.utils._extract_model_safe(
+        local_model_with_data_path, local_model_with_data_dir_path
+    )
     model_with_data_path = (
         local_model_with_data_dir_path
         + "/"

onnx/shape_inference/implementation.cc

@@ -488,29 +488,29 @@ class ShapeInferenceImplBase {
           ProcessCall(n, *(iter->second), ctx);
         } else {
           has_unsupported_op = true;
+          return;
         }
       } else {
         has_unsupported_op = true;
+        return;
       }
-      if (!has_unsupported_op) {
-        for (int i = 0; i < n.output_size(); ++i) {
-          // skip type and shape propagation for missing optional outputs.
-          if (!n.output(i).empty())
-            UpdateType(n.output(i), ctx.getOutputType(i));
-        }
-        // Constant values are tracked to improve inference/checking for subsequent nodes.
-        ProcessConstant(n);
-        // If data-propagation is enabled, partial-evaluation (aka data-propagation) is performed
-        // to improve inference/checking for subsequent nodes.
-        if (options.enable_data_propagation && schema && schema->has_data_propagation_function()) {
-          if (generated_shape_data_by_name == nullptr) {
-            fail_shape_inference(
-                "Container for generated shape data cannot be nullptr when enable_data_propagation option is set.");
-          }
-          DataPropagationContextImpl data_propagation_ctx(
-              n, value_types_by_name, input_data_by_name, *generated_shape_data_by_name);
-          schema->GetDataPropagationFunction()(data_propagation_ctx);
+      for (int i = 0; i < n.output_size(); ++i) {
+        // skip type and shape propagation for missing optional outputs.
+        if (!n.output(i).empty())
+          UpdateType(n.output(i), ctx.getOutputType(i));
+      }
+      // Constant values are tracked to improve inference/checking for subsequent nodes.
+      ProcessConstant(n);
+      // If data-propagation is enabled, partial-evaluation (aka data-propagation) is performed
+      // to improve inference/checking for subsequent nodes.
+      if (options.enable_data_propagation && schema && schema->has_data_propagation_function()) {
+        if (generated_shape_data_by_name == nullptr) {
+          fail_shape_inference(
+              "Container for generated shape data cannot be nullptr when enable_data_propagation option is set.");
         }
+        DataPropagationContextImpl data_propagation_ctx(
+            n, value_types_by_name, input_data_by_name, *generated_shape_data_by_name);
+        schema->GetDataPropagationFunction()(data_propagation_ctx);
       }
     }
     ONNX_CATCH(const ONNX_NAMESPACE::InferenceError& ex) {

onnx/tools/net_drawer.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 # A library and utility for drawing ONNX nets. Most of this implementation has
 # been borrowed from the caffe2 implementation
-# https://github.com/pytorch/pytorch/blob/master/caffe2/python/net_drawer.py
+# https://github.com/pytorch/pytorch/blob/v2.3.1/caffe2/python/net_drawer.py
 #
 # The script takes two required arguments:
 #   -input: a path to a serialized ModelProto .pb file.

onnx/utils.py

@@ -4,6 +4,7 @@
 from __future__ import annotations
 
 import os
+import tarfile
 
 import onnx.checker
 import onnx.helper
@@ -212,3 +213,65 @@ def extract_model(
     onnx.save(extracted, output_path)
     if check_model:
         onnx.checker.check_model(output_path)
+
+
+def _tar_members_filter(
+    tar: tarfile.TarFile, base: str | os.PathLike
+) -> list[tarfile.TarInfo]:
+    """Check that the content of ``tar`` will be extracted safely
+
+    Args:
+        tar: The tarball file
+        base: The directory where the tarball will be extracted
+
+    Returns:
+        list of tarball members
+    """
+    result = []
+    for member in tar:
+        member_path = os.path.join(base, member.name)
+        abs_base = os.path.abspath(base)
+        abs_member = os.path.abspath(member_path)
+        if not abs_member.startswith(abs_base):
+            raise RuntimeError(
+                f"The tarball member {member_path} in downloading model contains "
+                f"directory traversal sequence which may contain harmful payload."
+            )
+        elif member.issym() or member.islnk():
+            raise RuntimeError(
+                f"The tarball member {member_path} in downloading model contains "
+                f"symbolic links which may contain harmful payload."
+            )
+        result.append(member)
+    return result
+
+
+def _extract_model_safe(
+    model_tar_path: str | os.PathLike, local_model_with_data_dir_path: str | os.PathLike
+) -> None:
+    """Safely extracts a tar file to a specified directory.
+
+    This function ensures that the extraction process mitigates against
+    directory traversal vulnerabilities by validating or sanitizing paths
+    within the tar file. It also provides compatibility for different versions
+    of the tarfile module by checking for the availability of certain attributes
+    or methods before invoking them.
+
+    Args:
+        model_tar_path: The path to the tar file to be extracted.
+        local_model_with_data_dir_path: The directory path where the tar file
+      contents will be extracted to.
+    """
+    with tarfile.open(model_tar_path) as model_with_data_zipped:
+        # Mitigate tarball directory traversal risks
+        if hasattr(tarfile, "data_filter"):
+            model_with_data_zipped.extractall(
+                path=local_model_with_data_dir_path, filter="data"
+            )
+        else:
+            model_with_data_zipped.extractall(
+                path=local_model_with_data_dir_path,
+                members=_tar_members_filter(
+                    model_with_data_zipped, local_model_with_data_dir_path
+                ),
+            )

onnx/version.py

@@ -1,5 +1,5 @@
 # This file is generated by setup.py. DO NOT EDIT!
 
