# ConvNeXt

**Category:** CNN · **Code:**
[`timm/models/convnext.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/convnext.py) ·
**Architectures:** 31 · **Pretrained weights:** 101 (61 with ImageNet-1k results)

ConvNeXt is a pure convolutional network that adopts design choices from vision transformers, such as large depthwise
kernels, inverted bottlenecks and LayerNorm. ConvNeXt-V2 adds Global Response Normalization (GRN) and is pretrained as a
fully convolutional masked autoencoder (FCMAE).

## Papers

* [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545)
* [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://arxiv.org/abs/2301.00808)
* [Reproducible scaling laws for contrastive language-image learning](https://arxiv.org/abs/2212.07143)
* [DINOv3](https://arxiv.org/abs/2508.10104)
* [Efficient Universal Perception Encoder](https://arxiv.org/abs/2603.22387)

## Usage

See the [Quickstart](../quickstart) for loading pretrained weights, image preprocessing and fine-tuning, and [Feature
Extraction](../feature_extraction) for using the models as backbones.

```py
>>> import timm
>>> model = timm.create_model('convnext_tiny.in12k_ft_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `ConvNeXt` |
|---|---|
| [`features_only=True` feature maps](../model_api#intermediate-features) | ✓ (strides 4, 8, 16, 32) |
| [`forward_intermediates()`](../model_api#intermediate-features) | ✓ |
| [`prune_intermediate_layers()`](../model_api#intermediate-features) | ✓ |
| [Any input size, no changes needed](../model_api#input-size) | ✓ |
| [`set_input_size()`](../model_api#input-size) | – |
| [`dynamic_img_size=True`](../model_api#input-size) | – |
| [`set_grad_checkpointing()`](../model_api#training-hooks) | ✓ |
| [Layer-wise LR decay (`group_matcher()`)](../model_api#training-hooks) | ✓ |
| [`reset_classifier()`](../model_api#classifier) | ✓ |

✓ supported, ✓ (square) works for square sizes only, ✗ not supported, – not needed (the model already accepts any input
size). Checked by running each feature on a randomly initialized model (`ConvNeXt` with `convnext_zepto_rms` at 224),
other architectures of the same class are expected to behave the same. See the [Model API](../model_api) page for
details.

## Architectures

| Architecture | Params (M) | GMACs | Input size | Pretrained weights |
|---|---:|---:|---:|---:|
| `convnext_atto` | 3.70 | 0.55 | 224 | 1 |
| `convnext_atto_ols` | 3.70 | 0.58 | 224 | 1 |
| `convnext_atto_rms` | 3.69 | 0.55 | 224 | 0 |
| `convnext_base` | 88.59 | 15.38 | 224 | 16 |
| `convnext_femto` | 5.22 | 0.79 | 224 | 1 |
| `convnext_femto_ols` | 5.23 | 0.82 | 224 | 1 |
| `convnext_large` | 197.77 | 34.40 | 224 | 5 |
| `convnext_large_mlp` | 200.13 | 70.21 | 320 | 10 |
| `convnext_nano` | 15.59 | 2.46 | 224 | 6 |
| `convnext_nano_ols` | 15.65 | 2.65 | 224 | 1 |
| `convnext_pico` | 9.05 | 1.37 | 224 | 1 |
| `convnext_pico_ols` | 9.06 | 1.43 | 224 | 1 |
| `convnext_small` | 50.22 | 8.71 | 224 | 9 |
| `convnext_tiny` | 28.59 | 4.47 | 224 | 9 |
| `convnext_tiny_hnf` | 28.59 | 4.47 | 224 | 1 |
| `convnext_xlarge` | 350.20 | 60.98 | 224 | 3 |
| `convnext_xxlarge` | 846.47 | 198.09 | 256 | 4 |
| `convnext_zepto_rms` | 2.16 | 0.30 | 224 | 1 |
| `convnext_zepto_rms_ols` | 2.16 | 0.34 | 224 | 1 |
| `convnextv2_atto` | 3.71 | 0.55 | 224 | 2 |
| `convnextv2_base` | 88.72 | 15.38 | 224 | 4 |
| `convnextv2_femto` | 5.23 | 0.79 | 224 | 2 |
| `convnextv2_huge` | 660.29 | 337.96 | 384 | 4 |
| `convnextv2_large` | 197.96 | 34.40 | 224 | 4 |
| `convnextv2_nano` | 15.62 | 2.46 | 224 | 4 |
| `convnextv2_pico` | 9.07 | 1.37 | 224 | 2 |
| `convnextv2_small` | 50.32 | 8.71 | 224 | 0 |
| `convnextv2_tiny` | 28.64 | 4.47 | 224 | 4 |
| `test_convnext` | 0.27 | 0.03 | 160 | 1 |
| `test_convnext2` | 0.48 | 0.05 | 160 | 1 |
| `test_convnext3` | 0.47 | 0.05 | 160 | 1 |

GMACs and parameter counts are for the default input size and classifier of each architecture, from the [benchmark
results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

## Pretrained weights

Top-1 is ImageNet-1k validation accuracy from
[`results-imagenet.csv`](https://github.com/huggingface/pytorch-image-models/blob/main/results/results-imagenet.csv) at
the listed eval size, - if the weight has no ImageNet-1k result (e.g. pretraining or image-text weights). Classes is the
size of the pretrained classifier, none for weights without one.

Weights are grouped by source: the paper or origin given in the pretrained config, else a Hub organization other than
`timm`, else the first part of the pretrained tag (`architecture.tag`). Sources with a single weight are listed under
other.

### ConvNeXt V2

Pretrained configs reference [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked
Autoencoders](https://arxiv.org/abs/2301.00808).

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnextv2_atto.fcmae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_atto.fcmae) |
| `convnextv2_atto.fcmae_ft_in1k` | 224 (test 288) | 77.794 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_atto.fcmae_ft_in1k) |
| `convnextv2_base.fcmae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_base.fcmae) |
| `convnextv2_base.fcmae_ft_in1k` | 224 (test 288) | 85.490 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in1k) |
| `convnextv2_base.fcmae_ft_in22k_in1k` | 224 (test 288) | 86.994 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k) |
| `convnextv2_base.fcmae_ft_in22k_in1k_384` | 384 | 87.638 | 384 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k_384) |
| `convnextv2_femto.fcmae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_femto.fcmae) |
| `convnextv2_femto.fcmae_ft_in1k` | 224 (test 288) | 79.342 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_femto.fcmae_ft_in1k) |
| `convnextv2_huge.fcmae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_huge.fcmae) |
| `convnextv2_huge.fcmae_ft_in1k` | 224 (test 288) | 86.618 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in1k) |
| `convnextv2_huge.fcmae_ft_in22k_in1k_384` | 384 | 88.666 | 384 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_384) |
| `convnextv2_huge.fcmae_ft_in22k_in1k_512` | 512 | 88.860 | 512 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_512) |
| `convnextv2_large.fcmae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_large.fcmae) |
| `convnextv2_large.fcmae_ft_in1k` | 224 (test 288) | 86.132 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in1k) |
| `convnextv2_large.fcmae_ft_in22k_in1k` | 224 (test 288) | 87.494 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k) |
| `convnextv2_large.fcmae_ft_in22k_in1k_384` | 384 | 88.180 | 384 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k_384) |
| `convnextv2_nano.fcmae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_nano.fcmae) |
| `convnextv2_nano.fcmae_ft_in1k` | 224 (test 288) | 82.490 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in1k) |
| `convnextv2_nano.fcmae_ft_in22k_in1k` | 224 (test 288) | 82.666 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k) |
| `convnextv2_nano.fcmae_ft_in22k_in1k_384` | 384 | 83.366 | 384 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k_384) |
| `convnextv2_pico.fcmae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_pico.fcmae) |
| `convnextv2_pico.fcmae_ft_in1k` | 224 (test 288) | 81.062 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_pico.fcmae_ft_in1k) |
| `convnextv2_tiny.fcmae` | 224 | - | - | none | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_tiny.fcmae) |
| `convnextv2_tiny.fcmae_ft_in1k` | 224 (test 288) | 83.478 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in1k) |
| `convnextv2_tiny.fcmae_ft_in22k_in1k` | 224 (test 288) | 84.428 | 288 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k) |
| `convnextv2_tiny.fcmae_ft_in22k_in1k_384` | 384 | 85.098 | 384 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k_384) |

### `clip` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnext_base.clip_laion2b` | 256 | - | - | 640 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laion2b) |
| `convnext_base.clip_laion2b_augreg` | 256 | - | - | 640 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg) |
| `convnext_base.clip_laion2b_augreg_ft_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k) |
| `convnext_base.clip_laion2b_augreg_ft_in12k_in1k` | 256 | 86.378 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k) |
| `convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384` | 384 | 87.144 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384) |
| `convnext_base.clip_laion2b_augreg_ft_in1k` | 256 | 86.184 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in1k) |
| `convnext_base.clip_laiona` | 256 | - | - | 640 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laiona) |
| `convnext_base.clip_laiona_320` | 320 | - | - | 640 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laiona_320) |
| `convnext_base.clip_laiona_augreg_320` | 320 | - | - | 640 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laiona_augreg_320) |
| `convnext_base.clip_laiona_augreg_ft_in1k_384` | 384 | 86.490 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.clip_laiona_augreg_ft_in1k_384) |
