树莓派运行根据自己的数据集训练好的ssd_512_resnet50_v1_voc模型报错

以下的讨论是基于:
MXNet版本: 1.5.0
python:3.7
opencv 3.4.18
操作系统: raspbian

在树莓派4上执行到以下语句报错,在ubuntu16.04下则可以正常运行。
net = gluon.SymbolBlock.imports(symbol_file=modefile, input_names=[‘data’], param_file=parafile)
报错信息如下:
Traceback (most recent call last):
File “demofile_ssd.py”, line 41, in
gDet = Detector()
File “/home/pi/Downloads/detector_ssd_rasp.py”, line 9060, in init
self.net = gluon.SymbolBlock.imports(symbol_file=modefile, input_names=[‘data’], param_file=parafile)
File “/usr/local/lib/python3.7/dist-packages/mxnet/gluon/block.py”, line 1018, in imports
sym = symbol.load(symbol_file)
File “/usr/local/lib/python3.7/dist-packages/mxnet/symbol/symbol.py”, line 2620, in load
check_call(_LIB.MXSymbolCreateFromFile(c_str(fname), ctypes.byref(handle)))
File “/usr/local/lib/python3.7/dist-packages/mxnet/base.py”, line 252, in check_call
raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: Cannot find argument ‘layout’, Possible Arguments:

kernel : Shape(tuple), optional, default=[]
Pooling kernel size: (y, x) or (d, y, x)
pool_type : {‘avg’, ‘lp’, ‘max’, ‘sum’},optional, default=‘max’
Pooling type to be applied.
global_pool : boolean, optional, default=0
Ignore kernel size, do global pooling based on current input feature map.
cudnn_off : boolean, optional, default=0
Turn off cudnn pooling and use MXNet pooling operator.
pooling_convention : {‘full’, ‘same’, ‘valid’},optional, default=‘valid’
Pooling convention to be applied.
stride : Shape(tuple), optional, default=[]
Stride: for pooling (y, x) or (d, y, x). Defaults to 1 for each dimension.
pad : Shape(tuple), optional, default=[]
Pad for pooling: (y, x) or (d, y, x). Defaults to no padding.
p_value : int or None, optional, default=‘None’
Value of p for Lp pooling, can be 1 or 2, required for Lp Pooling.
count_include_pad : boolean or None, optional, default=None
Only used for AvgPool, specify whether to count padding elements for averagecalculation. For example, with a 55 kernel on a 33 corner of a image,the sum of the 9 valid elements will be divided by 25 if this is set to true,or it will be divided by 9 if this is set to false. Defaults to true.

corrupted size vs. prev_size
已放弃

另外,在把训练好的模型进行转换时,执行以下语句报错,在ubuntu16.04下则可以正常运行。
ctx = mx.cpu()
im_fname = ‘1.jpg’
x, img = data.transforms.presets.ssd.load_test(im_fname, short=512)
x = x.as_in_context(ctx)

报错信息如下:
Traceback (most recent call last):
File “model_transform.py”, line 8, in
x, img = data.transforms.presets.ssd.load_test(im_fname, short=512)
File “/usr/local/lib/python3.7/dist-packages/gluoncv/data/transforms/presets/ssd.py”, line 94, in load_test
imgs = [mx.image.imread(f) for f in filenames]
File “/usr/local/lib/python3.7/dist-packages/gluoncv/data/transforms/presets/ssd.py”, line 94, in
imgs = [mx.image.imread(f) for f in filenames]
File “/usr/local/lib/python3.7/dist-packages/mxnet/image/image.py”, line 83, in imread
return _internal._cvimread(filename, *args, **kwargs)
File “”, line 35, in _cvimread
File “/usr/local/lib/python3.7/dist-packages/mxnet/_ctypes/ndarray.py”, line 92, in _imperative_invoke
ctypes.byref(out_stypes)))
File “/usr/local/lib/python3.7/dist-packages/mxnet/base.py”, line 252, in check_call
raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: [10:51:27] /work/mxnet/src/io/image_io.cc:249: Build with USE_OPENCV=1 for image io.

Stack trace returned 8 entries:
[bt] (0) /usr/local/lib/python3.7/dist-packages/mxnet/libmxnet.so(dmlc::StackTrace()+0x34) [0xae058acc]
[bt] (1) /usr/local/lib/python3.7/dist-packages/mxnet/libmxnet.so(dmlc::LogMessageFatal::~LogMessageFatal()+0x30) [0xae058db0]
[bt] (2) /usr/local/lib/python3.7/dist-packages/mxnet/libmxnet.so(mxnet::io::Imread(nnvm::NodeAttrs const&, std::vector<mxnet::NDArray, std::allocatormxnet::NDArray > const&, std::vector<mxnet::NDArray, std::allocatormxnet::NDArray >)+0x3c) [0xae1a7d38]
[bt] (3) /usr/local/lib/python3.7/dist-packages/mxnet/libmxnet.so(mxnet::Imperative::Invoke(mxnet::Context const&, nnvm::NodeAttrs const&, std::vector<mxnet::NDArray
, std::allocatormxnet::NDArray* > const&, std::vector<mxnet::NDArray*, std::allocatormxnet::NDArray* > const&)+0x1b4) [0xae1869a0]
[bt] (4) /usr/local/lib/python3.7/dist-packages/mxnet/libmxnet.so(MXImperativeInvokeImpl(void*, int, void**, int*, void***, int, char const**, char const**)+0x3b4) [0xae07f314]
[bt] (5) /usr/local/lib/python3.7/dist-packages/mxnet/libmxnet.so(MXImperativeInvokeEx+0x80) [0xae080240]
[bt] (6) /lib/arm-linux-gnueabihf/libffi.so.6(ffi_call_VFP+0x54) [0xb5d78cc0]
[bt] (7) /lib/arm-linux-gnueabihf/libffi.so.6(ffi_call+0x154) [0xb5d796cc]

Segmentation fault: 11

请各位帮忙看看原因,或者是否有别的办法调用模型,谢谢!