 
-version = "1.16.0"
-git_version = "990217f043af7222348ca8f0301e17fa7b841781"
+version = "1.16.2"
+git_version = "3bf92c03a9f27eba3bda1e5b9e63ea20ec213557"

{onnx-1.16.0.dist-info → onnx-1.16.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnx
-Version: 1.16.0
+Version: 1.16.2
 Summary: Open Neural Network Exchange
 Author-email: ONNX Contributors <onnx-technical-discuss@lists.lfaidata.foundation>
 License: Apache License v2.0
@@ -14,7 +14,7 @@ Requires-Dist: numpy >=1.20
 Requires-Dist: protobuf >=3.20.2
 Provides-Extra: reference
 Requires-Dist: google-re2 ; extra == 'reference'
-Requires-Dist: Pillow ; extra == 'reference'
+Requires-Dist: pillow ; extra == 'reference'
 
 <!--
 Copyright (c) ONNX Project Contributors

{onnx-1.16.0.dist-info → onnx-1.16.2.dist-info}/RECORD

@@ -7,7 +7,7 @@ onnx/cpp2py_export.cc,sha256=ffp_Z2wm5ABVrMi3OLIg086E1y1RRuN5rnOSqghIR-E,31228
 onnx/external_data_helper.py,sha256=teW0FLi_knNys0oA7pNL2znlUuD_cftOPVvwxqQ89qg,11910
 onnx/gen_proto.py,sha256=s21pPEC_HKO2_A0B0QPvcPHt7D-L3vr9n9LNexMuQYs,8887
 onnx/helper.py,sha256=ZlBHegNB76eElEjzbHZeLWOtj7IE52MQql90JzaOF5E,55671
-onnx/hub.py,sha256=Kv7Wly22sYxAxXTllGzOsvs9_6uKAQ5I4Uo9eBdquzs,18326
+onnx/hub.py,sha256=j7LiqxwN_guK3AlU_e-8RCfcZYPnI73USkCbf6WlQ-Y,18398
 onnx/inliner.py,sha256=Ukl3lPP9lC-lUNr2jQzwNZt6g0MPPcNUlxjEHKZbYPk,1772
 onnx/mapping.py,sha256=EEOhJsiUtONiin34fkMInjdOjtqTm3R_wsoNeDeC-W4,8457
 onnx/model_container.py,sha256=aXpLqFjZF2RbjbUni04xYtwVLxG1pr6YYXWx_zz_Pko,13104
@@ -22,7 +22,7 @@ onnx/onnx-operators.proto,sha256=JQbdYTnvJhfQrFk82zzzEKpokcOUujZ4QBKqvSJNBLU,543
 onnx/onnx-operators_pb.h,sha256=vlw2jzH5sZfKNzs6x4f34-riKuXPy9PjXbo8ZvOx068,202
 onnx/onnx.in.proto,sha256=XTWpwFI3cPFVEn4owXCId3oK6s6wdIIUB4TQCzyzgJE,38526
 onnx/onnx.proto,sha256=mej19HPF15gUvT_6r6hbxI3x7Mxc9pR-Crm7rR9cvnA,38116
-onnx/onnx_cpp2py_export.cp38-win32.pyd,sha256=eUfAGqPEZdVcrCiPaKTnd0yCcyxX6BZqu4zGazzQvuU,2503168
+onnx/onnx_cpp2py_export.cp38-win32.pyd,sha256=2BqceEZJSpEWtyRWhdfmGGUHNr2ny6_bQFf949ykNwA,2504704
 onnx/onnx_data_pb.py,sha256=Czjgcf0pv2Vk_mBsch2sG4bYkzRpNG1efzhhdEilN8I,94
 onnx/onnx_data_pb2.py,sha256=YuJmAGmOGE_ClfmD9Gbbc1qn9_FzOMDH61e7ay9t5xw,2894
 onnx/onnx_data_pb2.pyi,sha256=VTSip9Evt2RqdKpntIo6G9LVASJVfc6zJ-yy-T4kW_o,4682
@@ -42,8 +42,8 @@ onnx/serialization.py,sha256=kDFNFRgel53rW0V9ZS-tG5G0PV9Rms60TsOxbNOs1IM,8069
 onnx/shape_inference.py,sha256=eiCtyo0v5MR2JQIIe5lTk1E6pwxKgH-hhhpkbLJASrw,5951
 onnx/string_utils.h,sha256=jAFGm8XyB3PwvijH-0Cni_83gu1rfXQ7v16OGyPeuMU,1337
 onnx/subbyte.py,sha256=wYA14-QUhRWD829f-8cxPviSjffUb19rCJSuXIDdIfg,2361
-onnx/utils.py,sha256=OYvWSG_ulwV6e_h6udGrTPnHCbBnMns_y6G_mrDY0t4,8600
