Csongor Szabo comments

Repositories
Issues
Comments

Results 2 comments of


                                            Csongor Szabo

PyTorch to CoreML model conversion does not handle the torch tensor narrow() operation.

Same issue here with dynamic input shape :grimacing:

PyTorch to CoreML model conversion does not handle the torch tensor narrow() operation.

This worked for me with dynamic shape inputs: ```python @register_torch_op(override=True) def narrow(context, node): data, dim, start, length = _get_inputs(context, node, expected=4) if any_symbolic(data.shape): data_shape = mb.shape(x=data).sym_val else: data_shape = mb.shape(x=data).val...