Tutorial Lengkap ONNX Runtime: High-Performance ML Inference

ONNX Runtime adalah inference engine performa tinggi untuk model machine learning dalam format ONNX. Library ini menyediakan akselerasi lintas platform untuk model yang dilatih di PyTorch, TensorFlow, dan framework lainnya, menjadikannya ideal untuk deployment ML production.

Mengapa ONNX Runtime?

• Cross-platform: Windows, Linux, macOS, mobile, edge
• Akselerasi hardware: Optimasi CPU, GPU, NPU
• Framework agnostic: Bekerja dengan model ONNX apapun
• Performa tinggi: Execution providers teroptimasi
• Production ready: API stabil dan dukungan enterprise

• Optimasi inference model
• Deployment lintas framework
• Inference edge dan mobile
• Cloud model serving
• Real-time predictions

Instalasi

# Versi CPU
pip install onnxruntime

Versi GPU (CUDA)
pip install onnxruntime-gpu

Untuk konversi model
pip install onnx torch transformers

Verify instalasi
python -c "import onnxruntime as ort; print(ort.version)"

Quick Start

1. Basic Inference

import onnxruntime as ort
import numpy as np

Load model
session = ort.InferenceSession("model.onnx")

Get info input/output
inputname = session.getinputs()[0].name
outputname = session.getoutputs()[0].name

print(f"Input: {inputname}")

print(f"Output: {outputname}")

Siapkan input
inputdata = np.random.randn(1, 3, 224, 224).astype(np.float32)


Jalankan inference
result = session.run([outputname], {inputname: inputdata})
print(f"Output shape: {result[0].shape}")

2. Multiple Inputs/Outputs

import onnxruntime as ort
import numpy as np

session = ort.InferenceSession("multiiomodel.onnx")

Get semua inputs
inputs = {inp.name: inp for inp in session.getinputs()}

for name, inp in inputs.items():
    print(f"Input: {name}, Shape: {inp.shape}, Type: {inp.type}")

Get semua outputs
outputs = [out.name for out in session.getoutputs()]

Siapkan inputs
inputfeed = {

    "inputids": np.array([[1, 2, 3, 4, 5]]).astype(np.int64),
    "attentionmask": np.array([[1, 1, 1, 1, 1]]).astype(np.int64)

}

Jalankan inference
results = session.run(outputs, inputfeed)
for name, result in zip(outputs, results):
    print(f"{name}: {result.shape}")

Konversi Model

1. PyTorch ke ONNX

import torch
import torch.nn as nn

Definisikan model
class SimpleModel(nn.Module):
    def init(self):
        super().init()
        self.fc1 = nn.Linear(10, 50)
        self.fc2 = nn.Linear(50, 2)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        return self.fc2(x)

model = SimpleModel()
model.eval()

Buat dummy input
dummyinput = torch.randn(1, 10)


Export ke ONNX
torch.onnx.export(
    model,
    dummyinput,
    "model.onnx",
    inputnames=["input"],

    outputnames=["output"],
    dynamicaxes={

        "input": {0: "batchsize"},
        "output": {0: "batchsize"}

    },
    opsetversion=14
)

2. TensorFlow ke ONNX

import tensorflow as tf
import tf2onnx

Load model TensorFlow
model = tf.keras.models.loadmodel("tfmodel")

Konversi ke ONNX
spec = (tf.TensorSpec((None, 224, 224, 3), tf.float32, name="input"),)

modelproto,  = tf2onnx.convert.fromkeras(

    model,
    inputsignature=spec,
    outputpath="model.onnx",

    opset=14
)

from transformers import AutoModelForSequenceClassification, AutoTokenizer
from optimum.onnxruntime import ORTModelForSequenceClassification

Load dan export
modelid = "distilbert-base-uncased-finetuned-sst-2-english"