You can deploy this model and start earning money today!

kerasformers/
densenet121_tv_in1k

Name: densenet121_tv_in1k
Availability: InStock

timm/densenet121.tv_in1k

finetune

apache-2.0

Views

No views yet

See our collection for all versions of DenseNet.

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

GitHub

zeromodels/densenet121_tv_in1k

Paper: Densely Connected Convolutional Networks (arXiv:1608.06993) · HF Papers

DenseNet connects each layer to every other layer in a feed-forward fashion. Classifier or dense-block backbone.

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

Pure-Keras 3 conversion of timm/densenet121.tv_in1k for zeromodels. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an image-classification / backbone checkpoint (DenseNetImageClassify / DenseNetModel).

✨ Quick start

python

import os

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

from PIL import Image
from zeromodels.models.densenet import DenseNetImageClassify, DenseNetModel, DenseNetImageProcessor

model = DenseNetImageClassify.from_weights("zeromodels/densenet121_tv_in1k")
processor = DenseNetImageProcessor.from_weights("zeromodels/densenet121_tv_in1k")

image = Image.open("your_image.jpg").convert("RGB")
pixels = processor(image)  # resize + normalize (normalization lives in the processor)
logits = model(pixels, training=False)
print(logits.shape)  # (1, num_classes)

# Feature extraction: the backbone without the classifier head
backbone = DenseNetModel.from_weights("zeromodels/densenet121_tv_in1k", as_backbone=True)
features = backbone(pixels, training=False)

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

Variant	Hub
`densenet121_tv_in1k`	`zeromodels/densenet121_tv_in1k`
`densenet161_tv_in1k`	`zeromodels/densenet161_tv_in1k`
`densenet169_tv_in1k`	`zeromodels/densenet169_tv_in1k`
`densenet201_tv_in1k`	`zeromodels/densenet201_tv_in1k`

Tips

Set KERAS_BACKEND before importing Keras / zeromodels.
DenseNetImageClassify returns class logits; DenseNetModel returns features (as_backbone=True for multi-scale stages).
See docs and Loading Weights.
Upstream / timm checkpoints: DenseNetImageClassify.from_weights("hf:timm/densenet121.tv_in1k").

Special Thanks

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

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

kerasformers/densenet121_tv_in1k