ModelListadosExterno

Oxford 17 Flowers Cnn

ResNet18 fine-tuned on the Oxford 17 Flowers dataset. Classifies RGB images into 17 flower categories.

Fontehuggingface.co/sergiudanstan/oxford-17-flowers-cnn/tree/e727ec879a13eada6c899c5a1863b1f1905d32ef

TipoOtherVersãoRevision e727ec8Bnota

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 42,7 MB
Versão: vRevision e727ec8
Atualizado: 11 de out. de 2026
Downloads: 6
Fonte: Hugging Face

Descrição da fonte

Oxford 17 Flowers — ResNet18 (97.8% test accuracy)

ResNet18 fine-tuned on the Oxford 17 Flowers dataset. Classifies RGB images into 17 flower categories.

Successor of the from-scratch educational CNN at darjja/oxford-17-flowers-cnn — same CLI, much higher accuracy:

Model	Test accuracy
From-scratch CNN, 64×64 (original)	62.13%
From-scratch CNN + augmentation & label smoothing	66.91%
ResNet18 fine-tuned, 224×224 (this repo)	97.79%

Quick start

pip install torch torchvision huggingface_hub pillow

Download the script and run it on any image:

huggingface-cli download sergiudanstan/oxford-17-flowers-cnn predict.py --local-dir .
python predict.py your_flower.jpg
python predict.py your_flower.jpg --top 5

The script downloads flower_cnn.pth, config.json, and model.py from this repo automatically on first run.

Training recipe

ImageNet-pretrained ResNet18 (torchvision IMAGENET1K_V1), full fine-tune at 224×224
Differential learning rates: backbone 1e-4, new head 1e-3 (AdamW, weight decay 1e-4)
CosineAnnealingLR, label smoothing 0.1, early stopping on validation accuracy
Augmentation: RandomResizedCrop(0.7–1.0), horizontal flip, rotation ±15°, ColorJitter 0.2
Split: 924 train / 164 val (15%, seed 42) / 272 official test
~3 minutes on a laptop RTX 5050

Files in this repo

File	Purpose
`predict.py`	CLI script — pass any image path as argument
`model.py`	Model definition (ResNet18 wrapper, `FlowerCNN`)
`flower_cnn.pth`	Fine-tuned weights (~45 MB)
`config.json`	Image size, class names

Classes

Bluebell, Buttercup, Coltsfoot, Cowslip, Crocus, Daffodil, Daisy, Dandelion, Fritillary, Iris, Lilyvalley, Pansy, Snowdrop, Sunflower, Tigerlily, Tulip, Windflower

Fontes

1 fonte

Hugging FacePrimárioVersão e727ec879a13eada6c899c5a1863b1f1905d32ef

huggingface.co/sergiudanstan/oxford-17-flowers-cnn/tree/e727ec879a13eada6c899c5a1863b1f1905d32ef

Verificado 27 de ago.

Artefatos de modelo

1 artefato

flower_cnn.pth

pth · 42,7 MB · SHA-256 c12813871829…d8da · Hugging Face

Download file

Trechos de fonte

2 trechos

Readme27 de ago.huggingface.co/sergiudanstan/oxford-17-flowers-cnn

--- license: apache-2.0 tags: - image-classification - pytorch - resnet datasets: - darjja/oxford-17-flowers --- # Oxford 17 Flowers — ResNet18 (97.8% test accuracy) ResNet18 fine-tuned on the [Oxford 17 Flowers](https://huggingface.co/datasets/darjja/oxford-17-flowers) dataset. Classifies RGB images into 17 flower categories. Successor of the from-scratch educational CNN at [darjja/oxford-17-flowers-cnn](https://huggingface.co/darjja/oxford-17-flowers-cnn) — same CLI, much higher accuracy: | Model | Test accuracy | |---|---| | From-scratch CNN, 64×64 (original) | 62.13% | | From-scratch CNN + augmentation & label smoothing | 66.91% | | **ResNet18 fine-tuned, 224×224 (this repo)** | **97.79%** | ## Quick start ```bash pip install torch torchvision huggingface_hub pillow ``` Download the script and run it on any image: ```bash huggingface-cli download sergiudanstan/oxford-17-flowers-cnn predict.py --local-dir . python predict.py your_flower.jpg python predict.py your_flower.jpg --top 5 ``` The script downloads `flower_cnn.pth`, `config.json`, and `model.py` from this repo automatically on first run. ## Training recipe - ImageNet-pretrained ResNet18 (torchvision `IMAGENET1K_V1`), full fine-tune at 224×224 - Differential learning rates: backbone 1e-4, new head 1e-3 (AdamW, weight decay 1e-4) - CosineAnnealingLR, label smoothing 0.1, early stopping on validation accuracy - Augmentation: RandomResizedCrop(0.7–1.0), horizontal flip, rotation ±15°, ColorJitter 0.2 - Split: 924 train / 164 val (15%, seed 42) / 272 official test - ~3 minutes on a laptop RTX 5050 ## Files in this repo | File | Purpose | |------|---------| | `predict.py` | CLI script — pass any image path as argument | | `model.py` | Model definition (ResNet18 wrapper, `FlowerCNN`) | | `flower_cnn.pth` | Fine-tuned weights (~45 MB) | | `config.json` | Image size, class names | ## Classes Bluebell, Buttercup, Coltsfoot, Cowslip, Crocus, Daffodil, Daisy, Dandelion, Fritillary, Iris, Lilyvalley, Pansy, Snowdrop, Sunflower, Tigerlily, Tulip, Windflower

Note27 de ago.huggingface.co/sergiudanstan/oxford-17-flowers-cnn

Source context: 6 downloads · 0 likes · Pipeline image-classification · Repo sergiudanstan/oxford-17-flowers-cnn