The following error occurs when inputting image to extract features through forward propagation. Sincerely ask for the reason

File "/home/xl/anaconda3/envs/test/lib/python3.5/site-packages/mxnet/base.py", line 253, in check_call
raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: [18:36:16] src/executor/graph_executor.cc:935: Shape of unspecifie arg: conv0_weight changed. This can cause the new executor to not share parameters with the old one. Please check for error in network.If this is intended, set partial_shaping=True to suppress this warning.
Stack trace:
[bt] (0) /home/xl/anaconda3/envs/test/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x4b09db) [0x7f759515b9db]
[bt] (1) /home/xl/anaconda3/envs/test/lib/python3.5/site-packages/mxnet/libmxnet.so(mxnet::exec::GraphExecutor::Reshape(bool, bool, mxnet::Context const&, std::map, std::allocator > > const&, std::unordered_map, std::equal_to, std::allocator > > const&, std::vector >*, std::vector >*, std::vector >*)+0x819) [0x7f75972b92d9]
[bt] (2) /home/xl/anaconda3/envs/test/lib/python3.5/site-packages/mxnet/libmxnet.so(MXExecutorReshapeEx+0x98c) [0x7f75971f526c]
[bt] (3) /home/xl/anaconda3/envs/test/lib/python3.5/lib-dynload/../../libffi.so.6(ffi_call_unix64+0x4c) [0x7f75c934aec0]
[bt] (4) /home/xl/anaconda3/envs/test/lib/python3.5/lib-dynload/../../libffi.so.6(ffi_call+0x22d) [0x7f75c934a87d]
[bt] (5) /home/xl/anaconda3/envs/test/lib/python3.5/lib-dynload/_ctypes.cpython-35m-x86_64-linux-gnu.so(_ctypes_callproc+0x2ce) [0x7f75deeb5cbe]
[bt] (6) /home/xl/anaconda3/envs/test/lib/python3.5/lib-dynload/_ctypes.cpython-35m-x86_64-linux-gnu.so(+0x136e5) [0x7f75deeb66e5]
[bt] (7) /home/xl/anaconda3/envs/test/bin/python(PyObject_Call+0x3a) [0x55a5ed54a61a]
[bt] (8) /home/xl/anaconda3/envs/test/bin/python(PyEval_EvalFrameEx+0x4e69) [0x55a5ed5f0fb9]

model = face_model.FaceModel(args)
img = cv2.imread('1.jpg')
print(img)
img = model.get_input(img)
f1 = model.get_feature(img)
print(f1[0:10])
gender, age = model.get_ga(img)
print(gender)
print(age)
# sys.exit(0)
img = cv2.imread('1.jpg')
print (img)
f2 = model.get_feature(img)
dist = np.sum(np.square(f1-f2))
print(dist)
sim = np.dot(f1, f2.T)
print(sim)
#diff = np.subtract(source_feature, target_feature)
#dist = np.sum(np.square(diff),1)