内容创作
#image
cv-classification
Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks.
DeepseekModel
官方收录技能
质量 优秀 · 90
v1.0.0
获取
https://deepseekmodel.com/api/download.php?id=aiming-lab-autoresearchclaw-researchclaw-skills-builtin-domain-cv-classification-skill-md&format=skill
下载 .skill
标准格式，含 system_prompt 与 model_config，导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name cv-classification description Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks. metadata {"category":"domain","trigger-keywords":"classification,image,cifar,imagenet,resnet,vision,cnn,vit","applicable-stages":"9,10","priority":"3","version":"1.0","author":"researchclaw","references":"He et al., Deep Residual Learning, CVPR 2016; Dosovitskiy et al., An Image is Worth 16x16 Words, ICLR 2021"} Image Classification Best Practice Architecture selection: Small scale (CIFAR-10/100): ResNet-18/34, WideResNet, Simple ViT Medium scale: ResNet-50, EfficientNet-B0/B1, DeiT-Small Large scale: ViT-B/16, ConvNeXt, Swin Transformer Training recipe: Optimizer: AdamW (lr=1e-3 to 3e-4) or SGD (lr=0.1 with cosine decay) Weight decay: 0.01-0.1 for AdamW, 5e-4 for SGD Data augmentation: RandomCrop, RandomHorizontalFlip, Cutout/CutMix Warmup: 5-10 epochs linear warmup for transformers Batch size: 128-256 for CNNs, 512-1024 for ViTs (if memory allows) Standard benchmarks: CIFAR-10: ~96% (ResNet-18), ~97% (WideResNet) CIFAR-100: ~80% (ResNet-18), ~84% (WideResNet) ImageNet: ~76% (ResNet-50), ~81% (ViT-B/16)
Agent 识别该技能的关键词，点击任意一个即可复制。
该技能未提供触发词。
下载的 .skill 包内含以下字段。
| 字段 | 说明 |
|---|---|
| format | 格式标识（skill/v1） |
| skill_id | 技能唯一 ID |
| name | 技能名称 |
| version | 版本号 |
| description | 技能描述 |
| category | 所属分类（数组） |
| trigger_words | 触发词列表 |
| tags | 标签列表 |
| source | 来源标识 |
| source_url | 来源链接（本页地址） |
| exported_at | 导出时间（每次下载生成） |
| system_prompt | 系统提示词正文 |
| model_config | 模型参数：provider / model / temperature / max_tokens / top_p |
| examples | 示例 |
| install_guide | 各平台导入说明（Coze / Dify / Claude / 自定义框架） |
