We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Describe the bug
Ort uses 0-based index for axes in Squeeze but looks like ONNX says it should be 1-based. https://github.com/onnx/onnx/blob/master/docs/Operators.md#Squeeze
axes : list of ints List of positive integers, indicate the dimensions to squeeze.
System information
The text was updated successfully, but these errors were encountered:
it's a technical error in the description then. it should be 0-based index for axes. The example in the spec https://github.com/onnx/onnx/blob/master/docs/Operators.md#examples-97 even uses a 0 axis
node = onnx.helper.make_node( 'Squeeze', inputs=['x'], outputs=['y'], axes=[0], ) x = np.random.randn(1, 3, 4, 5).astype(np.float32) y = np.squeeze(x, axis=0)
expect(node, inputs=[x], outputs=[y], name='test_squeeze')
Given onnx is an interchange format between frameworks and caffe2, tf, pytorch etc. use 0-based index, it wouldn't make sense for onnx to use 1-based.
Sorry, something went wrong.
Forward to ONNX repo: onnx/onnx#1755
No branches or pull requests
Describe the bug
Ort uses 0-based index for axes in Squeeze but looks like ONNX says it should be 1-based.
https://github.com/onnx/onnx/blob/master/docs/Operators.md#Squeeze
System information
The text was updated successfully, but these errors were encountered: