# ConvMixer

**Category:** CNN · **Code:**
[`timm/models/convmixer.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/convmixer.py) ·
**Architectures:** 3 · **Pretrained weights:** 3 (3 with ImageNet-1k results)

ConvMixer embeds the image as patches and keeps that resolution throughout, alternating depthwise convolutions (spatial
mixing) and pointwise convolutions (channel mixing).

## Papers

* [Patches Are All You Need?](https://arxiv.org/abs/2201.09792)

## 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('convmixer_1024_20_ks9_p14.in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `ConvMixer` |
|---|---|
| [`features_only=True` feature maps](../model_api#intermediate-features) | ✗ |
| [`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 (`ConvMixer` with `convmixer_768_32` 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 |
|---|---:|---:|---:|---:|
| `convmixer_768_32` | 21.11 | 19.55 | 224 | 1 |
| `convmixer_1024_20_ks9_p14` | 24.38 | 5.55 | 224 | 1 |
| `convmixer_1536_20` | 51.63 | 48.68 | 224 | 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.

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `convmixer_768_32.in1k` | 224 | 80.158 | 224 | 1000 | mit | [timm](https://huggingface.co/timm/convmixer_768_32.in1k) |
| `convmixer_1024_20_ks9_p14.in1k` | 224 | 76.944 | 224 | 1000 | mit | [timm](https://huggingface.co/timm/convmixer_1024_20_ks9_p14.in1k) |
| `convmixer_1536_20.in1k` | 224 | 81.382 | 224 | 1000 | mit | [timm](https://huggingface.co/timm/convmixer_1536_20.in1k) |