-onnx/version.py,sha256=zSedOo-BDfd9yHK95hMSLCTW_lDrdmV1oltOZWvHLtU,134
+onnx/utils.py,sha256=9ZbcvkYF9r849WoN4OSW55D6g4aNts9hcpKsLlPnT-o,11033
+onnx/version.py,sha256=V0os880BSkJTppWygfb6v6uUXpl0OrHRwpYMhDQ6GYQ,134
 onnx/version_converter.py,sha256=Qi0hGuU45xf8rD8E7W8f9MVgZiGIrPU5lzl2bOX6gG4,1274
 onnx/backend/__init__.py,sha256=HiuD-U6YHJwWikkemKJqBq-35U8KJ9LDdAwdisi7OlQ,85
 onnx/backend/base.py,sha256=myXeAXXVI31c_lcqxeAJNK3dRFncuJox2N55rTGANZ4,4680
@@ -109,7 +109,7 @@ onnx/backend/test/case/node/cosh.py,sha256=paohiM1-bYV3Uq5AeXM1MCXW_kPPabXA6vG7h
 onnx/backend/test/case/node/cumsum.py,sha256=dtoV_Rg1opPwMpx-jW6ItihP8roPkn5Ymp0brSt5jOQ,3482
 onnx/backend/test/case/node/deformconv.py,sha256=0kKFJlA45N3OE4YuSr_abaYqIXyDYEAnoEmiO1SyTKw,5647
 onnx/backend/test/case/node/depthtospace.py,sha256=UEryt7YdGewSq0dD5yzN5EVul5yOBkjaUFna9bt2h2Q,3632
-onnx/backend/test/case/node/dequantizelinear.py,sha256=6e5DqcT0bU4CVu6oUWCTI-yrC_6BkgBqMlJ3OTRA194,9404
+onnx/backend/test/case/node/dequantizelinear.py,sha256=0J7b5SaFatZoc6GaNVtLg1pIMhAm1Ly1KPiU7Vad68k,9408
 onnx/backend/test/case/node/det.py,sha256=aYZlgjZu0qmYUuuv6-6lZ4tW9CHr2PS6VU3wAL9KJ-U,1012
 onnx/backend/test/case/node/dft.py,sha256=tGoOa57NJWSJk8i6BFs1tQk-1YPp5xFVha-TNqYR0iE,3407
 onnx/backend/test/case/node/div.py,sha256=ae1QwxAnnhDkISGSWNDVNsScveoTTYDkqSRSYLWuro0,1475
@@ -184,7 +184,7 @@ onnx/backend/test/case/node/pow.py,sha256=mqZTB3aExWI77NHZMD5pa0fb0iTsSrVuVoYTZt
 onnx/backend/test/case/node/prelu.py,sha256=2mc_P13n4GYWE50wcvIhNoyIxmppmrBqq0et5O5ZEck,1160
 onnx/backend/test/case/node/qlinearconv.py,sha256=NcqkNkS24rCnTDHpLTePunkIwSdHt6mAlNLGF800oEY,2341
 onnx/backend/test/case/node/qlinearmatmul.py,sha256=liNk0Jzth3BWDJVp1PAOFWqHToB-KsvqN0CQVqwKo7U,5676
-onnx/backend/test/case/node/quantizelinear.py,sha256=c2X72l2VarjUAi-hIuJ6ZUF0aBwGmQF9kIakEnF1bvs,11284
+onnx/backend/test/case/node/quantizelinear.py,sha256=xWfKAQmAmYePK_vkbShRm7D4gJ3QzD1o4BUlv9hMPhI,11292
 onnx/backend/test/case/node/rangeop.py,sha256=p7Lz1xygHPHRUrfInf5FS2RBMhFL67kdLbyQxvxE2Ls,1491
 onnx/backend/test/case/node/reciprocal.py,sha256=34LwMciBx7lM5-KpzaDSCa5dL3VXblfLVpwoF8N1_48,782
 onnx/backend/test/case/node/reduce_log_sum.py,sha256=ons-ZqpqnpNaCkk2bUwVu-Di7i0MTeBfKL_fWMn1n8M,3159
@@ -1489,7 +1489,7 @@ onnx/backend/test/data/node/test_dequantizelinear_int16/test_data_set_0/output_0
 onnx/backend/test/data/node/test_dequantizelinear_int4/model.onnx,sha256=9LK35NYKjHLC6JmUJVZSXxI7vCSfoVOyZvVCxLwu4L8,196
 onnx/backend/test/data/node/test_dequantizelinear_int4/test_data_set_0/input_0.pb,sha256=8w_hl7JvcDysb07OiHDWHUWGW-hOCSWr8h5wywBEbS0,21
 onnx/backend/test/data/node/test_dequantizelinear_int4/test_data_set_0/input_1.pb,sha256=qN7egCoW3Tix8QKnMxT243blKL-WqkjKisULKpcdBdY,17
