Error when trying to export yoloNAS to ONNX using documentation tutorial script

[siddagra]

🐛 Describe the bug

ONNX export fails when trying the tutorial/documentation code in the yoloNAS-export .md:

from super_gradients.common.object_names import Models
from super_gradients.training import models

model = models.get(Models.YOLO_NAS_S, pretrained_weights="coco")

export_result = model.export("yolo_nas_s.onnx")

Error:

RuntimeError: The shape of input "raw_scores" has dynamic size "[1, 1000, 0]", please determine the input size manually by "--dynamic-input-shape --input-shape xxx" or "--input-shape xxx". Run "python3 -m onnxsim -h" for details

Versions

PyTorch version: 2.0.1+cu117 Is debug build: False CUDA used to build PyTorch: 11.7 ROCM used to build PyTorch: N/A

OS: Ubuntu 20.04.6 LTS (x86_64) GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0 Clang version: Could not collect CMake version: version 3.26.4 Libc version: glibc-2.31

Python version: 3.8.10 (default, May 26 2023, 14:05:08) [GCC 9.4.0] (64-bit runtime) Python platform: Linux-5.15.0-88-generic-x86_64-with-glibc2.29 Is CUDA available: True CUDA runtime version: 11.7.64 CUDA_MODULE_LOADING set to: LAZY GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3080 Nvidia driver version: 545.23.06 cuDNN version: Probably one of the following: /usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.5 /usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.5 /usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.5 /usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.5 /usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.5 /usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.5 /usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.5 HIP runtime version: N/A MIOpen runtime version: N/A Is XNNPACK available: True

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 43 bits physical, 48 bits virtual CPU(s): 12 On-line CPU(s) list: 0-11 Thread(s) per core: 2 Core(s) per socket: 6 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 113 Model name: AMD Ryzen 5 3600 6-Core Processor Stepping: 0 Frequency boost: enabled CPU MHz: 2200.000 CPU max MHz: 3900.0000 CPU min MHz: 2200.0000 BogoMIPS: 7799.96 Virtualization: AMD-V L1d cache: 192 KiB L1i cache: 192 KiB L2 cache: 3 MiB L3 cache: 32 MiB NUMA node0 CPU(s): 0-11 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 Retbleed: Mitigation; untrained return thunk; SMT enabled with STIBP protection Vulnerability Spec rstack overflow: Mitigation; safe RET 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; Retpolines, IBPB conditional, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected 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 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic 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 ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sme sev sev_es

Versions of relevant libraries: [pip3] botorch==0.5.1 [pip3] flake8==3.9.2 [pip3] flake8-import-order==0.18.1 [pip3] gpytorch==1.9.0 [pip3] mypy-extensions==1.0.0 [pip3] numpy==1.23.0 [pip3] onnx==1.13.0 [pip3] onnx-graphsurgeon==0.3.27 [pip3] onnx-simplifier==0.3.6 [pip3] onnx2tf==1.13.11 [pip3] onnxoptimizer==0.3.13 [pip3] onnxruntime==1.13.1 [pip3] onnxruntime-gpu==1.15.1 [pip3] onnxsim==0.4.31 [pip3] pytorch-lightning==2.0.4 [pip3] pytorch-quantization==2.1.3 [pip3] sng4onnx==1.0.1 [pip3] tf2onnx==1.14.0 [pip3] torch==2.0.1 [pip3] torch-tensorrt==1.4.0 [pip3] torchaudio==2.0.2 [pip3] torchcontrib==0.0.2 [pip3] torchdata==0.6.1 [pip3] torchmetrics==0.8.0 [pip3] torchtext==0.15.2 [pip3] torchvision==0.15.2 [pip3] triton==2.0.0 [conda] Could not collect

[BloodAxe]

I'm sorry to hear you are having issues with .export(). To ensure we dig to the root of the problem can you provide some additional information about your environment (pip freeze output would be enough).

Also, if you can provide a full stacktrace and not just one line that would help as understand why you having this issue on your machine. Thing is I cannot reproduce this error either locally (torch 2.0.1, sg 3.4.0, onnx-simplifier==0.4.33 onnx-graphsurgeon==0.3.27) or on our CI (We have allo sorts of tests coverting .export()). It could be some losse version of some package. Therefore a full pip freeze should give us a clue what may be causing this issue.

[siddagra]

Thank you for the response.

I tried re-installing all onnx packages. but got the same error.

