[ONNX] Switched to ONNX 1.17.0 (openvinotoolkit#26916)

### Details:
 - Switched to ONNX 1.17.0

### Tickets:
 - N/A

Author: gkrivor

conan.lock

@@ -10,7 +10,7 @@
         "opencl-icd-loader/2023.04.17#5f73dd9f0c023d416a7f162e320b9c77%1692732261.088",
         "opencl-headers/2023.04.17#3d98f2d12a67c2400de6f11d5335b5a6%1683936272.16",
         "opencl-clhpp-headers/2023.04.17#7c62fcc7ac2559d4839150d2ebaac5c8%1685450803.672",
-        "onnx/1.16.2#b5e8d35b10d454b26751762922465eb8%1712404811.278",
+        "onnx/1.17.0#c79fdfca3ae149874153de15a20f4598%1727864447.241",
         "onetbb/2021.10.0#cbb2fc43088070b48f6e4339bc8fa0e1%1693812561.235",
         "ittapi/3.24.0#9246125f13e7686dee2b0c992b71db94%1682969872.743",
         "hwloc/2.9.2#1c63e2eccac57048ae226e6c946ebf0e%1688677682.002",
@@ -33,4 +33,4 @@
     ],
     "python_requires": [],
     "config_requires": []
-}
+}

conanfile.txt

@@ -7,7 +7,7 @@ opencl-icd-loader/[>=2023.04.17]
 rapidjson/[>=1.1.0]
 xbyak/[>=6.62]
 snappy/[>=1.1.7]
-onnx/1.16.2
+onnx/1.17.0
 pybind11/[>=2.12.0]
 flatbuffers/[>=22.9.24]
 

src/bindings/python/constraints.txt

@@ -23,4 +23,4 @@ paddlepaddle==2.6.0
 tensorflow>=1.15.5,<2.18.0
 six~=1.16.0
 protobuf>=3.18.1,<4.0.0
-onnx==1.16.0
+onnx==1.17.0

src/frontends/onnx/tests/__init__.py

@@ -182,3 +182,6 @@ def xfail_test(reason="Mark the test as expected to fail", strict=True):
 xfail_issue_139936 = xfail_test(reason = "MaxPool accuracy fails")
 xfail_issue_139937 = xfail_test(reason = "GroupNorm, QLinearMatMul, DequantizeLinear translation failed")
 xfail_issue_139938 = xfail_test(reason = "QLinearMatMul accuracy fails")
+
+# ONNX 1.17
+skip_issue_119896 = pytest.mark.skip(reason="Unsupported element type: FLOAT8")

src/frontends/onnx/tests/ci_utils/onnxruntime/version

@@ -1 +1 @@
-rel-1.18.1
+rel-1.19.2

src/frontends/onnx/tests/tests_python/test_backend.py

@@ -57,6 +57,7 @@
     xfail_issue_113506,
     skip_dynamic_model,
     xfail_issue_119896,
+    skip_issue_119896,
     xfail_issue_119900,
     xfail_issue_119903,
     xfail_issue_119906,
@@ -246,7 +247,11 @@ def expect_fail(test_case_path, xfail):  # type: (str) -> None
         "OnnxBackendNodeModelTest.test_maxunpool_export_with_output_shape_cpu",
         "OnnxBackendNodeModelTest.test_maxunpool_export_without_output_shape_cpu",
     ),
-    (xfail_issue_38724, "OnnxBackendNodeModelTest.test_resize_tf_crop_and_resize_cpu"),
+    (
+        xfail_issue_38724,
+        "OnnxBackendNodeModelTest.test_resize_tf_crop_and_resize_cpu",
+        "OnnxBackendNodeModelTest.test_resize_tf_crop_and_resize_extrapolation_value_cpu"
+    ),
     (
         xfail_issue_33606,
         "OnnxBackendNodeModelTest.test_det_2d_cpu",
@@ -454,6 +459,7 @@ def expect_fail(test_case_path, xfail):  # type: (str) -> None
         "OnnxBackendNodeModelTest.test_resize_upsample_sizes_nearest_axes_2_3_cpu",
         "OnnxBackendNodeModelTest.test_resize_upsample_sizes_nearest_axes_3_2_cpu",
         "OnnxBackendNodeModelTest.test_resize_upsample_sizes_nearest_not_larger_cpu",
+        "OnnxBackendNodeModelTest.test_resize_upsample_sizes_nearest_not_smaller_cpu",
     ),
     (
         xfail_issue_99970,
@@ -520,6 +526,13 @@ def expect_fail(test_case_path, xfail):  # type: (str) -> None
         "OnnxBackendNodeModelTest.test_dequantizelinear_e4m3fn_float16_cpu",
         "OnnxBackendNodeModelTest.test_dequantizelinear_e4m3fn_zero_point_cpu",
     ),
+    (
+        skip_issue_119896,
+        "OnnxBackendNodeModelTest.test_cast_no_saturate_FLOAT16_to_FLOAT8E4M3FN_cpu",
+        "OnnxBackendNodeModelTest.test_cast_no_saturate_FLOAT16_to_FLOAT8E5M2_cpu",
+        "OnnxBackendNodeModelTest.test_cast_no_saturate_FLOAT_to_FLOAT8E4M3FN_cpu",
+        "OnnxBackendNodeModelTest.test_cast_no_saturate_FLOAT_to_FLOAT8E5M2_cpu",
+    ),
     (
         xfail_issue_119900,
         "OnnxBackendNodeModelTest.test_resize_downsample_scales_linear_half_pixel_symmetric_cpu",
@@ -626,6 +639,7 @@ def expect_fail(test_case_path, xfail):  # type: (str) -> None
         skip_misalignment,
         "OnnxBackendNodeModelTest.test_gelu_default_2_expanded_cpu",
         "OnnxBackendNodeModelTest.test_reduce_log_sum_exp_empty_set_expanded_cpu",
+        "OnnxBackendNodeModelTest.test_reduce_max_empty_set_cpu",
         "OnnxBackendNodeModelTest.test_group_normalization_epsilon_cpu",
         "OnnxBackendNodeModelTest.test_group_normalization_example_cpu",
         "OnnxBackendNodeModelTest.test_qlinearmatmul_3D_int8_float16_cpu",

thirdparty/onnx/onnx

@@ -3,7 +3,7 @@
 # files because the version differs between them:
 # tensorflow, numpy
 h5py>=3.1.0,<3.11.0
-onnx>=1.8.1,<=1.16.0
+onnx>=1.8.1,<=1.17.0
 networkx<=3.1.0
 pytest>=5.0,<8.4
 protobuf>=3.18.1,<4.0.0