-onnx/backend/test/data/node/test_dequantizelinear_int4/test_data_set_0/input_2.pb,sha256=2-c2oGJ2nFi3f5gMserIvtcpTbtacRrc-RRKTXA605k,19
+onnx/backend/test/data/node/test_dequantizelinear_int4/test_data_set_0/input_2.pb,sha256=GxHG9IjbNdY0hTEZRYeNssvlZnFbX4ouLHJww6ODDzg,21
 onnx/backend/test/data/node/test_dequantizelinear_int4/test_data_set_0/output_0.pb,sha256=AB-QMRL0DZclEXLlbWVi-ti0NMUhxGgqeAKzRFgL-rM,29
 onnx/backend/test/data/node/test_dequantizelinear_uint16/model.onnx,sha256=z3gpBXrtiijpDEjhgO8EFJWJR4_EZBJ8ei1dpUPMca0,181
 onnx/backend/test/data/node/test_dequantizelinear_uint16/test_data_set_0/input_0.pb,sha256=lXtHv2NCkXFokLmUC4XcHZ0KObiQXiRreUIK-COCeLU,17
@@ -1499,7 +1499,7 @@ onnx/backend/test/data/node/test_dequantizelinear_uint16/test_data_set_0/output_
 onnx/backend/test/data/node/test_dequantizelinear_uint4/model.onnx,sha256=doOZg8lFykcn-ZiGUM7t9eNIe8AXSPsFvhE_q9pNKmw,197
 onnx/backend/test/data/node/test_dequantizelinear_uint4/test_data_set_0/input_0.pb,sha256=DujJO55o1k-7hYjfqgLjHUHvFWS9ME3xYq410pSWAPk,13
 onnx/backend/test/data/node/test_dequantizelinear_uint4/test_data_set_0/input_1.pb,sha256=qN7egCoW3Tix8QKnMxT243blKL-WqkjKisULKpcdBdY,17
-onnx/backend/test/data/node/test_dequantizelinear_uint4/test_data_set_0/input_2.pb,sha256=UrqQhZcKtsM1nfoPcUQzBqfqwka_je5kwZ0E8Gr3lJA,19
+onnx/backend/test/data/node/test_dequantizelinear_uint4/test_data_set_0/input_2.pb,sha256=Uy6DIdWiaShjYZoqvhZytFOW-nrnkq_jDxhSya5GM1Q,21
 onnx/backend/test/data/node/test_dequantizelinear_uint4/test_data_set_0/output_0.pb,sha256=xQMWX_7whFxNBSm64slp3ncuglAEdprKtaQD0zkjTqI,29
 onnx/backend/test/data/node/test_det_2d/model.onnx,sha256=OW5mSOi7fO6hao91GdGbPZF9JKegWWmf7ZkgSHmS4vM,84
 onnx/backend/test/data/node/test_det_2d/test_data_set_0/input_0.pb,sha256=0phUVbSY99aYNDvbb4I7ZwTF4_oqB7I9Teh_3LZTlfk,27
@@ -3533,12 +3533,12 @@ onnx/backend/test/data/node/test_quantizelinear_blocked_symmetric/test_data_set_
 onnx/backend/test/data/node/test_quantizelinear_e4m3fn/model.onnx,sha256=22nDQPV_pY3TRB34BlD_KeS8ow0yOzDZjTNotuWr18M,181
 onnx/backend/test/data/node/test_quantizelinear_e4m3fn/test_data_set_0/input_0.pb,sha256=RpINE2Cg2dhwMgzJm3ZxSLDmJ1q0XwI6WmIHcL_j6Yc,29
 onnx/backend/test/data/node/test_quantizelinear_e4m3fn/test_data_set_0/input_1.pb,sha256=Zv7CydImWalnvbaS5VHQ6zTXvOUCohUym_ClUIDiLJ4,17
-onnx/backend/test/data/node/test_quantizelinear_e4m3fn/test_data_set_0/input_2.pb,sha256=3qDZIcWHdcD6sR2bi0d9zxwFMbgB-8xVA8QC78gP0h4,19
+onnx/backend/test/data/node/test_quantizelinear_e4m3fn/test_data_set_0/input_2.pb,sha256=_7Vdv5427rLlWyXQDc1ya_9WSxSO8L4LZu_OHnm_FT8,21
