Model card for dpn92.mx_in1k#
A DPN (Dual-Path Net) image classification model. Trained on ImageNet-1k in MXNet by paper authors and ported to PyTorch by Ross Wightman.
Model Details#
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 37.7
- GMACs: 6.5
- Activations (M): 18.2
- Image size: 224 x 224
- Papers:
- Dataset: ImageNet-1k
- Original: https://github.com/cypw/DPNs
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('dpn92.mx_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(
'dpn92.mx_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, 64, 112, 112])
# torch.Size([1, 336, 56, 56])
# torch.Size([1, 704, 28, 28])
# torch.Size([1, 1552, 14, 14])
# torch.Size([1, 2688, 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(
'dpn92.mx_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, 2688, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
Citation#
@article{Chen2017,
title={Dual Path Networks},
author={Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, Jiashi Feng},
journal={arXiv preprint arXiv:1707.01629},
year={2017}
}
onnx-community