Full stack trace:

Traceback (most recent call last):
  File "/media/user123/PortableSSD/onnx_exporting_yoloNAS.py", line 53, in <module>
    export_result = model.export(
  File "/home/user123/.local/lib/python3.8/site-packages/super_gradients/module_interfaces/exportable_detector.py", line 522, in export
    nms_attach_method(
  File "/home/user123/.local/lib/python3.8/site-packages/super_gradients/conversion/onnx/nms.py", line 385, in attach_onnx_nms
    convert_format_graph = PickNMSPredictionsAndReturnAsFlatResult.as_graph(
  File "/home/user123/.local/lib/python3.8/site-packages/super_gradients/conversion/onnx/nms.py", line 259, in as_graph
    model_opt, check_ok = onnxsim.simplify(onnx_file)
  File "/home/user123/.local/lib/python3.8/site-packages/onnxsim/onnx_simplifier.py", line 492, in simplify
    model = fixed_point(model, infer_shapes_and_optimize, constant_folding)
  File "/home/user123/.local/lib/python3.8/site-packages/onnxsim/onnx_simplifier.py", line 393, in fixed_point
    x = func_b(x)
  File "/home/user123/.local/lib/python3.8/site-packages/onnxsim/onnx_simplifier.py", line 482, in constant_folding
    res = forward_for_node_outputs(model,
  File "/home/user123/.local/lib/python3.8/site-packages/onnxsim/onnx_simplifier.py", line 229, in forward_for_node_outputs
    res = forward(model,
  File "/home/user123/.local/lib/python3.8/site-packages/onnxsim/onnx_simplifier.py", line 210, in forward
    inputs.update(generate_specific_rand_input(model, {name: shape}))
  File "/home/user123/.local/lib/python3.8/site-packages/onnxsim/onnx_simplifier.py", line 98, in generate_specific_rand_input
    raise RuntimeError(
RuntimeError: The shape of input "pred_scores" has dynamic size "[1, 100, 0]", please determine the input size manually by "--dynamic-input-shape --input-shape xxx" or "--input-shape xxx". Run "python3 -m onnxsim -h" for details

pip freeze output:

absl-py==1.0.0
addict==2.4.0
aiofiles==23.1.0
aiohttp==3.8.1
aiosignal==1.2.0
alabaster==0.7.13
albumentations==1.3.1
altair==5.1.2
antlr4-python3-runtime==4.9.3
anyio==3.7.1
apex==0.1
appdirs==1.4.4
apturl==0.5.2
arabic-reshaper==3.0.0
argon2-cffi==21.3.0
argon2-cffi-bindings==21.2.0
asn1crypto==1.5.1
astor==0.8.1
astunparse==1.6.3
async-timeout==4.0.2
asynctest==0.13.0
attrdict==2.0.1
attrs==21.4.0
autopep8==1.6.0
ax-platform==0.2.2
Babel==2.9.1
backcall==0.2.0
backports.zoneinfo==0.2.1
bbox-visualizer==0.1.0
bce-python-sdk==0.8.64
bcrypt==3.1.7
beautifulsoup4==4.11.1
black==21.7b0
bleach==4.1.0
blinker==1.4
boto3==1.28.81
botocore==1.31.81
botorch==0.5.1
Brlapi==0.7.0
Brotli==1.0.9
build==1.0.3
cachetools==4.2.4
certifi==2019.11.28
cffi==1.15.0
cfgv==3.3.1
chardet==3.0.4
charset-normalizer==3.1.0
cityscapesScripts==2.2.0
click==8.0.4
cloudpickle==2.1.0
cmake==3.25.0
codecov==2.1.12
colorama==0.4.3
coloredlogs==15.0.1
command-not-found==0.3
contourpy==1.0.7
coverage==5.3.1
craft-text-detector==0.4.3
cryptography==41.0.5
cssselect==1.1.0
cssselect2==0.7.0
cssutils==2.3.0
cupshelpers==1.0
cycler==0.11.0
Cython==0.29.31
cytoolz==0.12.1
data-gradients==0.2.2
dataclasses==0.6
dbus-python==1.2.16
debugpy==1.5.1
decorator==5.1.0
deepsparse==1.5.0
defer==1.0.6
defusedxml==0.7.1
Deprecated==1.2.13
depthwise-conv2d-implicit-gemm @ file:///media/user123/7200rpm%20Seagate/UGRP-TruckNumberPlate/parseq_slak/strhub/models/parseq/SLaK/cutlass/examples/19_large_depthwise_conv2d_torch_extension
detectron2 @ file:///media/user123/7200rpm%20Seagate/FasterDAN/SwinTextSpotter
diffimg==0.2.3
dill==0.3.6
distlib==0.3.4
distro==1.4.0
distro-info==0.23+ubuntu1.1
docutils==0.17.1
dotty-dict==1.3.0
duplicity==0.8.12.0
EasyProcess==1.1
editdistance==0.6.0
efficientnet==1.0.0
einops==0.3.2
entrypoint2==1.1
entrypoints==0.3
enum34==1.1.10
essential-generators==1.0
et-xmlfile==1.1.0
eth-hash==0.5.1
eth-typing==3.2.0
eth-utils==2.1.0
exceptiongroup==1.1.3
fairseq==1.0.0a0+bed7edb
fastapi==0.104.1
fasteners==0.14.1
FasterDAN @ file:///media/user123/7200rpm%20Seagate/FasterDAN
fastjsonschema==2.18.0
fasttext==0.9.1
fastwer==0.1.3
ffmpy==0.3.1
filelock==3.11.0
fire==0.4.0
flake8==3.9.2
flake8-import-order==0.18.1
Flask==2.0.2
Flask-Babel==2.0.0
flatbuffers==23.3.3
fonttools==4.39.3
freetype-py==2.3.0
frozenlist==1.3.0
fsspec==2022.5.0
ftfy==6.1.1
future==0.18.2
fvcore==0.1.5.post20211023
gast==0.4.0
gdown==4.7.1
geocoder==1.38.1
gitdb==4.0.10
GitPython==3.1.38
Glances==3.2.6.4
google-auth==2.20.0
google-auth-oauthlib==1.0.0
google-pasta==0.2.0
gpytorch==1.9.0
gradio==3.35.2
gradio_client==0.7.0
greenlet==1.1.3.post0
grpcio==1.54.2
h11==0.14.0
h5py==3.6.0
hexbytes==0.3.0
html5lib==1.1
httpcore==0.17.3
httplib2==0.14.0
httpx==0.24.1
huggingface-hub==0.15.1
humanfriendly==10.0
hydra-core==1.3.2
hyperopt @ git+https://github.com/hyperopt/hyperopt.git@d8515263a3168ba8f111179d29e74ffb09670610
identify==2.4.1
idna==3.4
imagecodecs==2022.8.8
imagecorruptions==1.1.2
imagededup==0.3.2
imageio==2.9.0
imagesize==1.4.1
imgaug==0.4.0
imgviz==1.7.2
importlib-metadata==4.10.0
importlib-resources==5.12.0
