ImageNet-1K classification at 224x224
According to the model card, this ResNet-101 v1.5 checkpoint is pretrained on ImageNet-1K at 224x224 for raw image-classification use.
Open Source Model Profile · microsoft
resnet-101
Resnet-101 is a Microsoft ResNet image-classification model for ImageNet-1K at 224x224. According to the model card, it is the v1.5 variant with revised downsampling stride placement.
- Publisher
- microsoft
- Task
- image-classification
- Model type
- resnet
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Resnet-101 is published by Microsoft as an image-classification model. Captured configuration identifies ResNetForImageClassification with model type resnet, and the record lists an Apache-2.0 license. According to the model card, it is ResNet-101 v1.5 pretrained on ImageNet-1K at 224x224 resolution.
Recorded capabilities
Residual learning design
According to the model card, ResNet uses residual learning and skip connections to enable much deeper convolutional networks.
Transformers classification workflow
According to the model card, the model classifies images into ImageNet classes with AutoFeatureExtractor and ResNetForImageClassification.
Use cases in the source record
- Raw image classification into ImageNet classes, using the documented Transformers feature extractor and model classes.
Limitations and unknowns
- No parameter count was extracted from the current evidence.
- 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-101
Captured: Unknown. Processed: 2026-09-07T19:34:51.766055+00:00.
ResNet-101 v1.5 ResNet model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in the paper Deep Residual Learning for Image Recognition by He et al. 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 (Residual Network) is a convolutional neural network that democratized the concepts of residual learning and skip connections. This enables to train much deeper models. This is ResNet v1.5, which differs from the original model: in the bottleneck blocks which require downsampling, v1 has stride = 2 in th…
F001F002F003F004F005F006F007F009F010F011F012F014