apache / mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
https://mxnet.apache.org
Apache License 2.0
20.78k stars 6.79k forks source link

Failed to load Arcface from ONNX model zoo #19066

Open bfgoldstein opened 4 years ago

bfgoldstein commented 4 years ago

Description

I was trying to load the Arcface model downloaded from ONNX model zoo, but a "NotImplementedError: Operator Sub not implemented." exception was raised.

It seems that this model had some problems before, but it was fixed here. However, there is a commit made on June 10 that removes support for some ONNX Operators, like add, subtract, multiply, and divide.

Error Message

[12:03:05] /home/bruno/mxnet/mxnet/src/storage/storage.cc:198: Using Pooled (Naive) StorageManager for CPU
Traceback (most recent call last):
  File "error_reproduce.py", line 5, in <module>
    sym, arg_params, aux_params = import_model(model)
  File "/home/bruno/mxnet/mxnet/python/mxnet/contrib/onnx/onnx2mx/import_model.py", line 59, in import_model
    sym, arg_params, aux_params = graph.from_onnx(model_proto.graph)
  File "/home/bruno/mxnet/mxnet/python/mxnet/contrib/onnx/onnx2mx/import_onnx.py", line 115, in from_onnx
    mxnet_sym = self._convert_operator(node_name, op_name, onnx_attr, inputs)
  File "/home/bruno/mxnet/mxnet/python/mxnet/contrib/onnx/onnx2mx/import_onnx.py", line 63, in _convert_operator
    raise NotImplementedError("Operator {} not implemented.".format(op_name))
NotImplementedError: Operator Sub not implemented.

To Reproduce

Minimal python script:

import sys
from mxnet.contrib.onnx.onnx2mx.import_model import import_model

model = sys.argv[1]
sym, arg_params, aux_params = import_model(model)

Environment

github-actions[bot] commented 4 years ago

Welcome to Apache MXNet (incubating)! We are on a mission to democratize AI, and we are glad that you are contributing to it by opening this issue. Please make sure to include all the relevant context, and one of the @apache/mxnet-committers will be here shortly. If you are interested in contributing to our project, let us know! Also, be sure to check out our guide on contributing to MXNet and our development guides wiki.