ModelPrésentéExterne

Cifar Cnn

A 3-block CNN trained from scratch on CIFAR-10 using PyTorch.

Sourcehuggingface.co/MarkivDunhar/cifar-cnn/tree/f2bb2f940fdbf29323c47facc271ab168d3f5e17

TypeOtherVersionRevision f2bb2f9CClasse

Source du modèle

Type: Other
Taille du fichier: 5,13 MB
Version: vRevision f2bb2f9
Mis à jour: 11 oct. 2026
Téléchargements: 5
Source: Hugging Face

Description de la source

CIFAR-10 CNN Classifier

A 3-block CNN trained from scratch on CIFAR-10 using PyTorch.

Classes

plane, car, bird, cat, deer, dog, frog, horse, ship, truck

Training

Architecture: 3× Conv blocks (32→64→128 channels) + FC classifier
Optimizer: Adam + OneCycleLR scheduler
Augmentation: RandomCrop, RandomFlip, ColorJitter, RandomErasing
Validation accuracy: ~80%+ (after 64 epochs)

Usage

from transformers import pipeline
from PIL import Image

classifier = pipeline(
    "image-classification",
    model="MarkivDunhar/cifar-cnn"
)

result = classifier("your_image.jpg")
print(result)
# [{'label': 'dog', 'score': 0.91}]

Sources

1 source

Hugging FacePrincipalVersion f2bb2f940fdbf29323c47facc271ab168d3f5e17

huggingface.co/MarkivDunhar/cifar-cnn/tree/f2bb2f940fdbf29323c47facc271ab168d3f5e17

Vérifié 26 août

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 5,13 MB · SHA-256 6c84dcd8c997…0a06 · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme26 aoûthuggingface.co/MarkivDunhar/cifar-cnn

--- license: apache-2.0 tags: - image-classification - pytorch - cifar10 datasets: - uoft-cs/cifar10 --- # CIFAR-10 CNN Classifier A 3-block CNN trained from scratch on CIFAR-10 using PyTorch. ## Classes plane, car, bird, cat, deer, dog, frog, horse, ship, truck ## Training - Architecture: 3× Conv blocks (32→64→128 channels) + FC classifier - Optimizer: Adam + OneCycleLR scheduler - Augmentation: RandomCrop, RandomFlip, ColorJitter, RandomErasing - Validation accuracy: ~80%+ (after 64 epochs) ## Usage ```python from transformers import pipeline from PIL import Image classifier = pipeline( "image-classification", model="MarkivDunhar/cifar-cnn" ) result = classifier("your_image.jpg") print(result) # [{'label': 'dog', 'score': 0.91}] ```

Note26 aoûthuggingface.co/MarkivDunhar/cifar-cnn

Source context: 5 downloads · 0 likes · Pipeline image-classification · Repo MarkivDunhar/cifar-cnn