Cannot allocate memory symbolic tensor shape [T.Any(), 3, 224, 224] [Bug]

[qq1243196045]

when I use tvmc ,something error occurred:

wget https://github.com/onnx/models/raw/main/vision/classification/resnet/model/resnet50-v2-7.onnx
tvmc compile --target "llvm"   --output resnet50-v2-7-tvm.tar  resnet50-v2-7.onnx

WARNING:autotvm:One or more operators have not been tuned. Please tune your model for better performance. Use DEBUG logging level to see more details.
Traceback (most recent call last):
  File "/root/anaconda3/envs/tvm-build/bin/tvmc", line 33, in <module>
    sys.exit(load_entry_point('tvm==0.13.dev217+g2d2b72733', 'console_scripts', 'tvmc')())
  File "/projects/tvm/python/tvm/driver/tvmc/main.py", line 118, in main
    sys.exit(_main(sys.argv[1:]))
  File "/projects/tvm/python/tvm/driver/tvmc/main.py", line 106, in _main
    return args.func(args)
  File "/projects/tvm/python/tvm/driver/tvmc/compiler.py", line 217, in drive_compile
    **transform_args,
  File "/projects/tvm/python/tvm/driver/tvmc/compiler.py", line 421, in compile_model
    workspace_pools=workspace_pools,
  File "/projects/tvm/python/tvm/driver/tvmc/compiler.py", line 491, in build
    workspace_memory_pools=workspace_pools,
  File "/projects/tvm/python/tvm/relay/build_module.py", line 372, in build
    mod_name=mod_name,
  File "/projects/tvm/python/tvm/relay/build_module.py", line 169, in build
    mod_name,
  File "/projects/tvm/python/tvm/_ffi/_ctypes/packed_func.py", line 238, in __call__
    raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
  15: TVMFuncCall
  14: tvm::relay::backend::RelayBuildModule::GetFunction(tvm::runtime::String const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#3}::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
  13: tvm::relay::backend::RelayBuildModule::Build(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&, tvm::Target const&, tvm::relay::Executor const&, tvm::relay::Runtime const&, tvm::WorkspaceMemoryPools const&, tvm::ConstantMemoryPools const&, tvm::runtime::String)
  12: tvm::relay::backend::RelayBuildModule::BuildRelay(tvm::IRModule, tvm::runtime::String const&)
  11: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::relay::backend::GraphExecutorCodegenModule::GetFunction(tvm::runtime::String 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*)
  10: tvm::relay::backend::GraphExecutorCodegen::Codegen(tvm::IRModule, tvm::relay::Function, tvm::runtime::String)
  9: tvm::relay::GraphPlanMemory(tvm::relay::Function const&)
  8: tvm::relay::StorageAllocator::Plan(tvm::relay::Function const&)
  7: tvm::relay::ExprVisitor::VisitExpr(tvm::RelayExpr const&)
  6: tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>::VisitExpr(tvm::RelayExpr const&)
  5: tvm::relay::transform::DeviceAwareExprVisitor::VisitExpr_(tvm::relay::FunctionNode const*)
  4: tvm::relay::StorageAllocaBaseVisitor::DeviceAwareVisitExpr_(tvm::relay::FunctionNode const*)
  3: tvm::relay::StorageAllocaBaseVisitor::CreateToken(tvm::RelayExprNode const*, bool)
  2: tvm::relay::StorageAllocator::CreateTokenOnDevice(tvm::RelayExprNode const*, tvm::VirtualDevice const&, bool)
  1: tvm::relay::TokenAllocator1D::Alloc(tvm::relay::StorageToken*, long)
  0: tvm::relay::TokenAllocator1D::GetMemorySize(tvm::relay::StorageToken*)
  File "/projects/tvm/src/relay/backend/token_allocator.cc", line 41
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 [T.Any(), 3, 224, 224]

[sheepHavingPurpleLeaf]

relay doesn't support dynamic inputs abd here is the batchsize. I'm also new to TVM, after some searching I found that relax can handle dynamic shape inputs now. But I haven't found a working example yet.

[masahi]

You don't need Relax if it is a simple dynamic shape like dynamic batch. TVMC apparently supports compiling and running with Relay VM, that's what you need here.

#10722