edadaltocg/vit_base_patch16_224_in21k_ft_cifar10

Model Card for Model ID

This model is a small timm/vitbasepatch16224.origin21kftin1k trained on cifar10.

• —Test Accuracy: 0.9896
• —License: MIT

How to Get Started with the Model

Use the code below to get started with the model.

import timm
import torch
from torch import nn

model = timm.create_model("timm/vit_base_patch16_224.orig_in21k_ft_in1k", pretrained=False)
model.head = nn.Linear(model.head.in_features, 10)
model.load_state_dict(
    torch.hub.load_state_dict_from_url(
        "https://huggingface.co/edadaltocg/vit_base_patch16_224_in21k_ft_cifar10/resolve/main/pytorch_model.bin",
        map_location="cpu",
        file_name="vit_base_patch16_224_in21k_ft_cifar10.pth",
    )
)

Training Data

Training data is cifar10.

Training Hyperparameters

• —config: scripts/train_configs/ft_cifar10.json

• —model: vit_base_patch16_224_in21k_ft_cifar10

• —dataset: cifar10

• —batch_size: 64

• —epochs: 10

• —validation_frequency: 1

• —seed: 1

• —criterion: CrossEntropyLoss

• —criterion_kwargs: {}

• —optimizer: SGD

• —lr: 0.01

• —optimizer_kwargs: {'momentum': 0.9, 'weight_decay': 0.0}

• —scheduler: CosineAnnealingLR

• —scheduler_kwargs: {'T_max': 10}

• —debug: False

Testing Data

Testing data is cifar10.

This model card was created by Eduardo Dadalto.