For some Const node: "initializer shape is inconsistent" about tensorflow-onnx HOT 7 CLOSED

I remember that there was some issue with caffe2 and winml that some tensor ops don't work if you use a scalar but they are perfectly happy if you pass [scalar] and I think we intentionally made a change to use [scalar] for that reason. Let me look at this again, it is some time ago and I don't know if caffe2 still needs this. We could maybe ifdef this for the caffe2 runtime ... this target thing was meant to allow runtime specific workarounds.

if ctx.is_target(TARGET_CAFFE2):

from tensorflow-onnx.

Thanks @guschmue for the reply, while this issue should be in tf-graph->onnx conversion stage, not yet hit the caffe2 runtime.

from tensorflow-onnx.

Do you mean let me comment the https://github.com/onnx/tensorflow-onnx/blob/master/tf2onnx/graph.py#L421 with check "if ctx.is_target(TARGET_CAFFE2):"?

from tensorflow-onnx.

void my comment ,,, not the same. I'll look at it today.

from tensorflow-onnx.

I just comment the L421 check to unblock the model conversion, so maybe we can consider to loose the shape==dim check for some special case. anyway, we can discuss once you get better context later. :)

from tensorflow-onnx.

sure

from tensorflow-onnx.

not having this issue recently, close this unless we got this failure again.

from tensorflow-onnx.