You can deploy this model and start earning money today!

kerasformers/
inception_v3_tf_adv_in1k

Name: inception_v3_tf_adv_in1k
Availability: InStock

timm/inception_v3.tf_adv_in1k

finetune

apache-2.0

Views

No views yet

See our collection for all versions of Inception-V3.

Run Inception-V3 with Keras 3: JAX, PyTorch, or TensorFlow

GitHub

zeromodels/inception_v3_tf_adv_in1k

Paper: Rethinking the Inception Architecture for Computer Vision (arXiv:1512.00567) · HF Papers

Inception-V3 factorizes convolutions for efficient multi-scale features. Classifier or multi-stage backbone.

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

Pure-Keras 3 conversion of timm/inception_v3.tf_adv_in1k for zeromodels. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is an image-classification / backbone checkpoint (InceptionV3ImageClassify / InceptionV3Model).

✨ Quick start

python

import os

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

from PIL import Image
from zeromodels.models.inceptionv3 import InceptionV3ImageClassify, InceptionV3Model, InceptionV3ImageProcessor

model = InceptionV3ImageClassify.from_weights("zeromodels/inception_v3_tf_adv_in1k")
processor = InceptionV3ImageProcessor.from_weights("zeromodels/inception_v3_tf_adv_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 = InceptionV3Model.from_weights("zeromodels/inception_v3_tf_adv_in1k", as_backbone=True)
features = backbone(pixels, training=False)

Load any Inception-V3 variant the same way with from_weights("zeromodels/<variant>"):

Variant	Hub
`inception_v3_gluon_in1k`	`zeromodels/inception_v3_gluon_in1k`
`inception_v3_tf_adv_in1k`	`zeromodels/inception_v3_tf_adv_in1k`
`inception_v3_tf_in1k`	`zeromodels/inception_v3_tf_in1k`

Tips

Set KERAS_BACKEND before importing Keras / zeromodels.
InceptionV3ImageClassify returns class logits; InceptionV3Model returns features (as_backbone=True for multi-scale stages).
See docs and Loading Weights.
Upstream / timm checkpoints: InceptionV3ImageClassify.from_weights("hf:timm/inception_v3.tf_adv_in1k").

Special Thanks

A huge thank you to the Inception-V3 authors and the timm / Hub communities for creating and releasing these models.

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

kerasformers/inception_v3_tf_adv_in1k