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