| `convnext_large_mlp.clip_laion2b_augreg` | 256 | - | - | 768 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg) |
| `convnext_large_mlp.clip_laion2b_augreg_ft_in12k_384` | 384 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in12k_384) |
| `convnext_large_mlp.clip_laion2b_augreg_ft_in1k` | 256 | 87.344 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in1k) |
| `convnext_large_mlp.clip_laion2b_augreg_ft_in1k_384` | 384 | 87.890 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in1k_384) |
| `convnext_large_mlp.clip_laion2b_ft_320` | 320 | - | - | 768 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_ft_320) |
| `convnext_large_mlp.clip_laion2b_ft_soup_320` | 320 | - | - | 768 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_ft_soup_320) |
| `convnext_large_mlp.clip_laion2b_soup_ft_in12k_320` | 320 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_320) |
| `convnext_large_mlp.clip_laion2b_soup_ft_in12k_384` | 384 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_384) |
| `convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320` | 320 | 87.970 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320) |
| `convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384` | 384 | 88.334 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384) |
| `convnext_xxlarge.clip_laion2b_rewind` | 256 | - | - | 1024 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_rewind) |
| `convnext_xxlarge.clip_laion2b_soup` | 256 | - | - | 1024 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_soup) |
| `convnext_xxlarge.clip_laion2b_soup_ft_in12k` | 256 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_soup_ft_in12k) |
| `convnext_xxlarge.clip_laion2b_soup_ft_in1k` | 256 | 88.622 | 256 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k) |

### `fb` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnext_base.fb_in1k` | 224 (test 288) | 84.466 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.fb_in1k) |
| `convnext_base.fb_in22k` | 224 | - | - | 21841 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.fb_in22k) |
| `convnext_base.fb_in22k_ft_in1k` | 224 (test 288) | 86.302 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k) |
| `convnext_base.fb_in22k_ft_in1k_384` | 384 | 86.826 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k_384) |
| `convnext_large.fb_in1k` | 224 (test 288) | 84.862 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large.fb_in1k) |
| `convnext_large.fb_in22k` | 224 | - | - | 21841 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large.fb_in22k) |
| `convnext_large.fb_in22k_ft_in1k` | 224 (test 288) | 87.012 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k) |
| `convnext_large.fb_in22k_ft_in1k_384` | 384 | 87.456 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k_384) |
| `convnext_small.fb_in1k` | 224 (test 288) | 83.704 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_small.fb_in1k) |
| `convnext_small.fb_in22k` | 224 | - | - | 21841 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_small.fb_in22k) |
| `convnext_small.fb_in22k_ft_in1k` | 224 (test 288) | 85.276 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k) |
| `convnext_small.fb_in22k_ft_in1k_384` | 384 | 85.752 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k_384) |
| `convnext_tiny.fb_in1k` | 224 (test 288) | 82.694 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_tiny.fb_in1k) |
| `convnext_tiny.fb_in22k` | 224 | - | - | 21841 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_tiny.fb_in22k) |
| `convnext_tiny.fb_in22k_ft_in1k` | 224 (test 288) | 78.950 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k) |
| `convnext_tiny.fb_in22k_ft_in1k_384` | 384 | 84.098 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k_384) |
| `convnext_xlarge.fb_in22k` | 224 | - | - | 21841 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_xlarge.fb_in22k) |
| `convnext_xlarge.fb_in22k_ft_in1k` | 224 (test 288) | 87.378 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k) |
| `convnext_xlarge.fb_in22k_ft_in1k_384` | 384 | 87.764 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k_384) |

### `d1` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnext_femto.d1_in1k` | 224 (test 288) | 78.712 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_femto.d1_in1k) |
| `convnext_femto_ols.d1_in1k` | 224 (test 288) | 78.916 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_femto_ols.d1_in1k) |
| `convnext_pico.d1_in1k` | 224 (test 288) | 80.426 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_pico.d1_in1k) |
