A NFNet-Lite (Lightweight NFNet) image classification model. Trained in
timm
by Ross Wightman.
Normalization Free Networks are (pre-activation) ResNet-like models without any normalization layers. Instead of Batch Normalization or alternatives, they use Scaled Weight Standardization and specifically placed scalar gains in residual path and at non-linearities based on signal propagation analysis.
Lightweight NFNets are
timm
specific variants that reduce the SE and bottleneck ratio from 0.5 -> 0.25 (reducing widths) and use a smaller group size while maintaining the same depth. SiLU activations used instead of GELU.
Model Details
Model Type:
Image classification / feature backbone
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('nfnet_l0.ra2_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(
'nfnet_l0.ra2_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 1for o in output:
# print shape of each feature map in output# e.g.:# torch.Size([1, 64, 112, 112])# torch.Size([1, 256, 56, 56])# torch.Size([1, 512, 28, 28])# torch.Size([1, 1536, 14, 14])# torch.Size([1, 2304, 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(
'nfnet_l0.ra2_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, 2304, 7, 7) 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
@article{brock2021high,
author={Andrew Brock and Soham De and Samuel L. Smith and Karen Simonyan},
title={High-Performance Large-Scale Image Recognition Without Normalization},
journal={arXiv preprint arXiv:2102.06171},
year={2021}
}
@inproceedings{brock2021characterizing,
author={Andrew Brock and Soham De and Samuel L. Smith},
title={Characterizing signal propagation to close the performance gap in
unnormalized ResNets},
booktitle={9th International Conference on Learning Representations, {ICLR}},
year={2021}
}
@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}}
}
Runs of timm nfnet_l0.ra2_in1k on huggingface.co
90.3K
Total runs
0
24-hour runs
9.8K
3-day runs
23.4K
7-day runs
64.4K
30-day runs
More Information About nfnet_l0.ra2_in1k huggingface.co Model
nfnet_l0.ra2_in1k huggingface.co is an AI model on huggingface.co that provides nfnet_l0.ra2_in1k's model effect (), which can be used instantly with this timm nfnet_l0.ra2_in1k model. huggingface.co supports a free trial of the nfnet_l0.ra2_in1k model, and also provides paid use of the nfnet_l0.ra2_in1k. Support call nfnet_l0.ra2_in1k model through api, including Node.js, Python, http.
nfnet_l0.ra2_in1k huggingface.co is an online trial and call api platform, which integrates nfnet_l0.ra2_in1k's modeling effects, including api services, and provides a free online trial of nfnet_l0.ra2_in1k, you can try nfnet_l0.ra2_in1k online for free by clicking the link below.
timm nfnet_l0.ra2_in1k online free url in huggingface.co:
nfnet_l0.ra2_in1k is an open source model from GitHub that offers a free installation service, and any user can find nfnet_l0.ra2_in1k on GitHub to install. At the same time, huggingface.co provides the effect of nfnet_l0.ra2_in1k install, users can directly use nfnet_l0.ra2_in1k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.