See our collection for all versions of LeViT.

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

zeromodels/levit-128

Paper: LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference (arXiv:2104.01136) · HF Papers

LeViT is a hybrid convolution/transformer image classifier built for fast inference: a four-layer conv stem downsamples the image 16x, then three attention stages (each adding a learnable 2D relative-position bias) run over the tokens, with a BatchNorm fused into every linear layer and Hardswish activations. The released checkpoints are distilled - a second classification head is averaged with the first at inference. Base LeViT (hidden sizes 128/256/384, depths 4/4/4).

For more details on the model, please go to Meta's original model card.

Pure-Keras 3 conversion of facebook/levit-128 for zeromodels. One implementation runs unmodified on TensorFlow / Torch / JAX.

✨ Quick start

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

import keras
import numpy as np
from PIL import Image
from zeromodels.models.levit import LevitImageClassify

model = LevitImageClassify.from_weights("zeromodels/levit-128")

# LeViT preprocessing: resize the shortest edge to 256, then center-crop 224.
image = Image.open("your_image.jpg").convert("RGB")
w, h = image.size
short = 256
image = image.resize((round(short * w / h), short) if h <= w else (short, round(short * h / w)))
w, h = image.size
left, top = (w - 224) // 2, (h - 224) // 2
image = image.crop((left, top, left + 224, top + 224))

pixels = np.asarray(image, "float32")[None]  # raw [0, 255]; normalization is inside the model
logits = model(pixels, training=False)
print("top-1 ImageNet class id:", int(keras.ops.convert_to_numpy(logits)[0].argmax()))

Load any LeViT variant the same way with from_weights("zeromodels/<variant>"):

Variant	Hub
`levit-128S`	`zeromodels/levit-128S`
`levit-128`	`zeromodels/levit-128`
`levit-192`	`zeromodels/levit-192`
`levit-256`	`zeromodels/levit-256`
`levit-384`	`zeromodels/levit-384`

Tips

Set KERAS_BACKEND before importing Keras / zeromodels.
ImageNet normalization is baked into the model, so pass raw [0, 255] pixels.
Preprocess by resizing the shortest edge to 256 and center-cropping 224 (shown above) to match the reference; a plain resize((224, 224)) is close and also works.
LevitImageClassify averages the two distillation heads internally; LevitModel.from_weights(...) gives the backbone (the final token sequence, no head).
See Classification backbones and Loading Weights.
Community / upstream safetensors still work via the hf: prefix, e.g. LevitImageClassify.from_weights("hf:facebook/levit-128").