Model card for nextvit_small.bd_ssld_6m_in1k#
A Next-ViT image classification model. Trained by paper authors on an unknown 6M sample dataset and ImageNet-1k using SSLD distillation.
Model Details#
Model Type: Image classification / feature backboneModel Stats: Params (M): 31.8 GMACs: 5.8 Activations (M): 17.6 Image size: 224 x 224 Pretrain Dataset: Unknown-6MDataset: ImageNet-1kPapers: Original: https://github.com/bytedance/Next-ViT 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('nextvit_small.bd_ssld_6m_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)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(
'nextvit_small.bd_ssld_6m_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, 96, 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(
'nextvit_small.bd_ssld_6m_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 tensorModel Comparison#
By Top-1#
model top1 top1_err top5 top5_err param_count nextvit_large.bd_ssld_6m_in1k_384 86.542 13.458 98.142 1.858 57.87 nextvit_base.bd_ssld_6m_in1k_384 86.352 13.648 98.04 1.96 44.82 nextvit_small.bd_ssld_6m_in1k_384 85.964 14.036 97.908 2.092 31.76 nextvit_large.bd_ssld_6m_in1k 85.48 14.52 97.696 2.304 57.87 nextvit_base.bd_ssld_6m_in1k 85.186 14.814 97.59 2.41 44.82 nextvit_large.bd_in1k_384 84.924 15.076 97.294 2.706 57.87 nextvit_small.bd_ssld_6m_in1k 84.862 15.138 97.382 2.618 31.76 nextvit_base.bd_in1k_384 84.706 15.294 97.224 2.776 44.82 nextvit_small.bd_in1k_384 84.022 15.978 96.99 3.01 31.76 nextvit_large.bd_in1k 83.626 16.374 96.694 3.306 57.87 nextvit_base.bd_in1k 83.472 16.528 96.656 3.344 44.82 nextvit_small.bd_in1k 82.61 17.39 96.226 3.774 31.76
Citation#
@article{li2022next,
title={Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios},
author={Li, Jiashi and Xia, Xin and Li, Wei and Li, Huixia and Wang, Xing and Xiao, Xuefeng and Wang, Rui and Zheng, Min and Pan, Xin},
journal={arXiv preprint arXiv:2207.05501},
year={2022}
}
onnx-community