how to inference using onnx for object detection?

[MareArts]

💡 Your Question

where can I find or how to do inferencing using onnx?

There are example how to conver to onnx from pth file.

# Convert model to onnx
torch.onnx.export(model, dummy_input,  "yolo_nas_m.onnx")

but how do inferencing using onnx file?

#load onnx model
import onnxruntime as ort
providers = (["CUDAExecutionProvider", "CPUExecutionProvider"]  if use_gpu else ["CPUExecutionProvider"] )  
net = ort.InferenceSession(path, providers=providers)  # load session

net_input = net.get_inputs()[0]  # get input info
input_name = net_input.name
input_shape = net_input.shape
output_names = [x.name for x in net.get_outputs()]  # get output info

# input_name: 'input.1'
# input_shape: [1, 3, 640, 640]
# output_names: ['1698', '1690']
# 1698: type: float32[1,8400,4]
# 1690: type: float32[1,8400,2]

#fowarding how??

Above is code for onnx loading. But how to forward image and get bbox, and class with confidence given the onnx output?

and one more question, how to input image data to predict fuction instead of image path? This is example code in document.

# Note that currently only YoloX, PPYoloE and YOLO-NAS are supported.
model = models.get(Models.YOLO_NAS_L, pretrained_weights="coco")

IMAGES = [
    "../../../../documentation/source/images/examples/countryside.jpg",
    "../../../../documentation/source/images/examples/street_busy.jpg",
    "https://cdn-attachments.timesofmalta.com/cc1eceadde40d2940bc5dd20692901371622153217-1301777007-4d978a6f-620x348.jpg",
]

predictions = model.predict(IMAGES)

But my concern is how to feed opencv mat data or pil image data

image = cv2.imread(img_path)  # read image
predictions = model.predict( ?? how to feed image data instead of path ?? )

Thank you for advance.

Versions

Collecting environment information... PyTorch version: 1.11.0+cu113 Is debug build: False CUDA used to build PyTorch: 11.3 ROCM used to build PyTorch: N/A

OS: Ubuntu 20.04.6 LTS (x86_64) GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0 Clang version: Could not collect CMake version: version 3.26.4 Libc version: glibc-2.31

Python version: 3.8.17 (default, Jul 5 2023, 21:04:15) [GCC 11.2.0] (64-bit runtime) Python platform: Linux-5.15.0-78-generic-x86_64-with-glibc2.17 Is CUDA available: True CUDA runtime version: 11.4.120 CUDA_MODULE_LOADING set to: GPU models and configuration: GPU 0: NVIDIA Graphics Device Nvidia driver version: 520.61.05 cuDNN version: Probably one of the following: /usr/lib/x86_64-linux-gnu/libcudnn.so.7.6.5 /usr/local/cuda-11.4/targets/x86_64-linux/lib/libcudnn.so.8.8.0 /usr/local/cuda-11.4/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8.8.0 /usr/local/cuda-11.4/targets/x86_64-linux/lib/libcudnn_adv_train.so.8.8.0 /usr/local/cuda-11.4/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8.8.0 /usr/local/cuda-11.4/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8.8.0 /usr/local/cuda-11.4/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8.8.0 /usr/local/cuda-11.4/targets/x86_64-linux/lib/libcudnn_ops_train.so.8.8.0 /usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn.so.8 /usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8 /usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_adv_train.so.8 /usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8 /usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8 /usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8 /usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudnn_ops_train.so.8 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: 46 bits physical, 48 bits virtual CPU(s): 16 On-line CPU(s) list: 0-15 Thread(s) per core: 2 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Core(TM) i7-9800X CPU @ 3.80GHz Stepping: 4 CPU MHz: 3800.000 CPU max MHz: 4500.0000 CPU min MHz: 1200.0000 BogoMIPS: 7599.80 Virtualization: VT-x L1d cache: 256 KiB L1i cache: 256 KiB L2 cache: 8 MiB L3 cache: 16.5 MiB NUMA node0 CPU(s): 0-15 Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS 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; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req md_clear flush_l1d arch_capabilities

Versions of relevant libraries: [pip3] numpy==1.23.0 [pip3] pytorch-lightning==2.0.4 [pip3] pytorch-quantization==2.1.2 [pip3] torch==1.11.0+cu113 [pip3] torchaudio==0.11.0+cu113 [pip3] torchmetrics==0.8.0 [pip3] torchvision==0.12.0+cu113 [pip3] triton==2.0.0 [conda] numpy 1.23.0 pypi_0 pypi [conda] pytorch-quantization 2.1.2 pypi_0 pypi [conda] torch 1.11.0+cu113 pypi_0 pypi [conda] torchaudio 0.11.0+cu113 pypi_0 pypi [conda] torchmetrics 0.8.0 pypi_0 pypi [conda] torchvision 0.12.0+cu113 pypi_0 pypi

[BloodAxe]

We are currently working on adding the user-friendly onnx export support with end-to-end inference using ORT. Stay tuned for the next release.

[PrajwalCogniac]

@BloodAxe Thanks a lot for this feature ... It is really essential ! As this has been a huge bottleneck. Also what is the approx expected timeline for the next release ?

[BloodAxe]

This was recently merged to master branch and will land in 3.2.0 release somewhere next week (hopefully). This is how it would look like: https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/models_export.md