iniconfig==1.1.1
install==1.3.5
interrogate==1.5.0
iopath==0.1.7
iotop==0.6
ipykernel==6.6.0
ipython==7.30.1
ipython-genutils==0.2.0
ipywidgets==7.6.5
isort==5.9.2
itsdangerous==2.0.1
jedi==0.18.1
Jinja2==3.1.2
jmespath==1.0.1
joblib==1.3.2
jpegdupes==2.1.0
jpegtran-cffi==0.5.2
json-tricks==3.16.1
jsonschema==4.3.2
jupyter==1.0.0
jupyter-bbox-widget==0.5.0
jupyter-client==7.1.0
jupyter-console==6.4.0
jupyter-core==4.9.1
jupyterlab-pygments==0.1.2
jupyterlab-widgets==1.0.2
keras==2.7.0
Keras-Applications==1.0.8
keras-ocr==0.8.9
Keras-Preprocessing==1.1.2
keyring==18.0.1
kiwisolver==1.4.4
kwarray==0.6.2
labelme==5.2.0
langdetect==1.0.9
language-selector==0.1
lanms==1.0.2
lanms-neo==1.0.2
lap==0.4.0
launchpadlib==1.10.13
layoutparser==0.0.0
lazr.restfulclient==0.14.2
lazr.uri==1.0.3
libclang==12.0.0
lightning-utilities==0.9.0
linear-operator==0.1.1
linkify-it-py==2.0.2
lit==15.0.7
llvmlite==0.37.0
lmdb==1.2.1
lockfile==0.12.2
loguru==0.5.3
louis==3.12.0
lxml==4.7.1
macaroonbakery==1.3.1
Mako==1.1.0
Markdown==3.3.6
markdown-it-py==2.2.0
MarkupSafe==2.1.2
matplotlib==3.7.1
matplotlib-inline==0.1.3
maxvit @ git+https://github.com/ChristophReich1996/MaxViT@bf4ccfbf5882c16b6bc63117883acea16ac1def5
mccabe==0.6.1
mdit-py-plugins==0.3.3
mdurl==0.1.2
meld==3.20.2
memray==1.10.0
metaseg==0.4.4
mistune==0.8.4
mmcls==0.19.0
mmcv==1.4.0
mmcv-full==1.6.0
# Editable install with no version control (mmdet==2.25.1)
-e /home/user123/.local/lib/python3.8/site-packages
-e git+https://github.com/open-mmlab/mmocr.git@f0d7f14c6dd57bef91cbed1a56f99e519c8dce1c#egg=mmocr
mmpycocotools @ git+https://github.com/open-mmlab/cocoapi.git@01f805cd54d7bd7af64c0fbd5fd96d8ca0b9ddc9#subdirectory=pycocotools
-e git+https://github.com/open-mmlab/mmsegmentation.git@6c3e63e48b8f94a64ac5b1d88cab6fca005ae269#egg=mmsegmentation
model-index==0.1.11
monotonic==1.5
motmetrics==1.2.0
mplcursors==0.5.2
mpmath==1.3.0
msgpack==1.0.4
multidict==6.0.2
multiprocess==0.70.14
munch==4.0.0
mypy-extensions==1.0.0
natsort==8.3.1
nbclient==0.5.9
nbconvert==6.3.0
nbformat==4.2.0
nest-asyncio==1.5.4
netifaces==0.10.4
networkx==3.1
nltk==3.6.5
nodeenv==1.6.0
notebook==6.4.6
numba==0.54.1
numpy==1.23.0
nvidia-cublas-cu11==11.10.3.66
nvidia-cublas-cu12==12.1.3.1
nvidia-cuda-cupti-cu11==11.7.101
nvidia-cuda-cupti-cu12==12.1.105
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-nvrtc-cu12==12.1.105
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cuda-runtime-cu12==12.1.105
nvidia-cudnn-cu11==8.5.0.96
nvidia-cudnn-cu12==8.9.2.26
nvidia-cufft-cu11==10.9.0.58
nvidia-cufft-cu12==11.0.2.54
nvidia-curand-cu11==10.2.10.91
nvidia-curand-cu12==10.3.2.106
nvidia-cusolver-cu11==11.4.0.1
nvidia-cusolver-cu12==11.4.5.107
nvidia-cusparse-cu11==11.7.4.91
nvidia-cusparse-cu12==12.1.0.106
nvidia-nccl-cu11==2.14.3
nvidia-nccl-cu12==2.18.1
nvidia-nvjitlink-cu12==12.2.140
nvidia-nvtx-cu11==11.7.91
nvidia-nvtx-cu12==12.1.105
nvidia-pyindex==1.0.9
nvidia-tensorrt==99.0.0
oauthlib==3.1.0
olefile==0.46
omegaconf==2.3.0
onnx==1.13.0
onnx-graphsurgeon==0.3.27
onnx-simplifier==0.3.6
onnx2tf==1.13.11
onnxoptimizer==0.3.13
