You can deploy this model and start earning money today!

kerasformers/
convmixer_1024_20_ks9_p14_in1k

Name: convmixer_1024_20_ks9_p14_in1k
Rating: 2.5 (35 reviews)

timm/convmixer_1024_20_ks9_p14.in1k

finetune

mit

Views

No views yet

See our collection for all versions of ConvMixer.

Run ConvMixer with Keras 3: JAX, PyTorch, or TensorFlow

GitHub

kerasformers/convmixer_1024_20_ks9_p14_in1k

Paper: Patches Are All You Need? (arXiv:2201.09792) · HF Papers

ConvMixer applies depthwise and pointwise convolutions on patches in an isotropic stack. Classifier or single-scale backbone.

For more details on the model, please go to the upstream model card.

Pure-Keras 3 conversion of timm/convmixer_1024_20_ks9_p14.in1k for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an image-classification / backbone checkpoint (ConvMixerImageClassify / ConvMixerModel).

✨ Quick start

python

import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from PIL import Image
import numpy as np
from kerasformers.models.convmixer import ConvMixerImageClassify, ConvMixerModel

model = ConvMixerImageClassify.from_weights("kerasformers/convmixer_1024_20_ks9_p14_in1k")
backbone = ConvMixerModel.from_weights(
    "kerasformers/convmixer_1024_20_ks9_p14_in1k", as_backbone=True
)

image = Image.open("your_image.jpg").convert("RGB")
image = image.resize((224, 224))
x = np.asarray(image, dtype="float32")[None]  # (1, H, W, 3)
print(model(x).shape)  # (1, num_classes)
feats = backbone(x)
print(len(feats), [tuple(f.shape) for f in feats])

Load any ConvMixer variant the same way with from_weights("kerasformers/<variant>"):

Variant	Hub
`convmixer_1024_20_ks9_p14_in1k`	`kerasformers/convmixer_1024_20_ks9_p14_in1k`
`convmixer_1536_20_in1k`	`kerasformers/convmixer_1536_20_in1k`
`convmixer_768_32_in1k`	`kerasformers/convmixer_768_32_in1k`

Tips

Set KERAS_BACKEND before importing Keras / kerasformers.
ConvMixerImageClassify returns class logits; ConvMixerModel returns features (as_backbone=True for multi-scale stages).
See docs and Loading Weights.
Upstream / timm checkpoints: ConvMixerImageClassify.from_weights("hf:timm/convmixer_1024_20_ks9_p14.in1k").

Special Thanks

A huge thank you to the ConvMixer authors and the timm / Hub communities for creating and releasing these models.

License: see YAML license (usually matches the upstream checkpoint).