From 09c90226c4c84a46a43f97071bf944f749096861 Mon Sep 17 00:00:00 2001
From: An Yang <yangapku@users.noreply.huggingface.co>
Date: Thu, 1 Dec 2022 03:24:24 +0000
Subject: [PATCH] Update README.md

---
 README.md | 50 ++++++++++++++++++++++----------------------------
 1 file changed, 22 insertions(+), 28 deletions(-)

diff --git a/README.md b/README.md
index cb28c77..96398a2 100644
--- a/README.md
+++ b/README.md
@@ -9,42 +9,36 @@ license: apache-2.0
 This is the base-version of the Chinese CLIP, with ViT-B/16 as the image encoder and RoBERTa-wwm-base as the text encoder. Chinese CLIP is a simple implementation of CLIP on a large-scale dataset of around 200 million Chinese image-text pairs. For more details, please refer to our technical report https://arxiv.org/abs/2211.01335 and our official github repo https://github.com/OFA-Sys/Chinese-CLIP
 
 ## Use with the official API
-We provide a simple code snippet to show how to use the API for Chinese-CLIP. For starters, please install cn_clip:
-```bash
-# to install the latest stable release
-pip install cn_clip
+We provide a simple code snippet to show how to use the API of Chinese-CLIP to compute the image & text embeddings and similarities. 
 
-# or install from source code
-cd Chinese-CLIP
-pip install -e .
-```
-After installation, use Chinese CLIP as shown below:
 ```python
-import torch
 from PIL import Image
+import requests
+from transformers import ChineseCLIPProcessor, ChineseCLIPModel
 
-import cn_clip.clip as clip
-from cn_clip.clip import load_from_name, available_models
-print("Available models:", available_models())  
-# Available models: ['ViT-B-16', 'ViT-L-14', 'ViT-L-14-336', 'ViT-H-14', 'RN50']
+model = ChineseCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
+processor = ChineseCLIPProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model, preprocess = load_from_name("ViT-B-16", device=device, download_root='./')
-model.eval()
-image = preprocess(Image.open("examples/pokemon.jpeg")).unsqueeze(0).to(device)
-text = clip.tokenize(["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"]).to(device)
+url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg"
+image = Image.open(requests.get(url, stream=True).raw)
+# Squirtle, Bulbasaur, Charmander, Pikachu in English
+texts = ["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"]
 
-with torch.no_grad():
-    image_features = model.encode_image(image)
-    text_features = model.encode_text(text)
-    # Normalize the features. Please use the normalized features for downstream tasks.
-    image_features /= image_features.norm(dim=-1, keepdim=True) 
-    text_features /= text_features.norm(dim=-1, keepdim=True)      
+# compute image feature
+inputs = processor(images=image, return_tensors="pt")
+image_features = model.get_image_features(**inputs)
+image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True)  # normalize
 
-    logits_per_image, logits_per_text = model.get_similarity(image, text)
-    probs = logits_per_image.softmax(dim=-1).cpu().numpy()
+# compute text features
+inputs = processor(text=texts, padding=True, return_tensors="pt")
+text_features = model.get_text_features(**inputs)
+text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)  # normalize
 
-print("Label probs:", probs)  # [[1.268734e-03 5.436878e-02 6.795761e-04 9.436829e-01]]
+# compute image-text similarity scores
+inputs = processor(text=texts, images=image, return_tensors="pt", padding=True)
+outputs = model(**inputs)
+logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
+probs = logits_per_image.softmax(dim=1)  # probs: [[1.2686e-03, 5.4499e-02, 6.7968e-04, 9.4355e-01]]
 ```
 
 However, if you are not satisfied with only using the API, feel free to check our github repo https://github.com/OFA-Sys/Chinese-CLIP for more details about training and inference.