Aller au contenu
ModelPrésentéExterne
Télécharger

Cifar 10 Densenet

A PyTorch implementation of a DenseNet architecture trained from scratch on the CIFAR-10 dataset.

Sourcehuggingface.co/aijadugar/cifar-10-densenet/tree/052b4b7fc61b45a88fcacc03f943e733c5fb1687
TypeOtherVersionRevision 052b4b7BClasse

Source du modèle

Type
Other
Taille du fichier
3,05 MB
Version
vRevision 052b4b7
Mis à jour
10 oct. 2026
Téléchargements
4
Source
Hugging Face

Description de la source

DenseNet on CIFAR-10

A PyTorch implementation of a DenseNet architecture trained from scratch on the CIFAR-10 dataset.

Model Details

  • Architecture: DenseNet
  • Framework: PyTorch
  • Dataset: CIFAR-10
  • Input Size: 3 × 32 × 32
  • Classes: 10
  • Growth Rate: 32

CIFAR-10 Classes

LabelClass
0airplane
1automobile
2bird
3cat
4deer
5dog
6frog
7horse
8ship
9truck

Training

  • Optimizer: SGD
  • Learning Rate: 0.1
  • Momentum: 0.9
  • Weight Decay: 5e-4
  • Scheduler: StepLR
  • Loss: CrossEntropyLoss
  • Epochs: 30
  • Batch Size: 128

Performance

MetricValue
Test Accuracy88.77%
Test Accuracy (DP)88.77%

Model Files

  • densenet_cifar10.pth

Load Model

model = DenseNet()

model.load_state_dict(
    torch.load("densenet_cifar10.pth")
)

model.eval()

Inference

with torch.no_grad():
    outputs = model(images)
    _, predicted = torch.max(outputs, 1)

Author

Ankit Bari

Sources

1 source
Hugging FacePrincipalVersion 052b4b7fc61b45a88fcacc03f943e733c5fb1687
huggingface.co/aijadugar/cifar-10-densenet/tree/052b4b7fc61b45a88fcacc03f943e733c5fb1687

Vérifié 10 oct.

Artefacts du modèle

2 artefacts

densenet-cifar10.safetensors

safetensors · 3,05 MB · SHA-256 4c9eaeb35371…8502 · Hugging Face

Télécharger

densenet-dp-cifar10.safetensors

safetensors · 3,05 MB · SHA-256 14cba75c9682…90b6 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme1 aoûthuggingface.co/aijadugar/cifar-10-densenet

--- license: mit language: - en library_name: pytorch pipeline_tag: image-classification tags: - pytorch - densenet - cnn - cifar10 - image-classification - computer-vision datasets: - cifar10 --- # DenseNet on CIFAR-10 A PyTorch implementation of a DenseNet architecture trained from scratch on the CIFAR-10 dataset. ## Model Details - Architecture: DenseNet - Framework: PyTorch - Dataset: CIFAR-10 - Input Size: 3 × 32 × 32 - Classes: 10 - Growth Rate: 32 ## CIFAR-10 Classes | Label | Class | |------:|--------| | 0 | airplane | | 1 | automobile | | 2 | bird | | 3 | cat | | 4 | deer | | 5 | dog | | 6 | frog | | 7 | horse | | 8 | ship | | 9 | truck | ## Training - Optimizer: SGD - Learning Rate: 0.1 - Momentum: 0.9 - Weight Decay: 5e-4 - Scheduler: StepLR - Loss: CrossEntropyLoss - Epochs: 30 - Batch Size: 128 ## Performance | Metric | Value | |--------|------:| | Test Accuracy | 88.77% | | Test Accuracy (DP) | 88.77% | ## Model Files - `densenet_cifar10.pth` ## Load Model ```python model = DenseNet() model.load_state_dict( torch.load("densenet_cifar10.pth") ) model.eval() ``` ## Inference ```python with torch.no_grad(): outputs = model(images) _, predicted = torch.max(outputs, 1) ``` ## Author Ankit Bari - GitHub: https://github.com/aijadugar - Hugging Face: https://huggingface.co/aijadugar

Note10 oct.huggingface.co/aijadugar/cifar-10-densenet

Source context: 4 downloads · 0 likes · Pipeline image-classification · Library pytorch · Repo aijadugar/cifar-10-densenet

Note1 aoûthuggingface.co/aijadugar/cifar-10-densenet

Source context: 14601 downloads · 0 likes · Pipeline image-classification · Library pytorch · Repo aijadugar/cifar-10-densenet