Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · microsoft

resnet-18

Resnet-18 is an 11.70M-parameter Microsoft ResNet image classifier. According to the model card, it is trained on ImageNet-1K with residual connections.

Publisher
microsoft
Task
image-classification
Model type
resnet
License
apache-2.0
Library
transformers
Publication status
Approved for indexing

Model overview

Resnet-18 is published by Microsoft as an image-classification model. Captured configuration identifies ResNetForImageClassification with model type resnet, and Safetensors metadata reports 11,699,112 parameters. According to the model card, it is a ResNet model trained on ImageNet-1K and introduced with the Deep Residual Learning for Image Recognition paper.

Recorded capabilities

ImageNet-1K classification

According to the model card, this ResNet checkpoint is trained on ImageNet-1K for raw image-classification use.

Compact 11.70M-parameter ResNet

Captured configuration identifies ResNetForImageClassification, with Safetensors metadata reporting 11,699,112 parameters.

Transformers classification workflow

According to the model card, the model runs with AutoImageProcessor and AutoModelForImageClassification on Transformers inputs.

Use cases in the source record

  • Raw image classification into ImageNet classes, using the documented Transformers image processor and classification model.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • The model card notes it was written by the Hugging Face team, not the original ResNet release team.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: microsoft/resnet-18

Captured: Unknown. Processed: 2026-09-07T19:34:51.781762+00:00.

ResNet ResNet model trained on imagenet-1k. It was introduced in the paper Deep Residual Learning for Image Recognition and first released in this repository . 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. Intended uses & limitations You can use the raw model for image classification. See the model hub to look for…

F001F002F003F004F005F006F007F008F010F011F012F014F015