1. Support int32 input data type.
2. Support GatherV2 op
3. Add transpose to ExpandDim op.

1. input_data_formats flag in yaml supports OIHW
2. MaceTensor support OIHW data format

1. Remove data_format flag for ambiguous
2. add has_data_format for distinguish models without data format.

N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>

support kaldi-onnx model convert
support validate output data from url

Bring gain of top-1 accuracy (69.54% -> 70.20%)

1. Fix random device chosen bug.
2. Add random device chosen strategy for running model.

Simple print fix so it will work with py3 and removed spaces as requested as well.

1. Convert OpenCL binary files to code.
2. example support OpenCL byte stream with --cl_binary_to_code flag.

bugfix: 修复使用benchmark命令是，传入的device是cpu+gpu，而mace的某些方法只能检测cpu或者gpu这种形式(而不是cpu+gpu)，因此需要将cpu和gpu分开加入到runtime_list中，否则无法执行GPU

Regex will not match ADB IP devices.

add onnx_optimizer tool and update onnx info in docs