onnxruntime==1.13.1
onnxruntime-gpu==1.15.1
onnxsim==0.4.31
openai-clip==1.0.1
opencv-contrib-python==4.5.5.62
opencv-python==4.7.0.72
opencv-python-headless==4.5.4.60
openmim==0.1.5
openpyxl==3.0.9
opt-einsum==3.3.0
ordered-set==4.0.2
orjson==3.9.10
oscrypto==1.3.0
p-tqdm==1.4.0
packaging==23.0
paddle-bfloat==0.1.7
paddleocr==2.5.0.3
paddlepaddle==2.4.2
paddlepaddle-gpu==2.5.1
pandas==1.1.4
pandocfilters==1.5.0
paramiko==2.6.0
parso==0.8.3
pathos==0.3.0
pathspec==0.11.1
pexpect==4.6.0
pickleshare==0.7.5
Pillow==9.5.0
pip-tools==7.3.0
platformdirs==3.11.0
plotly==5.10.0
pluggy==1.0.0
ply==3.11
Polygon3==3.0.9.1
portalocker==2.3.2
pox==0.3.2
ppft==1.7.6.6
pre-commit==2.16.0
prefetch-generator==1.0.3
premailer==3.10.0
pretrainedmodels==0.7.4
prettytable==3.0.0
prometheus-client==0.12.0
prompt-toolkit==3.0.24
protobuf==3.20.3
psutil==5.9.6
ptyprocess==0.7.0
py==1.11.0
py-cpuinfo==8.0.0
py-machineid==0.3.0
py3nvml==0.2.7
pyasn1==0.4.8
pyasn1-modules==0.2.8
pybind11==2.9.0
pycairo==1.25.1
pyclipper==1.3.0.post2
pycocotools==2.0.6
pycodestyle==2.7.0
pycparser==2.21
pycryptodome==3.12.0
pycuda==2022.2.2
pycups==1.9.73
pydantic==1.10.9
pyDeprecate==0.3.1
pydot==1.4.2
pydub==0.25.1
pydyf==0.6.0
pyflakes==2.3.1
Pygments==2.15.1
PyGObject==3.36.0
pygtrie==2.5.0
pyHanko==0.20.1
pyhanko-certvalidator==0.24.1
PyJWT==1.7.1
pylabel==0.1.40
pymacaroons==0.13.0
PyNaCl==1.3.0
pyparsing==2.4.5
pypdf==3.17.0
pypdfium2==3.21.1
pyphen==0.14.0
pypng==0.20220715.0
pyproject_hooks==1.0.0
PyQt5==5.15.9
PyQt5-Qt5==5.15.2
PyQt5-sip==12.12.0
pyquaternion==0.9.9
pyRFC3339==1.1
pyrsistent==0.18.0
PySocks==1.7.1
pystopwatch2 @ git+https://github.com/ildoonet/pystopwatch2.git@64ecd49a2a164b665f44c54d7015b0f7d8497b7e
pytest==7.1.2
pytest-benchmark==3.4.1
pytest-cov==3.0.0
pytest-runner==6.0.0
python-apt==2.0.1+ubuntu0.20.4.1
python-bidi==0.4.2
python-dateutil==2.8.2
python-debian==0.1.36+ubuntu1.1
python-doctr==0.6.0
python-Levenshtein==0.12.2
python-multipart==0.0.6
pytools==2023.1
pytorch-lightning==2.0.4
pytorch-quantization @ file:///media/user123/PortableSSD/yolov7%2Byolov5/TensorRT/tools/pytorch-quantization
PyTurboJPEG==1.7.0
pytz==2022.7.1
pyunpack==0.3
PyWavelets==1.2.0
pyxdg==0.26
PyYAML==6.0
pyzmq==22.3.0
qrcode==7.4.2
qtconsole==5.2.2
QtPy==2.3.1
qudida==0.0.4
rapidfuzz==1.9.1
ratelim==0.1.6
ray==2.7.1
ray-lightning @ git+https://github.com/ray-project/ray_lightning@299a776e4348050c477cbb4ecf958fb03ed64f26
redis==4.3.4
regex==2023.3.23
reportlab==4.0.7
requests==2.28.2
requests-oauthlib==1.3.0
requests-unixsocket==0.2.0
rich==13.4.2
rlp==3.0.0
rlPyCairo==0.3.0
rsa==4.8
s-tui==1.0.0b3
s3transfer==0.7.0
sacrebleu==2.0.0
sacremoses==0.0.46
safetensors==0.4.0
scikit-image==0.19.1
scikit-learn==1.3.1
scipy==1.10.1
screen-resolution-extra==0.0.0
seaborn==0.11.0
SecretStorage==2.3.1
segment-anything @ git+https://github.com/facebookresearch/segment-anything.git@6fdee8f2727f4506cfbbe553e23b895e27956588
semantic-version==2.10.0
Send2Trash==1.8.0
sentry-sdk==1.25.1
setuptools-scm==6.3.2
Shapely==1.8.5.post1
shellcheck-py==0.8.0.3
simplejson==3.16.0
simplification==0.5.19
six==1.16.0
