Vit Base Patch16 224 In21k Snacks

🚀 视觉变换器在 Matthijs/snacks 数据集上微调

视觉变换器（ViT）模型在 ImageNet - 21k 上进行预训练，并使用 torchvision 中的各种数据增强变换在 Matthijs/snacks 数据集上进行了 5 个轮次的微调。

该模型在验证集和测试集上分别达到了 94.97% 和 94.43% 的准确率。

📦 数据集和模型信息

📊 评估指标

💻 使用示例

基础用法

from transformers import ViTFeatureExtractor
from torchvision.transforms import (
    Compose,
    Normalize,
    Resize,
    RandomResizedCrop,
    RandomHorizontalFlip,
    RandomAdjustSharpness,
    ToTensor
)

checkpoint = 'google/vit-base-patch16-224-in21k'
feature_extractor = ViTFeatureExtractor.from_pretrained(checkpoint)

# transformations on the training set
train_aug_transforms = Compose([
    RandomResizedCrop(size=feature_extractor.size),
    RandomHorizontalFlip(p=0.5),
    RandomAdjustSharpness(sharpness_factor=5, p=0.5),
    ToTensor(),
    Normalize(mean=feature_extractor.image_mean, std=feature_extractor.image_std),
])

# transformations on the validation/test set
valid_aug_transforms = Compose([
    Resize(size=(feature_extractor.size, feature_extractor.size)),
    ToTensor(),
    Normalize(mean=feature_extractor.image_mean, std=feature_extractor.image_std),
])

上述代码块展示了在预处理过程中应用的各种变换，用于增强原始数据集。增强后的图像是通过 set_transform 方法实时生成的。