aijadugar/cifar-10-mobilenet

license: mit language:

• —en libraryname: pytorch pipelinetag: image-classification tags:
• —pytorch
• —mobilenetv2
• —cnn
• —cifar10
• —image-classification
• —computer-vision datasets:
• —cifar10 ---

MobileNetV2 on CIFAR-10

A PyTorch implementation of MobileNetV2 trained from scratch on the CIFAR-10 dataset.

Model Details

• —Architecture: MobileNetV2
• —Framework: PyTorch
• —Dataset: CIFAR-10
• —Input Size: 3 × 32 × 32
• —Classes: 10

CIFAR-10 Classes

Training

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

Performance

Model Files

• —mobilenetv2_cifar10.pth

Load Model

model = MobileNetV2()

model.load_state_dict(
    torch.load("mobilenetv2_cifar10.pth")
)

model.eval()

Inference

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