KerasFormers 是 AI Skill Hub 本期精选AI工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
KerasFormers 是一款基于 Python 开发的开源工具,专注于 Keras、预训练模型、视觉 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
KerasFormers 是一款基于 Python 开发的开源工具,专注于 Keras、预训练模型、视觉 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install kerasformers
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install kerasformers
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/IMvision12/KerasFormers
cd KerasFormers
pip install -e .
# 验证安装
python -c "import kerasformers; print('安装成功')"
# 命令行使用
kerasformers --help
# 基本用法
kerasformers input_file -o output_file
# Python 代码中调用
import kerasformers
# 示例
result = kerasformers.process("input")
print(result)
# kerasformers 配置文件示例(config.yml) app: name: "kerasformers" debug: false log_level: "INFO" # 运行时指定配置文件 kerasformers --config config.yml # 或通过环境变量配置 export KERASFORMERS_API_KEY="your-key" export KERASFORMERS_OUTPUT_DIR="./output"
KerasFormers is a collection of models with pretrained weights, built entirely with Keras 3. It supports a range of tasks, including classification, object detection (DETR, RT-DETR, RT-DETRv2, RF-DETR, D-FINE, OWL-ViT, OWLv2), segmentation (SAM, SAM2, SAM3, SegFormer, DeepLabV3, EoMT, MaskFormer, Mask2Former, MobileViT-DeepLabV3, RF-DETR), monocular depth estimation (Depth Anything V1, Depth Anything V2), feature extraction (DINO, DINOv2, DINOv3), vision-language modeling (CLIP, SigLIP, SigLIP2, MetaCLIP 2), speech recognition (Whisper, Speech2Text), text encoding and masked language modeling (BERT, RoBERTa, XLM-RoBERTa, DeBERTa, DeBERTa-v2, DeBERTa-v3), text generation with large language models (GPT, GPT-2, Qwen2, Qwen3, Qwen3.5, GPT-OSS), multimodal vision-language generation (Qwen2-VL, Qwen2.5-VL, Qwen3-VL), and more. It includes hybrid architectures like MaxViT alongside traditional CNNs and pure transformers. kerasformers includes custom layers and backbone support, providing flexibility and efficiency across various applications. For backbones, there are various weight variants like in1k, in21k, fb_dist_in1k, ms_in22k, fb_in22k_ft_in1k, ns_jft_in1k, aa_in1k, cvnets_in1k, augreg_in21k_ft_in1k, augreg_in21k, and many more.
From PyPI (recommended)
pip install -U kerasformers
From Source
pip install -U git+https://github.com/IMvision12/KerasFormers
高质量开源项目,支持多领域预训练模型
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,KerasFormers 在AI工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | KerasFormers |
| 原始描述 | 开源AI工具:KerasFormers: Open-source Keras 3 collection of pretrained models across Vision,。⭐11 · Python |
| Topics | Keras预训练模型视觉 |
| GitHub | https://github.com/IMvision12/KerasFormers |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-05-29 · 更新时间:2026-05-30 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。