FasterRcnn conversion to ONNX example fails

🐛 Describe the bug

Found in this example
https://github.com/pytorch/vision/blob/e65a857b5487a8493bc8a80a95d64d9f049de347/torchvision/models/detection/faster_rcnn.py#L373

Following this example, the onnx conversion fails. I get this error:

11/18/2024-22:21:39] [I] [TRT] Input filename:   faster_rcnn.onnx
[11/18/2024-22:21:39] [I] [TRT] ONNX IR version:  0.0.6
[11/18/2024-22:21:39] [I] [TRT] Opset version:    11
[11/18/2024-22:21:39] [I] [TRT] Producer name:    pytorch
[11/18/2024-22:21:39] [I] [TRT] Producer version: 1.11.0
[11/18/2024-22:21:39] [I] [TRT] Domain:           
[11/18/2024-22:21:39] [I] [TRT] Model version:    0
[11/18/2024-22:21:39] [I] [TRT] Doc string:       
[11/18/2024-22:21:39] [I] [TRT] ----------------------------------------------------------------
[11/18/2024-22:21:39] [E] Error[4]: ITensor::getDimensions: Error Code 4: Shape Error (reshape wildcard -1 has infinite number of solutions or no solution. Reshaping [0,364] to [0,-1].)
[11/18/2024-22:21:39] [E] [TRT] parsers/onnx/ModelImporter.cpp:944: While parsing node number 1826 [Reshape -> "rel_codes.3"]:
[11/18/2024-22:21:39] [E] [TRT] parsers/onnx/ModelImporter.cpp:947: --- Begin node ---
input: "box_regression"
input: "onnx::Reshape_3184"
output: "rel_codes.3"
name: "Reshape_1882"
op_type: "Reshape"

[11/18/2024-22:21:39] [E] [TRT] parsers/onnx/ModelImporter.cpp:948: --- End node ---
[11/18/2024-22:21:39] [E] [TRT] parsers/onnx/ModelImporter.cpp:950: ERROR: parsers/onnx/ModelImporter.cpp:197 In function parseNode:
[6] Invalid Node - Reshape_1882
ITensor::getDimensions: Error Code 4: Shape Error (reshape wildcard -1 has infinite number of solutions or no solution. Reshaping [0,364] to [0,-1].)
[11/18/2024-22:21:39] [E] Failed to parse onnx file
[11/18/2024-22:21:39] [I] Finished parsing network model. Parse time: 0.192799
[11/18/2024-22:21:39] [E] Parsing model failed
[11/18/2024-22:21:39] [E] Failed to create engine from model or file.
[11/18/2024-22:21:39] [E] Engine set up failed
&&&& FAILED TensorRT.trtexec [TensorRT v100600] [b26] # trtexec --onnx=faster_rcnn.onnx --saveEngine=test_engine.trt

Versions

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 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: 14.0.0-1ubuntu1.1
CMake version: version 3.22.1
Libc version: glibc-2.35

Python version: 3.12.2 | packaged by conda-forge | (main, Feb 16 2024, 20:50:58) [GCC 12.3.0] (64-bit runtime)
Python platform: Linux-6.8.0-48-generic-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 RTX A6000
Nvidia driver version: 550.120
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:                        48 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               32
On-line CPU(s) list:                  0-31
Vendor ID:                            AuthenticAMD
Model name:                           AMD Ryzen 9 7950X 16-Core Processor
CPU family:                           25
Model:                                97
Thread(s) per core:                   2
Core(s) per socket:                   16
Socket(s):                            1
Stepping:                             2
CPU max MHz:                          5881.0000
CPU min MHz:                          400.0000
BogoMIPS:                             8983.10
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid overflow_recov succor smca fsrm flush_l1d
Virtualization:                       AMD-V
L1d cache:                            512 KiB (16 instances)
L1i cache:                            512 KiB (16 instances)
L2 cache:                             16 MiB (16 instances)
L3 cache:                             64 MiB (2 instances)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-31
Vulnerability Gather data sampling:   Not affected
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:               Not affected
Vulnerability Spec rstack overflow:   Mitigation; Safe RET
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.1.1
[conda] numpy                     1.26.4                   pypi_0    pypi

Start with the Faster R-CNN ONNX conversion example in torchvision/models/detection/faster_rcnn.py around line 373 and reproduce the reported conversion. Inspect the generated faster_rcnn.onnx and the TensorRT trtexec failure at the Reshape node. Done means the documented example produces an ONNX model that TensorRT can parse successfully.