Spaces:
Sleeping
Sleeping
|
Download README.md from ZZW45/image-classifier: direct link, hf CLI and curl.
- Browser
- Download file 920 Bytes
-
https://huggingface.co/spaces/ZZW45/image-classifier/resolve/main/README.md
- Command line
-
hf download hf://spaces/ZZW45/image-classifier/README.md
-
curl -L -o README.md https://huggingface.co/spaces/ZZW45/image-classifier/resolve/main/README.md
920 Bytes
| title: Plant Disease Classifier | |
| emoji: 🌿 | |
| colorFrom: green | |
| colorTo: blue | |
| sdk: gradio | |
| sdk_version: 6.15.0 | |
| python_version: '3.12' | |
| app_file: app.py | |
| pinned: false | |
| datasets: | |
| - DScomp380/plant_village | |
| tags: | |
| - image-classification | |
| - plant-disease | |
| - pytorch | |
| # 植物病害识别 | |
| 上传叶片图片,查看预测类别、Top-5 概率和分类明细,也可以点击示例图片试用。 | |
| 使用从零训练的 PyTorch CNN,覆盖 PlantVillage 的 39 个类别,包括健康叶片、病害叶片和无叶片背景。模型在启动时加载一次;运行期间不下载训练数据集。 | |
| 本项目固定测试划分上的 top-1 accuracy 为 99.35%,macro-F1 为 99.13%;这些结果不代表真实拍摄环境中的准确率。模型未实现未知类别检测。 | |
| 入口自动适配 CPU Basic 和 ZeroGPU。ZeroGPU 模式只在执行分类时申请 GPU,可能需要排队并受访客额度限制。 | |