BMZ inference tool, inconsistency with input data

[kostrykin]

For this input image: https://github.com/bgruening/galaxytools/blob/cefdfdc13838de5108e13f54ecd69babb44009a1/tools/bioimaging/test-data/input_nucleisegboundarymodel.png

The bioimaging tool produces this output:

There seems to be an inconsistency with the rows/columns, maybe they are swapped unintentionally either for the input or for the output. It could also be a rotation in conjunction with mirroring, but I think this is rather unlikely.

There also is a test for this,

galaxytools/tools/bioimaging/bioimage_inference.xml

Lines 68 to 82 in cefdfdc

	<param name="input_imaging_model" value="input_imaging_model.zip" location="https://zenodo.org/api/records/6647674/files/weights-torchscript.pt/content"/>
	<param name="input_image_file" value="input_nucleisegboundarymodel.png"/>
	<param name="input_image_input_size" value="256,256,1,1"/>
	<param name="input_image_input_axes" value="bcyx"/>
	<output name="output_predicted_image" ftype="tif">
	<assert_contents>
	<has_size size="524846" delta="110" />
	</assert_contents>
	</output>
	<output name="output_predicted_image_matrix" ftype="npy">
	<assert_contents>
	<has_size size="524416" delta="110" />
	</assert_contents>
	</output>
	</test>

but the output is not really verified here.

@anuprulez Can you maybe help with this?

[anuprulez]

@kostrykin sure, will have a look at it soon