 onnx/backend/test/data/node/test_quantizelinear_e4m3fn/test_data_set_0/output_0.pb,sha256=nNu5UvmZ8mpsh_54mZqigNgGwEN8yszynDbulB-hJ5c,14
 onnx/backend/test/data/node/test_quantizelinear_e5m2/model.onnx,sha256=L0yVbjM9lrwdvbAwh8mhf89aKtCJEyrgcxacdH5tcEM,179
 onnx/backend/test/data/node/test_quantizelinear_e5m2/test_data_set_0/input_0.pb,sha256=RpINE2Cg2dhwMgzJm3ZxSLDmJ1q0XwI6WmIHcL_j6Yc,29
 onnx/backend/test/data/node/test_quantizelinear_e5m2/test_data_set_0/input_1.pb,sha256=Zv7CydImWalnvbaS5VHQ6zTXvOUCohUym_ClUIDiLJ4,17
-onnx/backend/test/data/node/test_quantizelinear_e5m2/test_data_set_0/input_2.pb,sha256=PW0rlxt1n-xDnnHatqfnNnTTn3NsbNGhcm1Gs7psnmY,19
+onnx/backend/test/data/node/test_quantizelinear_e5m2/test_data_set_0/input_2.pb,sha256=trfI5bwzv3rDl1dqKlEM_RmOGYCac0PrHNjqYeGXxa0,21
 onnx/backend/test/data/node/test_quantizelinear_e5m2/test_data_set_0/output_0.pb,sha256=Bk-NH1ZeWwTusSN6X2cuqkFjbYJ1vDxhtJZ592E76fw,14
 onnx/backend/test/data/node/test_quantizelinear_int16/model.onnx,sha256=8OIsIPruUoe4aZC2anHuM4n85GsQrL2BQYfQbYOYZJo,176
 onnx/backend/test/data/node/test_quantizelinear_int16/test_data_set_0/input_0.pb,sha256=VmE8fR23t887aluLk_qjxKg-S07NoLxCSje5xyEL5NI,73
@@ -3548,7 +3548,7 @@ onnx/backend/test/data/node/test_quantizelinear_int16/test_data_set_0/output_0.p
 onnx/backend/test/data/node/test_quantizelinear_int4/model.onnx,sha256=_W9CJtKqLcm3zntWa30qryL1IGODqC8Lt-W-r4fMSR0,204
 onnx/backend/test/data/node/test_quantizelinear_int4/test_data_set_0/input_0.pb,sha256=Lg7BLkDJVhKNTmTszgJp0eK_i1afP0XARGAXTfNFdeQ,59
 onnx/backend/test/data/node/test_quantizelinear_int4/test_data_set_0/input_1.pb,sha256=2Pe2lcrRWP5oT1EosWg6ZOv0VcNUIPd__rMnNp0couk,27
-onnx/backend/test/data/node/test_quantizelinear_int4/test_data_set_0/input_2.pb,sha256=xOW8QI3GKHP9nY6BjWU6d8g0gyiiAHzjrI5E0nP-HJw,20
+onnx/backend/test/data/node/test_quantizelinear_int4/test_data_set_0/input_2.pb,sha256=1d3dNu_2t0cVW-a0345YfmGWH3i1K_8DOgi_jg-eIdA,22
 onnx/backend/test/data/node/test_quantizelinear_int4/test_data_set_0/output_0.pb,sha256=y06PaLypD_0xbr5-dsEIz-izN4v0u_LvdzH-IedZ_W0,26
 onnx/backend/test/data/node/test_quantizelinear_uint16/model.onnx,sha256=Bzxw9Zgnq1uix9-HBgh_FLVkNfMG8X9RfD2iiDdOxOI,177
 onnx/backend/test/data/node/test_quantizelinear_uint16/test_data_set_0/input_0.pb,sha256=HBChWZzpiiAckJ1Lx-CShRBJIZz9e-vcIp8no74kWhI,57
@@ -3558,7 +3558,7 @@ onnx/backend/test/data/node/test_quantizelinear_uint16/test_data_set_0/output_0.
 onnx/backend/test/data/node/test_quantizelinear_uint4/model.onnx,sha256=fw0fba_Z4vNck23gKcLSd08zQkpEXxDA5uZmtiTkF_s,205
 onnx/backend/test/data/node/test_quantizelinear_uint4/test_data_set_0/input_0.pb,sha256=Lg7BLkDJVhKNTmTszgJp0eK_i1afP0XARGAXTfNFdeQ,59
 onnx/backend/test/data/node/test_quantizelinear_uint4/test_data_set_0/input_1.pb,sha256=2Pe2lcrRWP5oT1EosWg6ZOv0VcNUIPd__rMnNp0couk,27
-onnx/backend/test/data/node/test_quantizelinear_uint4/test_data_set_0/input_2.pb,sha256=3msGujD62Tj7EYUPxCej7yQD4E___QrkfkZk0u0m788,20
+onnx/backend/test/data/node/test_quantizelinear_uint4/test_data_set_0/input_2.pb,sha256=iIP2U9MJwQa9ghUcuN8tpW91KGfsrp1Q8akf22lwe2M,22
 onnx/backend/test/data/node/test_quantizelinear_uint4/test_data_set_0/output_0.pb,sha256=8q530wXE297IpPg4EiJTOU3f4gDmaAuZgtD9-UT2vyM,18
 onnx/backend/test/data/node/test_range_float_type_positive_delta/model.onnx,sha256=yDJm47JALZVJ9S2sTGlShf_fJRLQNqF-BYb_fTfohlo,174
 onnx/backend/test/data/node/test_range_float_type_positive_delta/test_data_set_0/input_0.pb,sha256=PnwKkhwnmd5quiS20ZgN5aEPgWHukh4Z1L_5tQBqFMg,15
@@ -6037,7 +6037,7 @@ onnx/backend/test/loader/__init__.py,sha256=mngOe26IgFmbbCjFIhAyLMnPGhCZoaB7ke-r
 onnx/backend/test/report/__init__.py,sha256=Ua3s3YmvUusUnffIyct0GnwIqFcMP_AsV5aIe1A4rLs,1261
 onnx/backend/test/report/base.py,sha256=npe6vog194R-rbyVje3cIUerSkLoFzDaq5xexAGqbDk,119
 onnx/backend/test/report/coverage.py,sha256=uxx9g_E6TpKakqWY_pfmU0ITIFjRDpkI8lPtu4YL9Zk,11258
-onnx/backend/test/runner/__init__.py,sha256=H-fHfM4x0gD-lSzqtgJNKEFUxQHNLNtXyQSBxWRGNRo,21889
+onnx/backend/test/runner/__init__.py,sha256=xPTbaxtrn_U6yroPfh2YX8wSqhBE-_ownwVka18FMgU,21850
 onnx/backend/test/runner/item.py,sha256=PEJjl6K3Z-bga8IMHN3alKcweygjAMzZhSa1ChKF6C8,429
 onnx/bin/__init__.py,sha256=HiuD-U6YHJwWikkemKJqBq-35U8KJ9LDdAwdisi7OlQ,85
 onnx/bin/checker.py,sha256=h4tAK3SaViHUdt8nBpookLAqVNSgIHhn2jL_GeHM7m0,684
@@ -6062,7 +6062,7 @@ onnx/common/proto_util.h,sha256=U-KYW5fBs1MqmYWmtMONpw8a75SRMD7D32a8dZ4LlN0,1473
 onnx/common/status.cc,sha256=nMqcYhcpXzyX-Ln7kZPC2EwOMbV5ssNuF6z05N6ojrw,1981
 onnx/common/status.h,sha256=7x8_ZLcNIZVL7HF1ArFp03KU2PUPT6eDZRhEedelnFc,2008
 onnx/common/tensor.h,sha256=tCw06bToUEkXWStd7h5n07ikpmNFadfefi0uDIW5jrw,7699
-onnx/common/version.h,sha256=886IcNQk5AeDaj9tUJ6xaoOv5UQB9vbhovx0faqjalw,308
+onnx/common/version.h,sha256=aMrqfR_s_hbgqoqwXdZGkD3XeZSVBr9W7H8B4cQMpPs,308
 onnx/common/visitor.h,sha256=Fn-B-0xAy0r3TEo0jh4yYrFJkBV7xZxrP94VX5AjzFI,3215
 onnx/defs/__init__.py,sha256=PZ01rEheu0-GhBVbHrehi9fMoS3e9Vx4XBPGXD_DqHo,4284
 onnx/defs/attr_proto_util.cc,sha256=qAGbnnDY7MvKN7nKIYl6K5f7irNeNnNJ61J67OP_TJk,3658
@@ -6102,7 +6102,7 @@ onnx/defs/image/defs.cc,sha256=TwqyFK_GbtLqanIo4ekYw9g4jp-vIlVBAe-1KWscbWA,2834
 onnx/defs/logical/defs.cc,sha256=Tbj__KPHpdhBAk2cPAhPHdJtPrWvlGkCifJtgnGGmFc,12166
 onnx/defs/logical/old.cc,sha256=3mcunnOuj4d2RAG-bjRwqJU8Eeg1qGE9OFLFOeicHUY,10334
 onnx/defs/math/defs.cc,sha256=0oWGGDB4hVOQd6XNZnKZ5_RaUH_jWvbYUfsAuWTXYk0,145250
