You can deploy this model and start earning money today!

timm/
gmlp_s16_224.ra3_in1k

Name: gmlp_s16_224.ra3_in1k
Availability: InStock

Views

No views yet

Model card for gmlp_s16_224.ra3_in1k

A gMLP image classification model. Trained on ImageNet-1k in timm by Ross Wightman.

Model Details

Model Type: Image classification / feature backbone
Model Stats:
- Params (M): 19.4
- GMACs: 4.4
- Activations (M): 15.1
- Image size: 224 x 224
Papers:
- Pay Attention to MLPs: https://arxiv.org/abs/2105.08050
Original: https://github.com/huggingface/pytorch-image-models
Dataset: ImageNet-1k

Model Usage

Image Classification

python

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('gmlp_s16_224.ra3_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)

Image Embeddings

python

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(
    'gmlp_s16_224.ra3_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, 196, 256) shaped tensor

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

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

Citation

bibtex

@inproceedings{Liu2021PayAT,
  title={Pay Attention to MLPs},
  author={Hanxiao Liu and Zihang Dai and David R. So and Quoc V. Le},
  booktitle={Neural Information Processing Systems},
  year={2021}
}