MobileNetV4 pretrained weights
Collection
Weights for MobileNet-V4 pretrained in timm
•
17 items
•
Updated
•
17
Model card for mobilenetv4_hybrid_large.ix_e600_r384_in1k
A MobileNet-V4 image classification model. Trained on ImageNet-1k by Ross Wightman.
Trained with timm scripts using hyper-parameters inspired by the MobileNet-V4 paper with timm enhancements.
NOTE: So far, these are the only known MNV4 weights. Official weights for Tensorflow models are unreleased.
Model Details
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 37.8
- GMACs: 7.8
- Activations (M): 34.5
- Image size: train = 384 x 384, test = 448 x 448
- Dataset: ImageNet-1k
- Original: https://github.com/tensorflow/models/tree/master/official/vision
- Papers:
- MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518
- PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
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('mobilenetv4_hybrid_large.ix_e600_r384_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(
'mobilenetv4_hybrid_large.ix_e600_r384_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, 24, 192, 192])
# torch.Size([1, 48, 96, 96])
# torch.Size([1, 96, 48, 48])
# torch.Size([1, 192, 24, 24])
# torch.Size([1, 960, 12, 12])
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(
'mobilenetv4_hybrid_large.ix_e600_r384_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, 960, 12, 12) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
Model Comparison
By Top-1
Citation
@article{qin2024mobilenetv4,
title={MobileNetV4-Universal Models for the Mobile Ecosystem},
author={Qin, Danfeng and Leichner, Chas and Delakis, Manolis and Fornoni, Marco and Luo, Shixin and Yang, Fan and Wang, Weijun and Banbury, Colby and Ye, Chengxi and Akin, Berkin and others},
journal={arXiv preprint arXiv:2404.10518},
year={2024}
}
@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}}
}
- Downloads last month
- 3,969
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.