ResNet-152 v1.5 ImageNet-1k training
According to the model card, this is a ResNet-152 v1.5 model pre-trained on ImageNet-1k at 224x224 resolution.
Open Source Model Profile · microsoft
resnet-152
resnet-152 is a 60.34M-parameter ResNet image-classification model from microsoft. According to the model card, it is a v1.5 model pre-trained on ImageNet-1k at 224x224.
- Publisher
- microsoft
- Task
- image-classification
- Model type
- resnet
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
resnet-152 is published by microsoft as an image-classification model. The captured configuration identifies ResNetForImageClassification with model type resnet, and Safetensors metadata reports 60,344,232 parameters. According to the model card, it is a ResNet-152 v1.5 model pre-trained on ImageNet-1k at 224x224.
Recorded capabilities
Residual design and v1.5 change
According to the model card, ResNet uses residual learning with skip connections, and v1.5 places stride 2 in the 3x3 convolution rather than the first 1x1 convolution in downsampling blocks.
Documented Transformers classification workflow
According to the model card, the model classifies images into 1,000 ImageNet classes with AutoFeatureExtractor and ResNetForImageClassification, illustrated on a COCO 2017 example.
Paper and dataset association
Hub tags record dataset:imagenet-1k and arxiv:1512.03385, matching the card's reference to ImageNet-1k training and the He et al. residual-learning paper.
Use cases in the source record
- Raw image classification into 1,000 ImageNet classes using the documented AutoFeatureExtractor and ResNetForImageClassification workflow.
- Reference ResNet-152 v1.5 checkpoint for studying residual-network behavior at 224x224 ImageNet-1k scope.
Limitations and unknowns
- No evaluation results were extracted from this record beyond a publisher-cited v1.5 accuracy note.
- The card states it was written by the Hugging Face team because the releasing team did not provide one, so its descriptions are secondary documentation rather than publisher-authored claims.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: microsoft/resnet-152
Captured: Unknown. Processed: 2026-09-07T19:34:51.773885+00:00.
ResNet-152 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…
F001F002F003F004F005F006F007F009F010F011F012F013F014F015F016