| --- |
| library_name: onnx |
| pipeline_tag: feature-extraction |
| license: bsd-3-clause |
| tags: |
| - eidora |
| - eidora-model-zoo |
| - onnx |
| - onnxruntime |
| - embeddings |
| - image |
| - resnet |
| - compute:medium |
| - modality:image |
| base_model: torchvision/resnet50-imagenet1k-v2 |
| datasets: |
| - imagenet-1k |
| metrics: |
| - cosine-similarity |
| model-index: |
| - name: RESNET50_2048 |
| results: [] |
| --- |
| |
| # RESNET50_2048 |
| |
| RESNET50_2048 is a medium image embedding model for dependable visual grouping in EIDORA. |
|
|
| ## Best For |
|
|
| - General image grouping and retrieval. |
| - Projects that need a well-established visual baseline. |
|
|
| ## Not Ideal For |
|
|
| - Text, video, or audio inputs. |
| - Fine-grained semantic retrieval where self-supervised models are preferred. |
|
|
| ## Compute Tier |
|
|
| Medium: better quality or broader domain coverage with moderate runtime cost. Intended for recent laptops and desktops. |
|
|
| ## Inputs |
|
|
| - `image`: required image input from `media_source`. |
|
|
| ## Output |
|
|
| The primary output is `embedding`, a float32 tensor shaped `[batch, 2048]`. Embeddings are already normalized and are intended for cosine similarity. |
|
|
| ## Usage In EIDORA |
|
|
| EIDORA shows this package as a medium 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 ResNet-50 ImageNet model. EIDORA converted the model to ONNX and is not the original model creator. Please cite Deep Residual Learning for Image Recognition and the original model repository when using this converted model. |
|
|
| Original model: https://github.com/pytorch/vision |
|
|
| Original paper: https://arxiv.org/abs/1512.03385 |
|
|
| Authors: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun |
|
|
| ```bibtex |
| @inproceedings{he2016deep, |
| title={Deep Residual Learning for Image Recognition}, |
| author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, |
| booktitle={CVPR}, |
| year={2016} |
| } |
| ``` |
|
|
| ## Training Data And Provenance |
|
|
| Base model: `torchvision/resnet50-imagenet1k-v2`. Source repository: https://pytorch.org/vision/stable/models/generated/torchvision.models.resnet50.html. Known training data: ImageNet-1K supervised classification data. Package payload size: 93951417 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 |
|
|
| ResNet-50 is trained for ImageNet classification, so its embeddings may underperform specialized or self-supervised models on some visual domains. |
|
|
| ## 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 ResNet-50 ImageNet weights. |
|
|
| ## Version |
|
|
| Package version: 1.0.0. ONNX opset: 17. Exporter: eidora-onnx-exporter 0.1.0. |
|
|
