tkat0 / chainer-nnvm-example

Chainer-NNVM-Example

Chainer Advent Calendar 2017 - Qiitaの2017/12/19の記事です。

Chainerで学習したモデルをONNX-ChainerとNNVM/TVMを使ってAndroidへデプロイする

Usage

Chainerの学習済みモデルYOLOv2_tinyをONNXに変換

$ cd models/YOLOv2_tiny/
$ python export.py

macBookのCPU,GPUにデプロイする

$ python run_pc.py

AndroidのCPU,GPUにデプロイする

$ python -m tvm.exec.rpc_proxy 

Android側でRPCプロキシサーバーに接続後、以下のコマンドを実行

$ python run_mobile.py

chainer-nnvm-example's Issues

ValueError: not enough values to unpack (expected 4, got 0)

はじめまして
ディープラーニングを実務で活用することを考えるとエッジでモデルを使うことが重要と感じ、スマホで動かす事にトライしております
数少ないネット上の情報ですので、非常に参考にさせて頂いております

質問です
環境構築後、run_pc.pyを実行するすると以下のエラーが出てしまいました
原因で気付くことがございましたら教えて頂けると助かります

〜〜〜〜〜〜
$ python run_pc.py
/anaconda3/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
WARNING:root:Attribute momentum is disabled in nnvm.sym.batch_norm
WARNING:root:Attribute momentum is disabled in nnvm.sym.batch_norm
WARNING:root:Attribute momentum is disabled in nnvm.sym.batch_norm
WARNING:root:Attribute momentum is disabled in nnvm.sym.batch_norm
WARNING:root:Attribute momentum is disabled in nnvm.sym.batch_norm
WARNING:root:Attribute momentum is disabled in nnvm.sym.batch_norm
WARNING:root:Attribute momentum is disabled in nnvm.sym.batch_norm
WARNING:root:Attribute momentum is disabled in nnvm.sym.batch_norm
Traceback (most recent call last):
File "run_pc.py", line 46, in
graph, lib, params = nnvm.compiler.build(sym, target, {input_name: data_shape}, params=params)
File "/anaconda3/lib/python3.6/site-packages/nnvm-0.8.0-py3.6.egg/nnvm/compiler/build_module.py", line 272, in build
graph = optimize(graph, shape, dtype, layout)
File "/anaconda3/lib/python3.6/site-packages/nnvm-0.8.0-py3.6.egg/nnvm/compiler/build_module.py", line 169, in optimize
graph = graph.apply(["InferShape", "InferType", "AlterOpLayout"])
File "/anaconda3/lib/python3.6/site-packages/nnvm-0.8.0-py3.6.egg/nnvm/graph.py", line 234, in apply
check_call(_LIB.NNGraphApplyPasses(self.handle, npass, cpass, ctypes.byref(ghandle)))
File "/anaconda3/lib/python3.6/site-packages/nnvm-0.8.0-py3.6.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 "/anaconda3/lib/python3.6/site-packages/nnvm-0.8.0-py3.6.egg/nnvm/top/nn.py", line 125, in alter_conv2d_layout
return topi.nn.conv2d_alter_layout(attrs, inputs, tinfos)
File "", line 2, in conv2d_alter_layout
File "/anaconda3/lib/python3.6/site-packages/tvm-0.2.0-py3.6-macosx-10.7-x86_64.egg/tvm/target.py", line 345, in dispatch_func
return dispatch_dict[k](*args, **kwargs)
File "/anaconda3/lib/python3.6/site-packages/topi-0.2.0-py3.6.egg/topi/x86/conv2d.py", line 141, in _alter_conv2d_layout
wkl = _get_workload(data, kernel, stride, padding, data.dtype)
File "/anaconda3/lib/python3.6/site-packages/topi-0.2.0-py3.6.egg/topi/nn/conv2d.py", line 134, in _get_workload
_, CI, IH, IW = [x.value for x in data.shape]
ValueError: not enough values to unpack (expected 4, got 0)