cpubone_b2pt5_dwnorm.timm_r256_in1k

Model card for cpubone_b2pt5_dwnorm.timm_r256_in1k

A CPUBone image classification model. CPUBone is designed for efficient CPU inference by balancing a low operation count with hardware-efficient execution (high MACs per second). It combines grouped MBConv variants, reduced convolution kernels, and LowFormer attention in its final two stages. This checkpoint was trained on ImageNet-1k in timm at 256 x 256 resolution.

Model Notes

• b2pt5 is an intermediate scale from the original CPUBone configs, between the paper B2 and B3 models. Its dwnorm local MBConv branches normalize the depthwise and projection convolutions, while leaving the expansion convolution unnormalized.
• The default preprocessing is encoded in the pretrained configuration: bicubic resize, ImageNet mean and standard deviation, and a center crop with crop_pct=0.95.
• The model can be used for ImageNet-1k classification, image embeddings, or multi-scale feature-map extraction with features_only=True.
• CPU latency depends on the target hardware, inference runtime, export path, and batch size. See the paper for device-specific batch-size-one measurements and methodology.

Model Details

• Model Type: Image Classification / Feature Encoder
• Model Stats:
  • Params (M): 30.4
  • GMACs: 2.5
  • Activations (M): 8.1
  • Image size: 256 x 256
• Original: https://github.com/altair199797/CPUBone
• License: Apache 2.0
• Dataset: ImageNet-1k
• Papers:
  • CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities: https://arxiv.org/abs/2603.26425
  • PyTorch Image Models: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Classification

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('cpubone_b2pt5_dwnorm.timm_r256_in1k', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Feature Map Extraction

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'cpubone_b2pt5_dwnorm.timm_r256_in1k',
    pretrained=True,
    features_only=True,
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

for o in output:
    # print shape of each feature map in output
    # e.g.:
    #  torch.Size([1, 48, 64, 64])
    #  torch.Size([1, 96, 32, 32])
    #  torch.Size([1, 192, 16, 16])
    #  torch.Size([1, 384, 8, 8])

    print(o.shape)

Image Embeddings

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'cpubone_b2pt5_dwnorm.timm_r256_in1k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 384, 8, 8) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor

Model Comparison

ImageNet-1k validation accuracy in FP32 with bicubic interpolation and a centered crop (crop_pct=0.95). Values are Top-1 / Top-5 percentages; only input resolution changes between columns.

Citation

@inproceedings{nottebaum2026cpubone,
  title={CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities},
  author={Nottebaum, Moritz and Dunnhofer, Matteo and Micheloni, Christian},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2026}
}

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}