---
language:
- en
tags:
- ResNet-50
---

# ResNet-50

## Model Description

ResNet-50 model from [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) paper.

## Original implementation

Follow [this link](https://huggingface.co/microsoft/resnet-50) to see the original implementation.

# How to use

You can use the `base` model that returns `last_hidden_state`.
```python
from transformers import AutoFeatureExtractor
from onnxruntime import InferenceSession
from datasets import load_dataset

# load image
dataset = load_dataset("huggingface/cats-image")
image = dataset["test"]["image"][0]

# load model
feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-50")
session = InferenceSession("onnx/model.onnx")

# ONNX Runtime expects NumPy arrays as input
inputs = feature_extractor(image, return_tensors="np")
outputs = session.run(output_names=["last_hidden_state"], input_feed=dict(inputs))
```

Or you can use the model with classification head that returns `logits`.
```python
from transformers import AutoFeatureExtractor
from onnxruntime import InferenceSession
from datasets import load_dataset

# load image
dataset = load_dataset("huggingface/cats-image")
image = dataset["test"]["image"][0]

# load model
feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-50")
session = InferenceSession("onnx/model_cls.onnx")

# ONNX Runtime expects NumPy arrays as input
inputs = feature_extractor(image, return_tensors="np")
outputs = session.run(output_names=["logits"], input_feed=dict(inputs))
```