说明文档

SigLIP 模型的 ONNX 导出版本。

模型

共导出 8 个模型。

名称	图像 (参数量/计算量)	图像尺寸	图像宽度 (编码器/嵌入)	文本 (参数量/计算量)	文本宽度 (编码器/嵌入)	创建时间
google/siglip-so400m-patch14-384	422.1M / 300.4G	384	1152 / 1152	412.8M / 52.7G	1152 / 1152	2024-01-08
google/siglip-base-patch16-256-multilingual	90.4M / 21.9G	256	768 / 768	85.6M / 10.9G	768 / 768	2024-01-08
google/siglip-large-patch16-384	311.5M / 174.5G	384	1024 / 1024	303.4M / 38.7G	1024 / 1024	2024-01-08
google/siglip-large-patch16-256	311.5M / 77.6G	256	1024 / 1024	303.4M / 38.7G	1024 / 1024	2024-01-08
google/siglip-base-patch16-512	90.4M / 87.7G	512	768 / 768	85.6M / 10.9G	768 / 768	2024-01-08
google/siglip-base-patch16-384	90.4M / 49.3G	384	768 / 768	85.6M / 10.9G	768 / 768	2024-01-08
google/siglip-base-patch16-256	90.4M / 21.9G	256	768 / 768	85.6M / 10.9G	768 / 768	2024-01-08
google/siglip-base-patch16-224	90.4M / 16.8G	224	768 / 768	85.6M / 10.9G	768 / 768	2023-10-01

deepghs/siglip_onnx

作者 deepghs

zero-shot-classification dghs-realutils

↓ 0 ♥ 3

创建时间: 2025-01-29 04:43:10+00:00

更新时间: 2025-01-29 15:41:17+00:00

在 Hugging Face 上查看

文件 (43)

.gitattributes

README.md

google/siglip-base-patch16-224/image_encode.onnx ONNX

google/siglip-base-patch16-224/meta.json

google/siglip-base-patch16-224/preprocessor.json

google/siglip-base-patch16-224/text_encode.onnx ONNX

google/siglip-base-patch16-224/tokenizer.json

google/siglip-base-patch16-256-multilingual/image_encode.onnx ONNX

google/siglip-base-patch16-256-multilingual/meta.json

google/siglip-base-patch16-256-multilingual/preprocessor.json

google/siglip-base-patch16-256-multilingual/text_encode.onnx ONNX

google/siglip-base-patch16-256-multilingual/tokenizer.json

google/siglip-base-patch16-256/image_encode.onnx ONNX

google/siglip-base-patch16-256/meta.json

google/siglip-base-patch16-256/preprocessor.json

google/siglip-base-patch16-256/text_encode.onnx ONNX

google/siglip-base-patch16-256/tokenizer.json

google/siglip-base-patch16-384/image_encode.onnx ONNX

google/siglip-base-patch16-384/meta.json

google/siglip-base-patch16-384/preprocessor.json

google/siglip-base-patch16-384/text_encode.onnx ONNX

google/siglip-base-patch16-384/tokenizer.json

google/siglip-base-patch16-512/image_encode.onnx ONNX

google/siglip-base-patch16-512/meta.json

google/siglip-base-patch16-512/preprocessor.json

google/siglip-base-patch16-512/text_encode.onnx ONNX

google/siglip-base-patch16-512/tokenizer.json

google/siglip-large-patch16-256/image_encode.onnx ONNX

google/siglip-large-patch16-256/meta.json

google/siglip-large-patch16-256/preprocessor.json

google/siglip-large-patch16-256/text_encode.onnx ONNX

google/siglip-large-patch16-256/tokenizer.json

google/siglip-large-patch16-384/image_encode.onnx ONNX

google/siglip-large-patch16-384/meta.json

google/siglip-large-patch16-384/preprocessor.json

google/siglip-large-patch16-384/text_encode.onnx ONNX

google/siglip-large-patch16-384/tokenizer.json

google/siglip-so400m-patch14-384/image_encode.onnx ONNX

google/siglip-so400m-patch14-384/meta.json

google/siglip-so400m-patch14-384/preprocessor.json

google/siglip-so400m-patch14-384/text_encode.onnx ONNX

google/siglip-so400m-patch14-384/tokenizer.json

models.parquet