| `convnext_pico_ols.d1_in1k` | 224 (test 288) | 80.458 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_pico_ols.d1_in1k) |

### `dinov3` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnext_base.dinov3_lvd1689m` | 224 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/convnext_base.dinov3_lvd1689m) |
| `convnext_large.dinov3_lvd1689m` | 224 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/convnext_large.dinov3_lvd1689m) |
| `convnext_small.dinov3_lvd1689m` | 224 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/convnext_small.dinov3_lvd1689m) |
| `convnext_tiny.dinov3_lvd1689m` | 224 | - | - | none | dinov3-license | [timm](https://huggingface.co/timm/convnext_tiny.dinov3_lvd1689m) |

### `eupe` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnext_base.eupe_lvd1689m` | 256 | - | - | none | fair-noncommercial-research-license | [timm](https://huggingface.co/timm/convnext_base.eupe_lvd1689m) |
| `convnext_small.eupe_lvd1689m` | 256 | - | - | none | fair-noncommercial-research-license | [timm](https://huggingface.co/timm/convnext_small.eupe_lvd1689m) |
| `convnext_tiny.eupe_lvd1689m` | 256 | - | - | none | fair-noncommercial-research-license | [timm](https://huggingface.co/timm/convnext_tiny.eupe_lvd1689m) |

### `d1h` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnext_nano.d1h_in1k` | 224 (test 288) | 81.474 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_nano.d1h_in1k) |
| `convnext_nano_ols.d1h_in1k` | 224 (test 288) | 81.612 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_nano_ols.d1h_in1k) |

### `ra4` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnext_zepto_rms.ra4_e3600_r224_in1k` | 224 | 72.820 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_zepto_rms.ra4_e3600_r224_in1k) |
| `convnext_zepto_rms_ols.ra4_e3600_r224_in1k` | 224 | 73.234 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_zepto_rms_ols.ra4_e3600_r224_in1k) |

### Other

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convnext_atto.d2_in1k` | 224 (test 288) | 77.016 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_atto.d2_in1k) |
| `convnext_atto_ols.a2_in1k` | 224 (test 288) | 77.220 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_atto_ols.a2_in1k) |
| `convnext_nano.in12k` | 224 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_nano.in12k) |
| `convnext_nano.in12k_ft_in1k` | 224 (test 288) | 82.882 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_nano.in12k_ft_in1k) |
| `convnext_nano.r384_ad_in12k` | 384 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_nano.r384_ad_in12k) |
| `convnext_nano.r384_in12k` | 384 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_nano.r384_in12k) |
| `convnext_nano.r384_in12k_ft_in1k` | 384 | 83.334 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_nano.r384_in12k_ft_in1k) |
| `convnext_small.in12k` | 224 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_small.in12k) |
| `convnext_small.in12k_ft_in1k` | 224 (test 288) | 85.324 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_small.in12k_ft_in1k) |
| `convnext_small.in12k_ft_in1k_384` | 384 | 86.186 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_small.in12k_ft_in1k_384) |
| `convnext_tiny.in12k` | 224 | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_tiny.in12k) |
| `convnext_tiny.in12k_ft_in1k` | 224 (test 288) | 84.448 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k) |
| `convnext_tiny.in12k_ft_in1k_384` | 384 | 85.154 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k_384) |
| `convnext_tiny_hnf.a2h_in1k` | 224 (test 288) | 82.608 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/convnext_tiny_hnf.a2h_in1k) |
| `test_convnext.r160_in1k` | 160 | 47.774 | 160 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/test_convnext.r160_in1k) |
| `test_convnext2.r160_in1k` | 160 | 53.520 | 160 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/test_convnext2.r160_in1k) |
| `test_convnext3.r160_in1k` | 160 | 53.302 | 160 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/test_convnext3.r160_in1k) |

## Citation

```bibtex
@Article{liu2022convnet,
  author  = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
  title   = {A ConvNet for the 2020s},
  journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year    = {2022},
}

@article{Woo2023ConvNeXtV2,
  title={ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders},
  author={Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon and Saining Xie},
  year={2023},
  journal={arXiv preprint arXiv:2301.00808},
}
```