Duplicate from OFA-Sys/chinese-clip-zero-shot-image-classification

Co-authored-by: An Yang <yangapku@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Chinese-CLIP Zero-Shot Image Classification
+emoji: 🐲
+colorFrom: yellow
+colorTo: pink
+sdk: gradio
+sdk_version: 3.12.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: OFA-Sys/chinese-clip-zero-shot-image-classification
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,46 @@
+from turtle import title
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+from PIL import Image
+
+
+pipes = {
+    "ViT/B-16": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-base-patch16"),
+    "ViT/L-14": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-large-patch14"),
+    "ViT/L-14@336px": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-large-patch14-336px"),
+    "ViT/H-14": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-huge-patch14"),
+}
+inputs = [
+    gr.inputs.Image(type='pil'),
+    "text",
+    gr.inputs.Radio(choices=[
+                                "ViT/B-16",
+                                "ViT/L-14", 
+                                "ViT/L-14@336px", 
+                                "ViT/H-14",
+                            ], type="value", default="ViT/B-16", label="Model"), 
+]
+images="festival.jpg"
+
+def shot(image, labels_text, model_name):
+    labels = [label.strip(" ") for label in labels_text.strip(" ").split(",")]
+    res = pipes[model_name](images=image, 
+           candidate_labels=labels,
+           hypothesis_template= "一张{}的图片。")
+    return {dic["label"]: dic["score"] for dic in res}
+
+iface = gr.Interface(shot, 
+            inputs, 
+            "label", 
+            examples=[["festival.jpg", "灯笼, 鞭炮, 对联", "ViT/B-16"], 
+                      ["cat-dog-music.png", "音乐表演, 体育运动", "ViT/B-16"],
+                      ["football-match.jpg", "梅西, C罗, 马奎尔", "ViT/B-16"]],
+            description="""<p>Chinese CLIP is a contrastive-learning-based vision-language foundation model pretrained on large-scale Chinese data. For more information, please refer to the paper and official github. Also, Chinese CLIP has already been merged into Huggingface Transformers! <br><br>
+            Paper: <a href='https://arxiv.org/abs/2211.01335'>https://arxiv.org/abs/2211.01335</a> <br>
+            Github: <a href='https://github.com/OFA-Sys/Chinese-CLIP'>https://github.com/OFA-Sys/Chinese-CLIP</a> (Welcome to star! 🔥🔥) <br><br>
+            To play with this demo, add a picture and a list of labels in Chinese separated by commas. 上传图片，并输入多个分类标签，用英文逗号分隔。<br>
+            You can duplicate this space and run it privately: <a style='display:inline-block' href='https://huggingface.co/spaces/OFA-Sys/chinese-clip-zero-shot-image-classification?duplicate=true'><img src='https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14' alt='Duplicate Space'></a></p>""",
+            title="Zero-shot Image Classification (中文零样本图像分类)")
+
+iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+git+https://github.com/huggingface/transformers.git@main#egg=transformers
+torch