search

AxisCommunications / onnx-to-keras

Convert onnx models exported from pytorch to tensorflow keras models with focus on performace and highleve compatibility.
MIT License
25 stars 13 forks source link

Support for op_softmax #4

Closed aitikgupta closed 4 years ago

aitikgupta commented 4 years ago

Softmax is a very common layer, could you add the implementation for it? Thanks.

Here's the traceback if you're interested.

 File "onnx2keras.py", line 459, in main
    model = onnx2keras(onnx.load(infile))
  File "onnx2keras.py", line 447, in onnx2keras
    output_tensors = ops.make_op(node.op_type, inputs, attrs)
  File "onnx2keras.py", line 20, in make_op
    return getattr(self, 'op_' + op_type.lower())(*inputs, **attrs)
AttributeError: 'TfKerasOperations' object has no attribute 'op_softmax'
aitikgupta commented 4 years ago

Nevermind, I created my own op_softmax function, closing this now.

hakanardo commented 4 years ago

Nice. A pullrequest would be welcome :)

On Mon, May 18, 2020 at 1:08 AM Aitik Gupta notifications@github.com wrote:

Nevermind, I created my own op_softmax function, closing this now.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/AxisCommunications/onnx-to-keras/issues/4#issuecomment-629875376, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA2GZ4PLHRMU5RHNQTJ7ZJTRSBU7NANCNFSM4NDSYEOA .

-- Håkan Ardö