跳到主要内容

Clip

OpenAI 连接视觉与语言的模型。支持零样本图像分类、图像-文本匹配和跨模态检索。在 4 亿个图像-文本对上进行训练。适用于无需微调的图像搜索、内容审核或视觉-语言任务。最适合通用图像理解。

技能元数据​

来源可选 — 使用 hermes skills install official/mlops/clip 安装
路径optional-skills/mlops/clip
版本1.0.0
作者Orchestra Research
许可证MIT
依赖项transformers, torch, pillow
标签Multimodal, CLIP, Vision-Language, Zero-Shot, Image Classification, OpenAI, Image Search, Cross-Modal Retrieval, Content Moderation

参考：完整 SKILL.md​

信息

以下是 Hermes 在触发此技能时加载的完整技能定义。这是技能激活时代理看到的指令。

CLIP - 对比语言-图像预训练 (Contrastive Language-Image Pre-Training)

OpenAI 能够通过自然语言理解图像的模型。

何时使用 CLIP​

使用时机：

  • 零样本图像分类（无需训练数据）
  • 图像-文本相似度/匹配
  • 语义图像搜索
  • 内容审核（检测色情、暴力内容）
  • 视觉问答
  • 跨模态检索（图像→文本，文本→图像）

指标：

  • GitHub 星标超过 25,300+
  • 在 4 亿个图像-文本对上进行训练
  • 在 ImageNet 上（零样本）性能媲美 ResNet-50
  • MIT 许可证

改用其他替代方案：

  • BLIP-2：更好的图像描述生成
  • LLaVA：视觉-语言聊天
  • Segment Anything：图像分割

快速开始​

安装​

pip install git+https://github.com/openai/CLIP.git
pip install torch torchvision ftfy regex tqdm

零样本分类​

import torch
import clip
from PIL import Image

# Load model
device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)

# Load image
image = preprocess(Image.open("photo.jpg")).unsqueeze(0).to(device)

# Define possible labels
text = clip.tokenize(["a dog", "a cat", "a bird", "a car"]).to(device)

# Compute similarity
with torch.no_grad():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)

    # Cosine similarity
    logits_per_image, logits_per_text = model(image, text)
    probs = logits_per_image.softmax(dim=-1).cpu().numpy()

# Print results
labels = ["a dog", "a cat", "a bird", "a car"]
for label, prob in zip(labels, probs[0]):
    print(f"{label}: {prob:.2%}")

可用模型​

# Models (sorted by size)
models = [
    "RN50",           # ResNet-50
    "RN101",          # ResNet-101
    "ViT-B/32",       # Vision Transformer (recommended)
    "ViT-B/16",       # Better quality, slower
    "ViT-L/14",       # Best quality, slowest
]

model, preprocess = clip.load("ViT-B/32")
模型参数量速度质量
RN50102M快良好
ViT-B/32151M中等更好
ViT-L/14428M慢最佳

图像-文本相似度​

# Compute embeddings
image_features = model.encode_image(image)
text_features = model.encode_text(text)

# Normalize
image_features /= image_features.norm(dim=-1, keepdim=True)
text_features /= text_features.norm(dim=-1, keepdim=True)

# Cosine similarity
similarity = (image_features @ text_features.T).item()
print(f"Similarity: {similarity:.4f}")
# Index images
image_paths = ["img1.jpg", "img2.jpg", "img3.jpg"]
image_embeddings = []

for img_path in image_paths:
    image = preprocess(Image.open(img_path)).unsqueeze(0).to(device)
    with torch.no_grad():
        embedding = model.encode_image(image)
        embedding /= embedding.norm(dim=-1, keepdim=True)
    image_embeddings.append(embedding)

image_embeddings = torch.cat(image_embeddings)

# Search with text query
query = "a sunset over the ocean"
text_input = clip.tokenize([query]).to(device)
with torch.no_grad():
    text_embedding = model.encode_text(text_input)
    text_embedding /= text_embedding.norm(dim=-1, keepdim=True)

# Find most similar images
similarities = (text_embedding @ image_embeddings.T).squeeze(0)
top_k = similarities.topk(3)

for idx, score in zip(top_k.indices, top_k.values):
    print(f"{image_paths[idx]}: {score:.3f}")

内容审核​

# Define categories
categories = [
    "safe for work",
    "not safe for work",
    "violent content",
    "graphic content"
]

text = clip.tokenize(categories).to(device)

# Check image
with torch.no_grad():
    logits_per_image, _ = model(image, text)
    probs = logits_per_image.softmax(dim=-1)

# Get classification
max_idx = probs.argmax().item()
max_prob = probs[0, max_idx].item()

print(f"Category: {categories[max_idx]} ({max_prob:.2%})")

批量处理​

# Process multiple images
images = [preprocess(Image.open(f"img{i}.jpg")) for i in range(10)]
images = torch.stack(images).to(device)

with torch.no_grad():
    image_features = model.encode_image(images)
    image_features /= image_features.norm(dim=-1, keepdim=True)

# Batch text
texts = ["a dog", "a cat", "a bird"]
text_tokens = clip.tokenize(texts).to(device)

with torch.no_grad():
    text_features = model.encode_text(text_tokens)
    text_features /= text_features.norm(dim=-1, keepdim=True)

# Similarity matrix (10 images × 3 texts)
similarities = image_features @ text_features.T
print(similarities.shape)  # (10, 3)

与向量数据库集成​

# Store CLIP embeddings in Chroma/FAISS
import chromadb

client = chromadb.Client()
collection = client.create_collection("image_embeddings")

# Add image embeddings
for img_path, embedding in zip(image_paths, image_embeddings):
    collection.add(
        embeddings=[embedding.cpu().numpy().tolist()],
        metadatas=[{"path": img_path}],
        ids=[img_path]
    )

# Query with text
query = "a sunset"
text_embedding = model.encode_text(clip.tokenize([query]))
results = collection.query(
    query_embeddings=[text_embedding.cpu().numpy().tolist()],
    n_results=5
)

最佳实践​

  1. 大多数情况下使用 ViT-B/32 - 良好的平衡
  2. 归一化嵌入向量 - 余弦相似度所必需
  3. 批量处理 - 更高效
  4. 缓存嵌入向量 - 重新计算成本高
  5. 使用描述性标签 - 更好的零样本性能
  6. 推荐使用 GPU - 速度快 10-50 倍
  7. 预处理图像 - 使用提供的预处理函数

性能​

操作CPUGPU (V100)
图像编码~200ms~20ms
文本编码~50ms~5ms
相似度计算<1ms<1ms

局限性​

  1. 不适用于细粒度任务 - 最适合 broad categories（宽泛类别）
  2. 需要描述性文本 - 模糊标签表现不佳
  3. 基于网络数据存在偏见 - 可能存在数据集偏见
  4. 无边界框 - 仅支持整张图像
  5. 空间理解有限 - 位置/计数能力较弱

资源​