AlexNet_IN1k / config.yaml
tillmannohm's picture
Upload 3 files
75fe452 verified
Raw
History Blame Contribute Delete
4.13 kB
schema_version: 1
id: EIDORA/AlexNet_IN1k
name: AlexNet_IN1k
version: 1.0.0
model_family: AlexNet
backend: onnx
runtime:
adapter: onnx_image
execution_provider: CPUExecutionProvider
model_path: model.onnx
input_names:
- pixel_values
output_name: embedding
onnxruntime:
opset: 17
tested_versions: '>=1.17,<2'
artifact:
path: model.onnx
sha256: 3e1277374f9da12a0c92084e19003dd541a792fccd5b4c0fd2bc4bfa54b28cc6
package_size_bytes: 228020495
inputs:
- id: image
modality: image
label: Images
required: true
source_kind: media_source
requirements:
color_space: RGB
layout: NCHW
width: 224
height: 224
preprocess:
image:
resize:
mode: resize_shorter_edge_then_center_crop
resize_size: 256
crop_width: 224
crop_height: 224
interpolation: bilinear
source: TorchVision AlexNet_Weights.IMAGENET1K_V1.transforms
rescale: 1/255
normalize:
mean:
- 0.485
- 0.456
- 0.406
std:
- 0.229
- 0.224
- 0.225
inside_onnx: true
embedding:
dimensions: 4096
feature_type: embedding
pooling: fc_head
normalized: true
similarity: cosine
output_name: embedding
dtype: float32
shape:
- batch
- 4096
display:
summary: 'Light: classic ImageNet visual embeddings for fast first-pass grouping
on laptops.'
compute_tier: light
modality_labels:
- image
recommended_batch_size: 8
validation:
fixtures:
- id: image_tensor_001
input_shape:
- 1
- 3
- 224
- 224
expected_shape:
- 1
- 4096
seed: 17
checks:
load_with: onnxruntime
execution_provider: CPUExecutionProvider
output_dtype: float32
finite: true
normalized_l2_range:
- 0.99
- 1.01
provenance:
base_model: torchvision/alexnet-imagenet1k-v1
source_repository: https://pytorch.org/vision/stable/models/generated/torchvision.models.alexnet.html
original_model_name: AlexNet ImageNet
original_model_url: https://proceedings.neurips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html
authors:
- Alex Krizhevsky
- Ilya Sutskever
- Geoffrey E. Hinton
paper_title: ImageNet Classification with Deep Convolutional Neural Networks
paper_url: https://proceedings.neurips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html
upstream_license: BSD-3-Clause for TorchVision code; ImageNet-trained weights distributed
by PyTorch under their documented model terms.
training_data: ImageNet-1K supervised classification data.
citation: "@inproceedings{krizhevsky2012imagenet,\n title={ImageNet Classification\
\ with Deep Convolutional Neural Networks},\n author={Krizhevsky, Alex and Sutskever,\
\ Ilya and Hinton, Geoffrey E.},\n booktitle={Advances in Neural Information\
\ Processing Systems},\n year={2012}\n}\n"
conversion_note: EIDORA produced this ONNX conversion and is not the original model
creator.
export_date: '2026-07-10'
exporter_version: eidora-onnx-exporter 0.1.0
model_card:
best_for:
- Fast baseline visual grouping.
- Small or exploratory image projects on ordinary laptops.
- Regression testing the EIDORA ONNX package pipeline.
not_ideal_for:
- Fine-grained visual similarity where modern self-supervised models perform better.
- Text, video, or audio inputs.
- Production-quality semantic image retrieval when a stronger model is acceptable.
limitations: AlexNet is an older supervised ImageNet model. It is useful as a lightweight
baseline, but modern CLIP, DINOv2, SigLIP, or domain-specific models will usually
produce stronger semantic similarity.
license:
id: bsd-3-clause
attribution: Converted to ONNX for EIDORA from the TorchVision AlexNet ImageNet
weights.
huggingface:
org: eidora
repo_name: alexnet_imagenet1k_4096
pipeline_tag: feature-extraction
tags:
- eidora
- eidora-model-zoo
- onnx
- onnxruntime
- embeddings
- image
- alexnet
- imagenet
- compute:light
- modality:image
datasets:
- imagenet-1k
metrics:
- cosine-similarity