ModelAufgelistetExtern

Cifar Cnn

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

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

ArtOtherVersionRevision f2bb2f9CBewertung

Modellquelle

Art: Other
Dateigröße: 5,13 MB
Version: vRevision f2bb2f9
Aktualisiert: 11. Okt. 2026
Downloads: 5
Quelle: Hugging Face

Quellenbeschreibung

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}]

Quellen

1 Quelle

Hugging FacePrimärVersion f2bb2f940fdbf29323c47facc271ab168d3f5e17

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

Verifiziert 26. Aug.

Modellartefakte

1 Artefakt

model.safetensors

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

Herunterladen

Quellenauszüge

2 Auszüge

Readme26. Aug.huggingface.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. Aug.huggingface.co/MarkivDunhar/cifar-cnn

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