uday60 commented on issue #4830: libnnvm_compiler.so file missing | Commands 
inside
URL: https://github.com/apache/incubator-tvm/issues/4830#issuecomment-583401837
 
 
   @tqchen 
   I have been using an earlier version of TVM. Now things have changed the 
following script is giving me a segmentation fault. I have already raised the 
issue here but no replies.
   
https://discuss.tvm.ai/t/conversion-script-terminate-called-after-throwing-an-instance-of-std-bad-alloc/5601
   
   
   ```
   import onnx
   import numpy as np
   import tvm
   import tvm.relay as relay
   import nnvm.compiler
   import nnvm.testing
   
   onnx_model = onnx.load('./centerface.onnx')
   opt_level = 3
   target = tvm.target.create("llvm -mcpu=haswell")
   
   image_size = (224, 224)
   shape_dict = {'data': (1, 3, *image_size)}
   print(shape_dict)
   
   nnvm_sym, nnvm_params = relay.frontend.from_onnx(onnx_model, shape_dict)
   with nnvm.compiler.build_config(opt_level=opt_level):
      graph, lib, params = nnvm.compiler.build(nnvm_sym, target, shape_dict, 
params=nnvm_params)
   
   lib.export_library("./centerface_deploy_lib.so")
   print('lib export succeefully')
   with open("./centerface_deploy_graph.json", "w") as fo:
      fo.write(graph.json())
   with open("./centerface_deploy_param.params", "wb") as fo:
      fo.write(nnvm.compiler.save_param_dict(params))
   ```

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to