yuwenjun1988 opened a new issue, #13225:
URL: https://github.com/apache/tvm/issues/13225

   Expected behavior
   No Crash
   
   Actual behavior
   Crash Stack
   python3 arm_cpu_imagenet_bench.py --model p20pro --rpc-key android
   --------------------------------------------------
   Network Name         Mean Inference Time (std dev)
   --------------------------------------------------
   dense is not optimized for arm cpu.
   dense is not optimized for arm cpu.
   dense is not optimized for arm cpu.
   pool is not optimized for arm cpu.
   pool is not optimized for arm cpu.
   pool is not optimized for arm cpu.
   pool is not optimized for arm cpu.
   pool is not optimized for arm cpu.
   dense is not optimized for arm cpu.
   dense is not optimized for arm cpu.
   dense is not optimized for arm cpu.
   Traceback (most recent call last):
     File "/mnt/e/code/tvm/apps/benchmark/arm_cpu_imagenet_bench.py", line 121, 
in <module>
       evaluate_network(network, target, target_host, args.repeat)
     File "/mnt/e/code/tvm/apps/benchmark/arm_cpu_imagenet_bench.py", line 58, 
in evaluate_network
       remote.upload(tmp.relpath(filename))
     File "/mnt/e/code/tvm/python/tvm/rpc/client.py", line 115, in upload
       self._remote_funcs["upload"](target, blob)
     File "/mnt/e/code/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):
     3: TVMFuncCall
     2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, 
tvm::runtime::TVMRetValue*) const
     1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int 
const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
     0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, 
int, std::function<void (tvm::runtime::TVMArgs)>)
     File "/mnt/e/code/tvm/src/runtime/rpc/rpc_endpoint.cc", line 804
   TVMError:
   ---------------------------------------------------------------
   An error occurred during the execution of TVM.
   
   Environment
   Ubuntu 18.04 TVM 0.11.dev0
   Any environment details, such as: Operating System, TVM version, etc
   
   Steps to reproduce
    python3 arm_cpu_imagenet_bench.py --model p20pro --rpc-key android


-- 
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.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to