Deploying the pretrained model. Does this have any requirement?

Hello, So when I am using deploy/test.py with an image with no face it pops up an error"raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: Error in operator conv0: [22:06:53] C:\Jenkins\workspace\mxnet-tag\mxnet\src\operator\nn\convolution.cc:152: Check failed: dshp.ndim()
== 4U (1 vs. 4) : Input data should be 4D in batch-num_filter-y-x" . Does everyimage require it to have a face? If so how do I deploy it on videos? Or is there any data_preprocessing?