[Apache TVM Discuss] [Questions] [ONNX] Failed to compile onnx yolov5s model

[xingyu zhou via Apache TVM Discuss <no...@discuss.tvm.ai>]

I was trying to compile a yolov5s onnx model but failed during compialtion stage, the error messgae is:

    Traceback (most recent call last):
     File "test2.py", line 18, in <module>
     graph, lib, params = relay.build(mod, params=params, target='llvm -mcpu=skylake-avx512')
    File "/home/ubuntu/tvm/python/tvm/relay/build_module.py", line 485, in build
    mod_name=mod_name,
    File "/home/ubuntu/tvm/python/tvm/relay/build_module.py", line 202, in build
    self._build(mod, target, target_host, executor, runtime, workspace_memory_pools, mod_name)
    File "/home/ubuntu/tvm/python/tvm/_ffi/_ctypes/packed_func.py", line 237, in __call__
    raise get_last_ffi_error()
    tvm._ffi.base.TVMError: Traceback (most recent call last):
    19: TVMFuncCall
    18: tvm::relay::backend::RelayBuildModule::GetFunction(std::__cxx11::basic_string<char, 
    std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#3}::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
    17: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
    16: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::relay::backend::GraphExecutorCodegenModule::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#2}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
    15: tvm::relay::backend::GraphExecutorCodegen::Codegen(tvm::IRModule, tvm::relay::Function, tvm::runtime::String)
    14: tvm::relay::GraphPlanMemory(tvm::relay::Function const&)
    13: tvm::relay::StorageAllocator::Plan(tvm::relay::Function const&)
    12: tvm::relay::ExprVisitor::VisitExpr(tvm::RelayExpr const&)
    11: tvm::relay::transform::DeviceAwareExprVisitor::VisitExpr_(tvm::relay::FunctionNode const*)
    10: tvm::relay::StorageAllocaBaseVisitor::DeviceAwareVisitExpr_(tvm::relay::FunctionNode const*)
    9: tvm::relay::StorageAllocaBaseVisitor::GetToken(tvm::RelayExpr const&)
    8: tvm::relay::ExprVisitor::VisitExpr(tvm::RelayExpr const&)
    7: tvm::relay::StorageAllocaBaseVisitor::VisitExpr_(tvm::relay::TupleNode const*)
    6: tvm::relay::StorageAllocaBaseVisitor::GetToken(tvm::RelayExpr const&)
    5: tvm::relay::ExprVisitor::VisitExpr(tvm::RelayExpr const&)
    4: tvm::relay::transform::DeviceAwareExprVisitor::VisitExpr_(tvm::relay::CallNode const*)
    3: tvm::relay::StorageAllocator::DeviceAwareVisitExpr_(tvm::relay::CallNode const*)
    2: tvm::relay::StorageAllocaBaseVisitor::CreateToken(tvm::RelayExprNode const*, bool)
    1: tvm::relay::StorageAllocator::CreateTokenOnDevice(tvm::RelayExprNode const*, tvm::VirtualDevice const&, bool)
    0: tvm::relay::StorageAllocator::GetMemorySize(tvm::relay::StorageToken*)
    File "/home/ubuntu/tvm/src/relay/backend/graph_plan_memory.cc", line 398
    TVMError: 
    ---------------------------------------------------------------

    An error occurred during the execution of TVM.
    For more information, please see: https://tvm.apache.org/docs/errors.html
    ---------------------------------------------------------------
      Check failed: (pval != nullptr) is false: Cannot allocate memory symbolic tensor shape [1, ?, 85]

The model I used is here: https://docs.ultralytics.com/tutorials/torchscript-onnx-coreml-export/
exported using command:

>python3 export.py --weights yolov5s.pt --batch 1 --opset 14 --dynamic

I am wondering anyone encountered similar problems and how to solve it.





---
[Visit Topic](https://discuss.tvm.apache.org/t/onnx-failed-to-compile-onnx-yolov5s-model/12297/1) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/aaed38eb3203a17adada083b2d1f66a1525c711261a098554d3d5757bdba7723).