sklearn==0.0
smmap==5.0.1
sng4onnx==1.0.1
sniffio==1.3.0
snowballstemmer==2.2.0
sortedcontainers==2.4.0
sounddevice==0.4.6
soupsieve==2.3.2.post1
sparsezoo==1.5.1
Sphinx==4.0.3
sphinx-glpi-theme==0.4.1
sphinx-rtd-theme==1.3.0
sphinxcontrib-applehelp==1.0.4
sphinxcontrib-devhelp==1.0.2
sphinxcontrib-htmlhelp==2.0.1
sphinxcontrib-jquery==4.1
sphinxcontrib-jsmath==1.0.1
sphinxcontrib-qthelp==1.0.3
sphinxcontrib-serializinghtml==1.1.5
SQLAlchemy==1.4.26
ssh-import-id==5.10
starlette==0.27.0
stringcase==1.2.0
suffix-tree==0.0.7
suffix-trees==0.3.0
super-gradients==3.4.0
svglib==1.5.1
sympy==1.11.1
systemd-python==234
tabulate==0.8.9
tenacity==8.1.0
tensorboard==2.13.0
tensorboard-data-server==0.7.1
tensorboard-plugin-wit==1.8.0
tensorboardX==2.6.2.2
tensorflow-addons==0.20.0
tensorflow-estimator==2.7.0
tensorflow-gpu==2.7.0
tensorflow-io-gcs-filesystem==0.23.1
tensorrt==8.6.1.post1
tensorrt-bindings==8.6.1
tensorrt-dispatch==8.6.1
tensorrt-dispatch-bindings==8.6.1
tensorrt-dispatch-libs==8.6.1
tensorrt-lean==8.6.1
tensorrt-lean-bindings==8.6.1
tensorrt-lean-libs==8.6.1
tensorrt-libs==8.6.1
termcolor==1.1.0
terminado==0.12.1
terminaltables==3.1.10
testpath==0.5.0
texttable==1.7.0
tf2onnx==1.14.0
tflite-support==0.4.3
theconf @ git+https://github.com/wbaek/theconf@83bd68045c9a09e6ba88646d075fe4b0f5403bba
thop==0.1.1.post2209072238
threadpoolctl==3.0.0
tifffile==2021.11.2
tiffile==2018.10.18
timm==0.9.7
tinycss2==1.2.1
tkintertable==1.3.3
tokenizers==0.10.3
toml==0.10.2
tomli==1.2.3
toolz==0.12.0
torch==2.0.1
torch-tensorrt==1.4.0
torchaudio==2.0.2
torchcontrib==0.0.2
torchdata==0.6.1
torchmetrics==0.8.0
torchtext==0.15.2
torchvision==0.15.2
tornado==6.1
tqdm==4.65.0
traitlets==5.1.1
transformers==4.15.0
transliterate==1.10.2
trdg==1.8.0
treelib==1.6.1
trie==2.1.0
triton==2.0.0
typeguard==2.13.3
typing==3.7.4.3
typing_extensions==4.5.0
tzdata==2023.3
tzlocal==5.2
ubelt==0.10.2
ubuntu-advantage-tools==8001
ubuntu-drivers-common==0.0.0
uc-micro-py==1.0.2
ufw==0.36
ultralytics==8.0.205
unattended-upgrades==0.1
Unidecode==1.3.6
uritools==4.0.2
urllib3==1.26.15
urwid==2.0.1
usb-creator==0.3.7
uvicorn==0.23.2
validators==0.18.2
virtualenv==20.11.2
visualdl==2.2.2
wadllib==1.3.3
warmup-scheduler @ git+https://github.com/ildoonet/pytorch-gradual-warmup-lr.git@6b5e8953a80aef5b324104dc0c2e9b8c34d622bd
wcwidth==0.2.5
weasyprint==59.0
webencodings==0.5.1
websockets==11.0.3
Werkzeug==2.0.2
widgetsnbextension==3.5.2
wikipedia==1.4.0
winregistry==1.1.1
wrapt==1.13.3
xdoctest==1.0.1
xhtml2pdf==0.2.12
xkit==0.0.0
XlsxWriter==3.0.2
xmltodict==0.12.0
xtcocotools==1.13
yacs==0.1.8
yapf==0.32.0
yarl==1.7.2
zipp==3.15.0
zopfli==0.2.2

Thank you for the help. I would be very grateful if you could help me get this to work. Thank you.

[BloodAxe]

It looks like the minimal required version of onnxsim that we have 0.3.6 is too low to handle dynamic axes. For me it looks like onnx-simplifier>=0.4.3 fixes the issue. Can you please pip install -U onnx-simplifier==0.4.3 and try again? I beleive it should work for your case too.

[siddagra]

Fixed it thanks but the speed is low.