Oxford Pet Segmentation

🚀 FPN模型卡片

FPN（Feature Pyramid Network）模型可用於圖像語義分割任務，藉助預訓練權重能快速加載使用，同時可靈活調整初始化參數以適配不同場景。

🚀 快速開始

加載預訓練模型

import segmentation_models_pytorch as smp

model = smp.FPN.from_pretrained("oxford-pet-segmentation")

💻 使用示例

基礎用法

import segmentation_models_pytorch as smp

model = smp.FPN.from_pretrained("oxford-pet-segmentation")

高級用法

# 定義模型初始化參數
model_init_params = {
    "encoder_name": "resnet34",
    "encoder_depth": 5,
    "encoder_weights": "imagenet",
    "decoder_pyramid_channels": 256,
    "decoder_segmentation_channels": 128,
    "decoder_merge_policy": "add",
    "decoder_dropout": 0.2,
    "in_channels": 3,
    "classes": 1,
    "activation": None,
    "upsampling": 4,
    "aux_params": None
}

📚 詳細文檔

模型初始化參數

model_init_params = {
    "encoder_name": "resnet34",
    "encoder_depth": 5,
    "encoder_weights": "imagenet",
    "decoder_pyramid_channels": 256,
    "decoder_segmentation_channels": 128,
    "decoder_merge_policy": "add",
    "decoder_dropout": 0.2,
    "in_channels": 3,
    "classes": 1,
    "activation": None,
    "upsampling": 4,
    "aux_params": None
}

模型指標

[
    {
        "test_per_image_iou": 0.9065093398094177,
        "test_dataset_iou": 0.9125494360923767
    }
]

數據集

數據集名稱：Oxford Pet

更多信息

• 庫：https://github.com/qubvel/segmentation_models.pytorch
• 文檔：https://smp.readthedocs.io/en/latest/

本模型已使用 PytorchModelHubMixin 推送到Hub。

📄 許可證

本項目採用MIT許可證。