Problems encountered while compiling the onnx model about nnsmith HOT 4 CLOSED

I entered the tvm environment to reinstall the required configuration for nnsmith and ran the command "nnsmith. model_exec model. type=onnx"\

Backend. type=onnxruntime\

Model. path=nnsmith_ Output/model.onnx\

Cmp. with='{type: tvm, optmax: true, target: CPU}' 'conducted differential testing, but encountered an error as shown in the above figure. Can someone help me identify the cause.

Well, this is a TVM problem and nnsmith cannot help here.

More specifically, the pre-built TVM binary is compiled using a GLibC version which is newer than what your OS has right now. You can either recompile TVM locally to use your local glibc or install a newer glibc in conda.

from nnsmith.

I entered the tvm environment to reinstall the required configuration for nnsmith and ran the command "nnsmith. model_exec model. type=onnx"
Backend. type=onnxruntime
Model. path=nnsmith_ Output/model.onnx
Cmp. with='{type: tvm, optmax: true, target: CPU}' 'conducted differential testing, but encountered an error as shown in the above figure. Can someone help me identify the cause.

Well, this is a TVM problem and nnsmith cannot help here.

More specifically, the pre-built TVM binary is compiled using a GLibC version which is newer than what your OS has right now. You can either recompile TVM locally to use your local glibc or install a newer glibc in conda.

I understand. Thanks for your help.

from nnsmith.

I entered the tvm environment to reinstall the required configuration for nnsmith and ran the command "nnsmith. model_exec model. type=onnx"\

Backend. type=onnxruntime\

Model. path=nnsmith_ Output/model.onnx\

Cmp. with='{type: tvm, optmax: true, target: CPU}' 'conducted differential testing, but encountered an error as shown in the above figure. Can someone help me identify the cause.

from nnsmith.

Thanks for reporting the issue. Looks like you are right, onnx updated their API in 1.15.0 to load_from_string. Please bear a bit by downgrading the onnx versions for now before I brought up a fix.

from nnsmith.