kerasformers/tf_efficientnet_lite2_in1k

See our collection for all versions of EfficientNet-Lite.

Run EfficientNet-Lite with Keras 3: JAX, PyTorch, or TensorFlow

kerasformers/tf_efficientnet_lite2_in1k

Paper: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946) · HF Papers

EfficientNet-Lite is the mobile/EdgeTPU-friendly EfficientNet family (no squeeze-excite, ReLU6). Classifier or backbone.

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

Pure-Keras 3 conversion of timm/tf_efficientnet_lite2.in1k for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an image-classification / backbone checkpoint (EfficientNetLiteImageClassify / EfficientNetLiteModel).

✨ Quick start

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

from PIL import Image
import numpy as np
from kerasformers.models.efficientnet_lite import EfficientNetLiteImageClassify, EfficientNetLiteModel

model = EfficientNetLiteImageClassify.from_weights("kerasformers/tf_efficientnet_lite2_in1k")
backbone = EfficientNetLiteModel.from_weights(
    "kerasformers/tf_efficientnet_lite2_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 EfficientNet-Lite variant the same way with from_weights("kerasformers/<variant>"):

Variant	Hub
tf_efficientnet_lite0_in1k	kerasformers/tf_efficientnet_lite0_in1k
tf_efficientnet_lite1_in1k	kerasformers/tf_efficientnet_lite1_in1k
tf_efficientnet_lite2_in1k	kerasformers/tf_efficientnet_lite2_in1k
tf_efficientnet_lite3_in1k	kerasformers/tf_efficientnet_lite3_in1k
tf_efficientnet_lite4_in1k	kerasformers/tf_efficientnet_lite4_in1k

Tips

• Set KERAS_BACKEND before importing Keras / kerasformers.
• EfficientNetLiteImageClassify returns class logits; EfficientNetLiteModel returns features (as_backbone=True for multi-scale stages).
• See docs and Loading Weights.
• Upstream / timm checkpoints: EfficientNetLiteImageClassify.from_weights("hf:timm/tf_efficientnet_lite2.in1k").

Special Thanks

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

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