Views
No views yet
Szegedy et al., 2017 — Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (arXiv:1602.07261)
timm/inception_resnet_v2.tf_in1k,
converted to Lucid-native safetensors.| Tag | acc@1 | acc@5 | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|---|
TF_IN1K (default) | 80.46 | 95.31 | 55.8M | — | 213.39 MB | timm |
1import lucid.models as models
2from lucid.models.weights import InceptionResNetV2Weights
3
4# default tag
5model = models.inception_resnet_v2_cls(pretrained=True)
6
7# explicit tag (enum or string)
8model = models.inception_resnet_v2_cls(weights=InceptionResNetV2Weights.TF_IN1K)
9model = models.inception_resnet_v2_cls(pretrained="TF_IN1K")
10
11# preprocessing travels with the weights
12weights = InceptionResNetV2Weights.TF_IN1K
13preprocess = weights.transforms()
14logits = model(preprocess(image)[None]).logitstimm/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.apache-2.0 — inherited from the original weights.@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}
}