EIDORA/VGG19_IN1k

VGG19_4096

VGG19_4096 is a heavy image embedding model for classic high-dimensional visual features in EIDORA.

Best For

• Classic high-dimensional image embeddings.
• Comparisons with established VGG-based workflows.

Not Ideal For

• Large projects on laptops.
• Text, video, or audio inputs.

Compute Tier

Heavy: highest quality or largest model size with the slowest CPU runtime. Intended for smaller projects or workstation-class machines.

Inputs

• image: required image input from media_source.

Output

The primary output is embedding, a float32 tensor shaped [batch, 4096]. Embeddings are already normalized and are intended for cosine similarity.

Usage In EIDORA

EIDORA shows this package as a heavy image embedding model in the Model Zoo. Use it for discovery maps, grouping, retrieval, and related embedding workflows.

Preprocessing

• image: resize mode defaults to crop_center; rescale uses 1/255; normalize inside the ONNX graph with mean [0.485, 0.456, 0.406] and std [0.229, 0.224, 0.225].

Authorship And Citation

This ONNX package was produced by EIDORA from the original VGG-19 ImageNet model. EIDORA converted the model to ONNX and is not the original model creator. Please cite Very Deep Convolutional Networks for Large-Scale Image Recognition and the original model repository when using this converted model.

Original model: https://www.robots.ox.ac.uk/~vgg/research/very_deep/

Original paper: https://arxiv.org/abs/1409.1556

Authors: Karen Simonyan, Andrew Zisserman

@article{simonyan2014very,
  title={Very Deep Convolutional Networks for Large-Scale Image Recognition},
  author={Simonyan, Karen and Zisserman, Andrew},
  journal={arXiv preprint arXiv:1409.1556},
  year={2014}
}

Training Data And Provenance

Base model: torchvision/vgg19-imagenet1k-v1. Source repository: https://pytorch.org/vision/stable/models/generated/torchvision.models.vgg19.html. Known training data: ImageNet-1K supervised classification data. Package payload size: 558291338 bytes.

Evaluation And Validation

The package validation checks that the ONNX graph loads with ONNX Runtime CPU execution, runs the declared fixtures, returns finite float32 embeddings with the declared shape, and matches the artifact hash recorded in config.yaml.

Limitations And Safety

VGG-19 is large and slow on CPU. It is mainly useful for compatibility and classic-feature baselines rather than efficient modern retrieval.

License And Attribution

This package uses license bsd-3-clause. Upstream license: BSD-3-Clause for TorchVision code; ImageNet weights are distributed by PyTorch under documented model terms. Converted to ONNX for EIDORA from TorchVision VGG-19 ImageNet weights.

Version

Package version: 1.0.0. ONNX opset: 17. Exporter: eidora-onnx-exporter 0.1.0.