---
title: resnet-18
canonical_url: "https://www.modelscope.cn/models/microsoft/resnet-18"
md_url: "https://www.modelscope.cn/models/microsoft/resnet-18.md"
repository: microsoft/resnet-18
last_updated: 2025-07-22
license: apache-2.0
pipeline_tag: image-classification
tasks:
  - image-classification
model_type:
  - resnet
architectures:
  - ResNetForImageClassification
parameters: 11.7M
tensor_type:
  - F32
  - I64
library_name:
  - pytorch
  - transformer
  - safetensors
  - tensorflow
frameworks:
  - pytorch
downloads: 582
stars: 3
tags:
  - vision
  - image-classification
---

# resnet-18

> resnet-18 - microsoft 在 ModelScope 开源的模型。ResNet model trained on imagenet-1k. It was introduced in the paper Deep Residual Learning for Image Recognition and first released in this repository.

microsoft/resnet-18 是 ModelScope 魔搭社区上的 11.7M 参数image-classification模型，采用 apache-2.0 许可。

- **Repository**: microsoft/resnet-18
- **License**: apache-2.0
- **Tasks**: image-classification
- **Parameters**: 11.7M
- **Tags**: vision, image-classification
- **Downloads**: 582
- **Stars**: 3
- **Last updated**: 2025-07-22

Source: https://www.modelscope.cn/models/microsoft/resnet-18

---

# ResNet

ResNet model trained on imagenet-1k. It was introduced in the paper [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) and first released in [this repository](https://github.com/KaimingHe/deep-residual-networks). 

Disclaimer: The team releasing ResNet did not write a model card for this model so this model card has been written by the Hugging Face team.

## Model description

ResNet introduced residual connections, they allow to train networks with an unseen number of layers (up to 1000). ResNet won the 2015 ILSVRC & COCO competition, one important milestone in deep computer vision.

![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/resnet_architecture.png)

## Intended uses & limitations

You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=resnet) to look for
fine-tuned versions on a task that interests you.

### How to use

Here is how to use this model:

```python
>>> from transformers import AutoImageProcessor, AutoModelForImageClassification
>>> import torch
>>> from datasets import load_dataset

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

>>> image_processor = AutoImageProcessor.from_pretrained("microsoft/resnet-18")
>>> model = AutoModelForImageClassification.from_pretrained("microsoft/resnet-18")

>>> inputs = image_processor(image, return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = logits.argmax(-1).item()
>>> print(model.config.id2label[predicted_label])
tiger cat
```



For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/resnet).