AI

MinerU项目中使用的模型，欢迎下载使用。 模型使用请参考PDF-Extract-Kit项目。 SDK Download # First, install the ModelScope librar

Model card for seresnextaa201d32x8d.swin12k A SE-ResNeXt-D (Rectangle-2 Anti-Aliasing) image classif

*.onnx models are converted from https://www.modelscope.cn/models/damo/speechparaformerasr_nat-zh-cn

Model card for vitbasepatch8_224.dino A Vision Transformer (ViT) image feature model. Trained with S

Model card for tresnetm.miilin21k A TResNet image classification model. Trained on ImageNet-21K-P ("

CLIP (OpenAI model for timm) Model Details The CLIP model was developed by researchers at OpenAI to

Introduction Models in this repo are converted from https://www.modelscope.cn/models/iic/speechparaf

Model card for vitlargepatch14reg4dinov2.lvd142m A Vision Transformer (ViT) image feature model with

当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 SDK下载 #安装ModelS

Model card for vitlargepatch14clip336.datacompxlftinat21 Part of a series of timm fine-tune experime

Model card for vitgiantpatch14_dinov2.lvd142m A Vision Transformer (ViT) image feature model. Pretra

Model card for vitbasepatch16_224.mae A Vision Transformer (ViT) image feature model. Pretrained on

Model card for seresnextaa201d32x8d.swin12kftin1k_384 A SE-ResNeXt-D (Rectangle-2 Anti-Aliasing) ima

Model card for vitlargepatch14clip336.laion2bftin12kin1kinat21 Part of a series of timm fine-tune ex

Model card for tresnetv2l.miil_in21k A TResNet image classification model. Trained on ImageNet-21K-P

Model card for vithugepatch14_224.mae A Vision Transformer (ViT) image feature model. Pretrained on

Model card for resnet18.a1_in1k A ResNet-B image classification model. This model features: ReLU ac

Model card for vitbasepatch16_224.dino A Vision Transformer (ViT) image feature model. Trained with

Model card for vitlargeclip336.datacompxlftaugreginat21 Part of a series of timm fine-tune experimen

Model card for vitlargepatch14_dinov2.lvd142m A Vision Transformer (ViT) image feature model. Pretra