-onnx/defs/math/old.cc,sha256=pnVHt23OuOyYjiRwCVmLBc4eiDHvHxgs6c0rLbE8ucM,133720
+onnx/defs/math/old.cc,sha256=zzg1j-uB0Ifhx9r-kf-i5NArZxhbq6zgj0E-6pkLAiw,133878
 onnx/defs/math/utils.cc,sha256=J86Vx2b1T3zyrwxrEV2sB4vNzN9yg9i-w6cAOGgFJbk,4981
 onnx/defs/math/utils.h,sha256=rL7InDv3ZROqK2tsINn70J92gsmgYdRLiYMsKEviDTg,1347
 onnx/defs/nn/defs.cc,sha256=6MgRpvf0vjTpVdX6x2h0PzP0c17-QVFuKHAaN8zE0fw,128345
@@ -6111,8 +6111,8 @@ onnx/defs/object_detection/defs.cc,sha256=kke0G3Bo0WXsL1jJ9G3eauu_il6NTGZSTYBCr7
 onnx/defs/object_detection/old.cc,sha256=Kfck4FSzoyv90IdefqN028RxGXj5syrnMHtX05vFOWI,8343
 onnx/defs/optional/defs.cc,sha256=9wPzDUjtnMQVWmR_2gaXw0pNUUxI1UyDr0rlWW1fU20,6670
 onnx/defs/optional/old.cc,sha256=gEVbnZiknNPPoHk5pJYfUcGQaLgxgjXaXMR2LQ6rbp4,3499
-onnx/defs/quantization/defs.cc,sha256=6DQxDPmTLWf9ReM-ts9KFVkcTirxSurrs_OgD4P4EPs,13702
-onnx/defs/quantization/old.cc,sha256=ZiIPGiiZs0x4qxRlfEDB6ZBqql6GjBDA04NpZhSx7GE,15630
+onnx/defs/quantization/defs.cc,sha256=az2b0vYdWyROAYrTfe8N8XAa61vx5WX242fLKa1CAkQ,13777
+onnx/defs/quantization/old.cc,sha256=n3ZFYTTIc6c6j9NTITKyXsFQpus6_obhJEq4jlxS1Nc,15703
 onnx/defs/reduction/defs.cc,sha256=rHvP9SDvpIKSVD6MEm1rifZPm5Gtmm8la5_rWlanuiY,6316
 onnx/defs/reduction/old.cc,sha256=cHIoo2USwB9GY7R0ANTR4m47kGZko6laiSNsURHoGVQ,19434
 onnx/defs/reduction/utils.cc,sha256=Ml0jJiMwSq2pnKgHEWyfnOfiX2cqsCyL6pev2D_VeHk,6375
@@ -6121,7 +6121,7 @@ onnx/defs/rnn/defs.cc,sha256=oHWuTnER8fXzvcmd1zf61oXDIZaNo7je6wy_sqfnOFI,20092
 onnx/defs/rnn/old.cc,sha256=HnFsXxbQIzmRR965HRB2X5vQVjpOWHNEPkpmcKkJiY0,40210
 onnx/defs/sequence/defs.cc,sha256=0CGv3Oxsg9jKoXteXcCzRQ3O7_U_BkbpK9win7gSf1c,34822
 onnx/defs/tensor/defs.cc,sha256=T1SMqOFZIrhTI_EziiBD0zcQck_1gdcuw5X4wy9BqcU,166662
-onnx/defs/tensor/old.cc,sha256=oIpbDbd3ObNXMrWibwWVAz149G6h27Rep86Oo0WxT4U,271738
+onnx/defs/tensor/old.cc,sha256=vxBKu570Tsi-aUsBeSsBBv5ZscrDE-dO6s51iEWvvcE,271732
 onnx/defs/tensor/utils.cc,sha256=EYWBGwdBFu2mPG6nWnounD7fkj6qrRPX_xiW9eQuLYg,19317
 onnx/defs/tensor/utils.h,sha256=NW6Bf_osOOPr7ibHPXYP7aHlU5zLn5OVzvmySHd3m4I,1855
 onnx/defs/text/defs.cc,sha256=xle6eQMSIGgADF0LyWnbYAa6GXDWA4uQtopu7iuLq9o,10575
@@ -6373,7 +6373,7 @@ onnx/reference/ops/experimental/op_im2col.py,sha256=YLYL6JVcCBUdvVzq4eGrg-Q9Pvm2
 onnx/reference/ops_optimized/__init__.py,sha256=T1nSBzjXBKSnMJzKdQxw39bYBcLj7lbO0uAx63DQkPc,274
 onnx/reference/ops_optimized/op_conv_optimized.py,sha256=y0L2AfrN9yti3gRtK8Z2rAIRN7hmivQHYDZUr2ZvO4w,6608
 onnx/shape_inference/attribute_binder.h,sha256=ICoFJLBC8GU1n8vEbUD8BW4p0-cuaBbRhNo7dKQ7xgY,2446
-onnx/shape_inference/implementation.cc,sha256=_BtfAJtoOFybMskd5Kc1noe8sleRAZmjfaA-_XcdLk0,43711
