metadata
library_name: lucid
license: apache-2.0
tags:
- image-classification
- convnext
- lucid
datasets:
- imagenet-22k
- imagenet-1k
pipeline_tag: image-classification
model-index:
- name: convnext-xlarge
results:
- task:
type: image-classification
dataset:
name: ImageNet-1k
type: imagenet-1k
metrics:
- type: acc@1
value: 87
- type: acc@5
value: 98.2
ConvNeXt-XLarge
Liu et al., 2022 — A ConvNet for the 2020s (arXiv:2201.03545)
Lucid port of timm/convnext_xlarge.fb_in22k_ft_in1k,
converted to Lucid-native safetensors.
Available weights
| Tag | acc@1 | acc@5 | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|---|
FB_IN22K_FT_IN1K (default) |
87.0 | 98.2 | 350.2M | — | 1335.93 MB | timm |
Usage
import lucid.models as models
from lucid.models.weights import ConvNeXtXLargeWeights
# default tag
model = models.convnext_xlarge_cls(pretrained=True)
# explicit tag (enum or string)
model = models.convnext_xlarge_cls(weights=ConvNeXtXLargeWeights.FB_IN22K_FT_IN1K)
model = models.convnext_xlarge_cls(pretrained="FB_IN22K_FT_IN1K")
# preprocessing travels with the weights
weights = ConvNeXtXLargeWeights.FB_IN22K_FT_IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits
Conversion
Converted from timm/convnext_xlarge.fb_in22k_ft_in1k via
python -m tools.convert_weights convnext_xlarge --tag FB_IN22K_FT_IN1K.
Key mapping + numerical parity verified against the source.
License
apache-2.0 — inherited from the original weights.
Citation
@inproceedings{liu2022convnet,
title={A ConvNet for the 2020s},
author={Liu, Zhuang and Mao, Hanzi and Wu, Chao-Yuan and Feichtenhofer, Christoph and Darrell, Trevor and Xie, Saining},
booktitle={CVPR}, year={2022}
}