You can deploy this model and start earning money today!

ketiswp/
stm32ai-MobileNetV2-0.5-ImageNet-PyTorch-224-fp32-onnx

Name: stm32ai-MobileNetV2-0.5-ImageNet-PyTorch-224-fp32-onnx
Availability: InStock

Views

No views yet

STM32AI MobileNetV2 0.5 ImageNet PyTorch 224 FP32 ONNX

FP32 ONNX version of STM32AI MobileNetV2 0.5 ImageNet PyTorch 224 for image classification.

Model Files

File	Purpose	Format
`model.onnx`	Downloadable converted model	ONNX
`model.onnx`	Original model; no duplicate source file	ONNX
`graphs/netron.png`	ONNX graph visualization	PNG
`mlir/onnx.mlir`	ONNX-MLIR import result	MLIR text

Parameter Summary

Item	Value
Precision	FP32
ONNX file size	7.51 MiB
Initializer tensors	106
Stored initializer elements	1,959,408
External weight files	None
Original format	ONNX

Stored initializer elements includes weights, biases, quantization scales, zero-points, and other constant tensors. It is not a trainable-parameter count.

Original Model Inference

The original artifact is already ONNX, so the ONNX example below applies.

The upstream artifact is already ONNX. The model.onnx file above is the source-compatible downloadable model for this variant.

Converted ONNX Inference

pip install huggingface_hub numpy onnxruntime

python

import numpy as np
import onnxruntime as ort
from huggingface_hub import hf_hub_download

repo_id = "ketiswp/stm32ai-MobileNetV2-0.5-ImageNet-PyTorch-224-fp32-onnx"
model_path = hf_hub_download(repo_id=repo_id, filename="model.onnx")

options = ort.SessionOptions()
options.intra_op_num_threads = 1
options.inter_op_num_threads = 1
options.execution_mode = ort.ExecutionMode.ORT_SEQUENTIAL
options.graph_optimization_level = ort.GraphOptimizationLevel.ORT_ENABLE_ALL
session = ort.InferenceSession(
    model_path,
    sess_options=options,
    providers=["CPUExecutionProvider"],
)

dtype_by_ort_type = {
    "tensor(float)": np.float32,
    "tensor(double)": np.float64,
    "tensor(float16)": np.float16,
    "tensor(int64)": np.int64,
    "tensor(int32)": np.int32,
    "tensor(int16)": np.int16,
    "tensor(int8)": np.int8,
    "tensor(uint8)": np.uint8,
    "tensor(bool)": np.bool_,
}
feeds = {}
for item in session.get_inputs():
    shape = [dim if isinstance(dim, int) and dim > 0 else 1 for dim in item.shape]
    feeds[item.name] = np.zeros(shape, dtype=dtype_by_ort_type[item.type])

outputs = session.run(None, feeds)
print([(item.name, value.shape, str(value.dtype))
       for item, value in zip(session.get_outputs(), outputs)])

Paired Model

INT8 version

Source

Project Validation

FP32/quantized comparison, conversion results, and reproduction code

This repository also includes the Netron graph, ONNX Dialect MLIR, and static MLIR dependency graph for this model variant.