inception-resnet-v2

Inception-ResNet v2

Szegedy et al., 2017 — Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (arXiv:1602.07261)

Lucid port of timm/inception_resnet_v2.tf_in1k, converted to Lucid-native safetensors.

Available weights

Usage

import lucid.models as models
from lucid.models.weights import InceptionResNetV2Weights

# default tag
model = models.inception_resnet_v2_cls(pretrained=True)

# explicit tag (enum or string)
model = models.inception_resnet_v2_cls(weights=InceptionResNetV2Weights.TF_IN1K)
model = models.inception_resnet_v2_cls(pretrained="TF_IN1K")

# preprocessing travels with the weights
weights = InceptionResNetV2Weights.TF_IN1K
preprocess = weights.transforms()
logits = model(preprocess(image)[None]).logits

Conversion

Converted from timm/inception_resnet_v2.tf_in1k via python -m tools.convert_weights inception_resnet_v2 --tag TF_IN1K. Key mapping + numerical parity verified against the source.

License

apache-2.0 — inherited from the original weights.

Citation

@inproceedings{szegedy2017inception,
  title={Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning},
  author={Szegedy, Christian and Ioffe, Sergey and Vanhoucke, Vincent and Alemi, Alexander A.},
  booktitle={AAAI}, year={2017}
}