executor_runner: Check failed (all_contiguous || all_channels_last): 2 input tensors have different dim orders

[zhangzhb369]

🐛 Describe the bug

Hello,
When I run my model using executor_runner, it failed:

I 00:00:00.004201 executorch:executor_runner.cpp:82] Model file ../../_models/test.pte is loaded.
I 00:00:00.004238 executorch:executor_runner.cpp:91] Using method forward
I 00:00:00.004246 executorch:executor_runner.cpp:138] Setting up planned buffer 0, size 221984.
I 00:00:00.017338 executorch:executor_runner.cpp:161] Method loaded.
I 00:00:00.017383 executorch:executor_runner.cpp:171] Inputs prepared.
E 00:00:00.059875 executorch:tensor_util_portable.cpp:128] Check failed (all_contiguous || all_channels_last): 2 input tensors have different dim orders
E 00:00:00.059906 executorch:op_permute_copy.cpp:49] Check failed (tensors_have_same_dim_order(in, out)):
E 00:00:00.059909 executorch:method.cpp:1038] KernelCall failed at instruction 0:5520 in operator aten::permute_copy.out: 0x12
E 00:00:00.059911 executorch:method.cpp:1047] arg 0 with type id 1
E 00:00:00.059912 executorch:method.cpp:1047] arg 1 with type id 8
E 00:00:00.059913 executorch:method.cpp:1047] arg 2 with type id 1
E 00:00:00.059914 executorch:method.cpp:1047] arg 3 with type id 1
F 00:00:00.059916 executorch:executor_runner.cpp:175] In function main(), assert failed (status == Error::Ok): Execution of method forward failed with status 0x12
Aborted (core dumped)

I built executor_runner by this command:

rm -rf cmake-out && mkdir cmake-out && cd cmake-out && cmake ..
cmake --build cmake-out --target executor_runner -j9

Thanks for your help.
The model:
test.zip

Versions

I ran test.pte model on win11/WSL2:

Collecting environment information...
PyTorch version: N/A
Is debug build: N/A
CUDA used to build PyTorch: N/A
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04 LTS (x86_64)
GCC version: (Ubuntu 11.2.0-19ubuntu1) 11.2.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.35

Python version: 3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.167.4-microsoft-standard-WSL2-x86_64-with-glibc2.35
Is CUDA available: N/A
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: GPU 0: NVIDIA GeForce MX450
Nvidia driver version: 538.78
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: N/A

CPU:
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        39 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               6
On-line CPU(s) list:                  0-5
Vendor ID:                            GenuineIntel
Model name:                           11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz
CPU family:                           6
Model:                                140
Thread(s) per core:                   2
Core(s) per socket:                   3
Socket(s):                            1
Stepping:                             1
BogoMIPS:                             5606.42
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512vbmi umip avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid movdiri movdir64b fsrm avx512_vp2intersect md_clear flush_l1d arch_capabilities
Virtualization:                       VT-x
Hypervisor vendor:                    Microsoft
Virtualization type:                  full
L1d cache:                            144 KiB (3 instances)
L1i cache:                            96 KiB (3 instances)
L2 cache:                             3.8 MiB (3 instances)
L3 cache:                             12 MiB (1 instance)
Vulnerability Gather data sampling:   Unknown: Dependent on hypervisor status
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Mitigation; Enhanced IBRS
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] numpy==1.22.4
[pip3] onnx==1.12.0
[pip3] tf2onnx==1.11.1
[conda] Could not collect

[kimishpatel]

Can you list detailed repro including the model you are trying to run? Which executor_runner are you using? Is this one from examples/portable?

I do see that you have test.zip file listed here but would appreciate a simple model definition pasted here if it is not large. If large we can take a look.

[GregoryComer]

Following up with what Kimish mentioned, do you have any explicit dim order conversion in your model, such as .to(memory_format=torch.channels_last)?

[zhangzhb369]

Sorry for the latency, I'll check and return back as soon as possible.

[zhangzhb369]

Following up with what Kimish mentioned, do you have any explicit dim order conversion in your model, such as .to(memory_format=torch.channels_last)?

Sorry I don't have the source code now. I only have model files.

Can you list detailed repro including the model you are trying to run? Which executor_runner are you using? Is this one from examples/portable?

I built executor_runner using this command : (base on version: release/0.4, tag: v0.4.0-rc5)

rm -rf cmake-out && mkdir cmake-out && cd cmake-out && cmake ..
cd .. && cmake --build cmake-out --target executor_runner -j9

The configure result:
-- ******** Summary ********
-- CMAKE_BUILD_TYPE : Debug
-- CMAKE_CXX_STANDARD : 17
-- CMAKE_CXX_COMPILER_ID : GNU
-- CMAKE_TOOLCHAIN_FILE :
-- BUCK2 : /home/xxx/xxx/xxx/executorch/cmake-out/buck2-bin/buck2-3bbde7daa94987db468d021ad625bc93dc62ba7fcb16945cb09b64aab077f284
-- PYTHON_EXECUTABLE : python3
-- FLATC_EXECUTABLE : flatc
-- EXECUTORCH_ENABLE_LOGGING : ON
-- EXECUTORCH_ENABLE_PROGRAM_VERIFICATION : ON
-- EXECUTORCH_LOG_LEVEL : Info
-- EXECUTORCH_BUILD_ANDROID_JNI : OFF
-- EXECUTORCH_BUILD_ARM_BAREMETAL : OFF
-- EXECUTORCH_BUILD_COREML : OFF
-- EXECUTORCH_BUILD_KERNELS_CUSTOM : OFF
-- EXECUTORCH_BUILD_EXECUTOR_RUNNER : ON
-- EXECUTORCH_BUILD_EXTENSION_DATA_LOADER : OFF
-- EXECUTORCH_BUILD_EXTENSION_MODULE : OFF
-- EXECUTORCH_BUILD_EXTENSION_RUNNER_UTIL : OFF
-- EXECUTORCH_BUILD_EXTENSION_TENSOR : OFF
-- EXECUTORCH_BUILD_FLATC : ON
-- EXECUTORCH_BUILD_GFLAGS : ON
-- EXECUTORCH_BUILD_GTESTS : OFF
-- EXECUTORCH_BUILD_HOST_TARGETS : ON
-- EXECUTORCH_BUILD_MPS : OFF
-- EXECUTORCH_BUILD_PYBIND : OFF
-- EXECUTORCH_BUILD_QNN : OFF
-- EXECUTORCH_BUILD_KERNELS_OPTIMIZED : OFF
-- EXECUTORCH_BUILD_KERNELS_QUANTIZED : OFF
-- EXECUTORCH_BUILD_DEVTOOLS : OFF
-- EXECUTORCH_BUILD_SIZE_TEST : OFF
-- EXECUTORCH_BUILD_XNNPACK : OFF
-- EXECUTORCH_BUILD_VULKAN : OFF
-- EXECUTORCH_BUILD_PTHREADPOOL : ON
-- EXECUTORCH_BUILD_CPUINFO : ON
-- Configuring done (26.0s)

run command:
./cmake-out/executor_runner --model_path ../test.pte

I do see that you have test.zip file listed here but would appreciate a simple model definition pasted here if it is not large. If large we can take a look.

Currently I don't have a model definition, but I have a original onnx model:
origin.zip

Hope that helps.
Thanks.