mlfoundations/open_clip 源码下载_部署教程

项目概述

An open source implementation of CLIP.

项目地址

https://github.com/mlfoundations/open_clip

项目页面预览

mlfoundations/open_clip preview

关键指标

Stars：13236
主要语言：Python
License：Other
最近更新：2025-11-04T16:10:46Z
默认分支：main

本站高速下载（国内可用）

源码压缩包下载：点击下载（本站镜像）
SHA256：5a6cc0583192a8dc66658af99696f4ca4b03d1ae211cfe025d3fc7798ef06d89

安装部署要点（README 精选）

Usage

pip install open_clip_torch

import torch
from PIL import Image
import open_clip

model, _, preprocess = open_clip.create_model_and_transforms('ViT-B-32', pretrained='laion2b_s34b_b79k')
model.eval()  # model in train mode by default, impacts some models with BatchNorm or stochastic depth active
tokenizer = open_clip.get_tokenizer('ViT-B-32')

image = preprocess(Image.open("docs/CLIP.png")).unsqueeze(0)
text = tokenizer(["a diagram", "a dog", "a cat"])

with torch.no_grad(), torch.autocast("cuda"):
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)

    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)  # prints: [[1., 0., 0.]]

If model uses timm image encoders (convnext, siglip, eva, etc) ensure the latest timm is installed. Upgrade timm if you see ‘Unknown model’ errors for the image encoder.

If model uses transformers tokenizers, ensure transformers is installed.

Install

We advise you first create a virtual environment with:

python3 -m venv .env
source .env/bin/activate
pip install -U pip

You can then install openclip for training with pip install 'open_clip_torch[training]'.

Sample single-process running code:

python -m open_clip_train.main \
    --save-frequency 1 \
    --zeroshot-frequency 1 \
    --report-to tensorboard \
    --train-data="/path/to/train_data.csv"  \
    --val-data="/path/to/validation_data.csv"  \
    --csv-img-key filepath \
    --csv-caption-key title \
    --imagenet-val=/path/to/imagenet/root/val/ \
    --warmup 10000 \
    --batch-size=128 \
    --lr=1e-3 \
    --wd=0.1 \
    --epochs=30 \
    --workers=8 \
    --model RN50

Note: imagenet-val is the path to the validation set of ImageNet for zero-shot evaluation, not the training set!
You can remove this argument if you do not want to perform zero-shot evaluation on ImageNet throughout training. Note that the val folder should contain subfolders. If it does not, please use this script.

常用命令（从 README 提取）

pip install open_clip_torch

python3 -m venv .env
source .env/bin/activate
pip install -U pip

python tests/util_test.py --model RN50 RN101 --save_model_list models.txt --git_revision 9d31b2ec4df6d8228f370ff20c8267ec6ba39383