You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2020/09/27 11:24:49 UTC

[GitHub] [incubator-tvm] fernchen opened a new issue #6571: Unable to build NMS in tensorflow

fernchen opened a new issue #6571:
URL: https://github.com/apache/incubator-tvm/issues/6571


   When I execute the test case in tests/python/frontend/tensorflow/test_forward.py, I try to change the mode to “” in _test_forward_nms_v3(…) function, then it will raise some error, like this:
   
   >   File "test_forward.py", line 165, in run_tvm_graph
       graph, lib, params = relay.build(mod, target, target_host, params)
     File "/root/projects/tvm_open/python/tvm/relay/build_module.py", line 259, in build
       graph_json, mod, params = bld_mod.build(mod, target, target_host, params)
     File "/root/projects/tvm_open/python/tvm/relay/build_module.py", line 126, in build
       self._build(mod, target, target_host)
     File "tvm/_ffi/_cython/./packed_func.pxi", line 321, in tvm._ffi._cy3.core.PackedFuncBase.__call__
     File "tvm/_ffi/_cython/./packed_func.pxi", line 256, in tvm._ffi._cy3.core.FuncCall
     File "tvm/_ffi/_cython/./packed_func.pxi", line 245, in tvm._ffi._cy3.core.FuncCall3
     File "tvm/_ffi/_cython/./base.pxi", line 160, in tvm._ffi._cy3.core.CALL
   tvm._ffi.base.TVMError: Traceback (most recent call last):
     [bt] (8) /root/projects/tvm_open/build/libtvm.so(tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>::VisitExpr(tvm::RelayExpr const&)+0x10c) [0x7fbc61b04f1e]
     [bt] (7) /root/projects/tvm_open/build/libtvm.so(tvm::NodeFunctor<void (tvm::runtime::ObjectRef const&, tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>*)>::operator()(tvm::runtime::ObjectRef const&, tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>*) const+0x11e) [0x7fbc61b05d8c]
     [bt] (6) /root/projects/tvm_open/build/libtvm.so(tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>::InitVTable()::{lambda(tvm::runtime::ObjectRef const&, tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>*)#6}::_FUN(tvm::runtime::ObjectRef const&, tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>*)+0x25) [0x7fbc61b05582]
     [bt] (5) /root/projects/tvm_open/build/libtvm.so(tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>::InitVTable()::{lambda(tvm::runtime::ObjectRef const&, tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>*)#6}::operator()(tvm::runtime::ObjectRef const&, tvm::relay::ExprFunctor<void (tvm::RelayExpr const&)>*) const+0x3e) [0x7fbc61b05556]
     [bt] (4) /root/projects/tvm_open/build/libtvm.so(tvm::relay::StorageAllocator::VisitExpr_(tvm::relay::CallNode const*)+0x167) [0x7fbc61d2ef4b]
     [bt] (3) /root/projects/tvm_open/build/libtvm.so(tvm::relay::StorageAllocator::CreateToken(tvm::RelayExprNode const*, bool)+0x1b7) [0x7fbc61d2ecbb]
     [bt] (2) /root/projects/tvm_open/build/libtvm.so(tvm::relay::StorageAllocator::Request(tvm::relay::StorageToken*)+0x33) [0x7fbc61d2f457]
     [bt] (1) /root/projects/tvm_open/build/libtvm.so(tvm::relay::StorageAllocator::GetMemorySize(tvm::relay::StorageToken*)+0x16d) [0x7fbc61d2f255]
     [bt] (0) /root/projects/tvm_open/build/libtvm.so(dmlc::LogMessageFatal::~LogMessageFatal()+0x4e) [0x7fbc60f619be]
     File "/root/projects/tvm_open/src/relay/backend/graph_plan_memory.cc", line 293
   TVMError: Check failed: pval != nullptr: Cannot allocate memory symbolic tensor shape [?]
   
   you can reproduce this problom by change the `mode` to "" in _test_forward_nms_v3 function of  tests/python/frontend/tensorflow/test_forward.py scripts and then execute the script.


----------------------------------------------------------------
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:
users@infra.apache.org

[GitHub] [incubator-tvm] tqchen closed issue #6571: Unable to build NMS in tensorflow

Posted by GitBox <gi...@apache.org>.
tqchen closed issue #6571:
URL: https://github.com/apache/incubator-tvm/issues/6571


   


----------------------------------------------------------------
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:
users@infra.apache.org

[GitHub] [incubator-tvm] tqchen commented on issue #6571: Unable to build NMS in tensorflow

Posted by GitBox <gi...@apache.org>.
tqchen commented on issue #6571:
URL: https://github.com/apache/incubator-tvm/issues/6571#issuecomment-700097770


   Thanks for asking the question, it would be great to use https://discuss.tvm.apache.org/ for general trouble shooting. In this particular case, it might due to the fact that the model imported contains dynamic shape and we do not support graph runtime for that(need to use vm)


----------------------------------------------------------------
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:
users@infra.apache.org