+onnx/shape_inference/implementation.cc,sha256=o2yo5deO3LkxzCYzynxKOFZaHMLC5SWmwismDE3LFdQ,43668
 onnx/shape_inference/implementation.h,sha256=zDEvkxX53zf1HgsymUsCfJMlxciW1yw0XzRF7_Svk40,19854
 onnx/test/__init__.pyi,sha256=VW4Y59avFWUotfJT9rPS5AachoNP4rSbu2Z43Ln5Wzw,254
 onnx/test/basic_test.py,sha256=ilA7YFfWJjR-8gRpzhfiMWXzcuytf2dMk3Ipg-hJ0uI,9831
@@ -6427,7 +6427,7 @@ onnx/test/version_converter/automatic_conversion_test_base.py,sha256=Kc2sTGYZY1E
 onnx/test/version_converter/automatic_downgrade_test.py,sha256=0QSOEYy416rXaohwwroTbhKANXTyNuSjs4gd2mxN1Zs,3372
 onnx/test/version_converter/automatic_upgrade_test.py,sha256=9-0xuQdYydfFDRFCK3SJZlh4HUdQad0aKa79bIJWbpk,56018
 onnx/tools/__init__.py,sha256=HiuD-U6YHJwWikkemKJqBq-35U8KJ9LDdAwdisi7OlQ,85
-onnx/tools/net_drawer.py,sha256=D1CjUu2SqPr9M5YuFWRknQGczHcXY6wJF5B1TP_72G8,5055
+onnx/tools/net_drawer.py,sha256=vAEERPpHmHvJpb-QS88JTa9UgLPbk1vv__fGCdIHs78,5055
 onnx/tools/replace_constants.py,sha256=-CKmbtN4oqaOiPBKQoiilFMBlAPyhRGyCK0ZrcdH2FQ,15272
 onnx/tools/update_model_dims.py,sha256=_18ze7JC_En-IC6SX3zHNhIFABaJa7vc5wsAEc9ygdg,3528
 onnx/version_converter/BaseConverter.h,sha256=VeziFFvwvPKyaCwuTtb6gtN3kAzFXOVxHiFsoBUBC5c,3853
@@ -6476,9 +6476,9 @@ onnx/version_converter/adapters/upsample_6_7.h,sha256=vHwjsHvCw3d5d4rE1UZBSI_EyG
 onnx/version_converter/adapters/upsample_8_9.h,sha256=a3U4oqwTt8gJXR2bf1d0LgOjjOg0JobuinpE-QBC4Fg,1334
 onnx/version_converter/adapters/upsample_9_10.h,sha256=J5xRPJQ6mTpLCV1yp6LaEoTaXghP9FhTFS-IAxRi5rs,1112
 onnx/version_converter/adapters/upsample_9_8.h,sha256=miIzjt52ofR78p3TAi5V9mQWUG8EZy8ExKsilj5SSvY,2598
-onnx-1.16.0.dist-info/LICENSE,sha256=Pd-b5cKP4n2tFDpdx27qJSIq0d1ok0oEcGTlbtL6QMU,11560
-onnx-1.16.0.dist-info/METADATA,sha256=_t3j5FnAt2iP3zQt3PJAPE3JjWZ7xkQxMtarnORIJUc,16842
-onnx-1.16.0.dist-info/WHEEL,sha256=57hb2VMKfzdcZEFKIri3BxIFhvran9ahu4uVnDJqFIU,96
-onnx-1.16.0.dist-info/entry_points.txt,sha256=kI2A5Kl3HXkb7WkSIlcynOx46XYhwXcFVJlmwL58mPk,156
-onnx-1.16.0.dist-info/top_level.txt,sha256=fok5iu7rojicZZye7lCMdLme_jvte9jjDqYyhL0Kg6E,5
-onnx-1.16.0.dist-info/RECORD,,
+onnx-1.16.2.dist-info/LICENSE,sha256=Pd-b5cKP4n2tFDpdx27qJSIq0d1ok0oEcGTlbtL6QMU,11560
+onnx-1.16.2.dist-info/METADATA,sha256=CZEVY9JSRVgMevXirUNIcT4fetxXnNPiH7hesgDEjd4,16842
+onnx-1.16.2.dist-info/WHEEL,sha256=3szW57pNWqFVRic6Ma4o9j5UYGJmr9Fs-0ZX6rmK_Y4,95
+onnx-1.16.2.dist-info/entry_points.txt,sha256=kI2A5Kl3HXkb7WkSIlcynOx46XYhwXcFVJlmwL58mPk,156
+onnx-1.16.2.dist-info/top_level.txt,sha256=fok5iu7rojicZZye7lCMdLme_jvte9jjDqYyhL0Kg6E,5
+onnx-1.16.2.dist-info/RECORD,,

{onnx-1.16.0.dist-info → onnx-1.16.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (72.1.0)
 Root-Is-Purelib: false
 Tag: cp38-cp38-win32