[ONNX] Error when using nnvm.compiler.build(sym, target, shape_dict, params=params)

Elizaaaaa · October 10, 2018, 10:25pm

Hi,

dmlc/nnvm/blob/master/tutorials/from_onnx.py

"""
Compile ONNX Models
===================
**Author**: `Joshua Z. Zhang <https://zhreshold.github.io/>`_

This article is an introductory tutorial to deploy ONNX models with NNVM.

For us to begin with, onnx module is required to be installed.

A quick solution is to install protobuf compiler, and
```bash
pip install onnx --user
```
or please refer to offical site.
https://github.com/onnx/onnx
"""
import nnvm
import tvm
import onnx
import numpy as np

This file has been truncated. show original

I’m following this tutorial of loading and compiling the onnx files, and get the error message at graph, lib, params = nnvm.compiler.build(sym, target, shape_dict, params=params)
The erros is:
_, CI, IH, IW = [x.value for x in data.shape]
ValueError: not enough values to unpack (expected 4, got 0)

The whole error message is:
Downloading from url https://gist.github.com/zhreshold/bcda4716699ac97ea44f791c24310193/raw/93672b029103648953c4e5ad3ac3aadf346a4cdc/super_resolution_0.2.onnx to super_resolution.onnx
File cat.png existed, skip.
Traceback (most recent call last):
File “test.py”, line 54, in
graph, lib, params = nnvm.compiler.build(sym, target, shape_dict, params=params)
File “/home/ubuntu/.local/lib/python3.5/site-packages/nnvm-0.8.0-py3.5.egg/nnvm/compiler/build_module.py”, line 305, in build
graph = graph.apply(“GraphCompile”)
File “/home/ubuntu/.local/lib/python3.5/site-packages/nnvm-0.8.0-py3.5.egg/nnvm/graph.py”, line 234, in apply
check_call(_LIB.NNGraphApplyPasses(self.handle, npass, cpass, ctypes.byref(ghandle)))
File “/home/ubuntu/.local/lib/python3.5/site-packages/nnvm-0.8.0-py3.5.egg/nnvm/_base.py”, line 75, in check_call
raise NNVMError(py_str(_LIB.NNGetLastError()))
nnvm._base.NNVMError: TVMCall CFunc Error:
Traceback (most recent call last):
File “tvm/_ffi/_cython/./function.pxi”, line 38, in tvm._ffi._cy3.core.tvm_callback
File “/home/ubuntu/.local/lib/python3.5/site-packages/nnvm-0.8.0-py3.5.egg/nnvm/top/nn.py”, line 106, in compute_conv2d
inputs[0], kernel, strides, padding, layout, out_dtype=out_dtype)
File “”, line 2, in conv2d
File “/home/ubuntu/.local/lib/python3.5/site-packages/tvm-0.5.dev0-py3.5-linux-x86_64.egg/tvm/target.py”, line 356, in dispatch_func
return dispatch_dict[k](*args, **kwargs)
File “/home/ubuntu/.local/lib/python3.5/site-packages/topi-0.5.dev0-py3.5.egg/topi/x86/conv2d.py”, line 119, in _declaration_conv
wkl = _get_workload(data, kernel, stride, padding, out_dtype)
File “/home/ubuntu/.local/lib/python3.5/site-packages/topi-0.5.dev0-py3.5.egg/topi/nn/conv2d.py”, line 75, in _get_workload
_, CI, IH, IW = [x.value for x in data.shape]
ValueError: not enough values to unpack (expected 4, got 0)

Anyone knows what’s happening? Thanks!