Update constant-folding of Gather operator so it also includes cases where rank of indices input is 0.
Currently it only support cases where rank of indices is 1.

Fix bug in unfold symbolic

…orch#50512)

previous error message looks like this 
```
RuntimeError: Unexpected node type: onnx::Gather
```
now
```
RuntimeError: Expected node type 'onnx::Constant' for argument 'groups' of node 'conv1d', got 'onnx::Gather'.
```

Repro example:
```python
    @torch.jit.script
    def conv(x, w):
        return F.conv1d(x, w, groups=x.shape[0])

    class Net(nn.Module):
        def forward(self, x, w):
            return conv(x, w)

    model = Net()

    x = torch.randn(8, 8, 512)
    w = torch.randn(8, 1, 3)
    torch.onnx.export(model,
                        (x, w),
                        "file.onnx",
                        opset_version=12)
```

…ch into neraoof/fixSetAttribute

Fix get/set attributes when getting/setting a model parameter.
This PR also fixes inplace ops in If blocks.

* enable remaining test in opset13

* add comments for error version test info

* fix comments:opset12 unbind problem

* add ignore[no-redef]

* fix format

Co-authored-by: hwangdeyu <deyhuang@qq.com>

Support for yolov5 compound-scaled object detection models export.

…pytorch#50123)

Previous insertBefore approach might end-up inserting clone node in inner sub-blocks, while then the node being used later at other outside call sites.

* Add loop & if node to the list of nodes that could produce sequence type output.
* Switch from `[]` to `at()` to avoid segfault of out of range access.

…d for ONNX export. (pytorch#51387)

* Enable Constant Folding for ONNX Opset 13

* fix CI clang-diagnostic

* fix integers type

* fix comments:sort axes and support negative number

* update squeeze op constant folding

* fix format warning

* fix clang-format issue

Co-authored-by: hwangdeyu <deyhuang@qq.com>

…t operator. (pytorch#51415)

* def unsafe_chunk() support and test in ops13.

* Use _unsqueeze_helper insteadof Unsqueeze operator

* Cast the splits into long.

* Change the test to a fixed dimension.

* Update test_pytorch_onnx_onnxruntime.py

* Disable test_loop_with_list for opset 13.

Co-authored-by: Negin Raoof <neginmr@utexas.edu>

* Support aten::Delete
* Refactor prepare_inplace_ops_for_onnx into one pass.

Fix bug in scatter_add symbolic

…nary inplace ops (pytorch#51318)

Modifications in remove_inplace_ops_for_onnx pass and remove_inplace_ops pass to better handle binary inplace ops

* Handles special case of binary inplace ops, where the first input node has a lower type precedence than the second input node. 
* When the inplace node is converted to a regular op, this information is lost and the resulting type is based on type precedence, just like regular ops. To avoid this loss of information, we add a cast node before the input node with the higher data type precedence, so that both the input types are the same.

…eraoof/fixSetAttribute2

# Conflicts:
#	scripts/onnx/test.sh
#	test/onnx/test_pytorch_onnx_onnxruntime.py
#	torch/csrc/jit/passes/onnx/remove_inplace_ops_for_onnx.cpp