Model card for efficientvit_l3.r224_in1k
An EfficientViT (MIT) image classification model. Trained on ImageNet-1k by paper authors.
Model Details
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 246.0
- GMACs: 27.6
- Activations (M): 39.2
- Image size: 224 x 224
- Papers:
- EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction: https://arxiv.org/abs/2205.14756
- Original: https://github.com/mit-han-lab/efficientvit
- Dataset: ImageNet-1k
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('efficientvit_l3.r224_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(
'efficientvit_l3.r224_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, 128, 56, 56])
# torch.Size([1, 256, 28, 28])
# torch.Size([1, 512, 14, 14])
# torch.Size([1, 1024, 7, 7])
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(
'efficientvit_l3.r224_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, 1024, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
Citation
@article{cai2022efficientvit,
title={EfficientViT: Enhanced linear attention for high-resolution low-computation visual recognition},
author={Cai, Han and Gan, Chuang and Han, Song},
journal={arXiv preprint arXiv:2205.14756},
year={2022}
}
- Downloads last month
- 417
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.