pytorch / glow

Compiler for Neural Network hardware accelerators

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[Bug] error on an ONNX model with the GlobalAveragePool operation

luyaor opened this issue · comments

When compiling following ONNX model with Glow, the compiler fails with errors.

image

Error message:

model-compiler: /usr/lib/llvm-8/include/llvm/ADT/ArrayRef.h:241: const T &llvm::ArrayRef<unsigned int>::operator[](size_t) const [T = unsigned int]: Assertion `Index < Length && "Invalid index!"' failed.   -dump-ird3097:~/dev/build_Debug# ./bin/model-compiler     -model ../genmodel-g-small/g299.onnx     -emit-bundle ./mybundle     --backend=CPU  
./bin/model-compiler[0xcbde7f]
./bin/model-compiler[0xcbc2a2]
./bin/model-compiler[0xcbe288]
/lib/x86_64-linux-gnu/libpthread.so.0(+0x12980)[0x7fe8040e2980]
/lib/x86_64-linux-gnu/libc.so.6(gsignal+0xc7)[0x7fe801b93e87]
/lib/x86_64-linux-gnu/libc.so.6(abort+0x141)[0x7fe801b957f1]
/lib/x86_64-linux-gnu/libc.so.6(+0x303fa)[0x7fe801b853fa]
/lib/x86_64-linux-gnu/libc.so.6(+0x30472)[0x7fe801b85472]
./bin/model-compiler[0x596dcb]
./bin/model-compiler[0x5d934d]
./bin/model-compiler[0x8e5796]
./bin/model-compiler[0xa72105]
./bin/model-compiler[0xa94cae]
./bin/model-compiler[0x8fe46f]
./bin/model-compiler[0xa7712c]
./bin/model-compiler[0xa7cbfa]
./bin/model-compiler[0xa7db03]
./bin/model-compiler[0xa7d6fe]
./bin/model-compiler[0x4d010a]
./bin/model-compiler[0x521510]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xe7)[0x7fe801b76c87]
./bin/model-compiler[0x4cee5a]
Aborted
root@0b21477d3097

The model file and run script are as follows:

./bin/model-compiler     -model ../g8.onnx     -emit-bundle ./mybundle     --backend=CPU  

model file is attached.
g8.onnx.zip