Vit Base Patch16 224 In21k Snacks

🚀 視覺變換器在 Matthijs/snacks 數據集上微調

視覺變換器（ViT）模型在 ImageNet - 21k 上進行預訓練，並使用 torchvision 中的各種數據增強變換在 Matthijs/snacks 數據集上進行了 5 個輪次的微調。

該模型在驗證集和測試集上分別達到了 94.97% 和 94.43% 的準確率。

📦 數據集和模型信息

📊 評估指標

💻 使用示例

基礎用法

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),
])

上述代碼塊展示了在預處理過程中應用的各種變換，用於增強原始數據集。增強後的圖像是通過 set_transform 方法即時生成的。