Create app.py

app.py

@@ -0,0 +1,49 @@
+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="openai/clip-vit-base-patch16"),
+    "ViT/L-14": pipeline("zero-shot-image-classification", model="openai/clip-vit-base-patch16"),
+}
+inputs = [
+    gr.inputs.Image(type='pil', 
+                    label="Image"),
+    gr.inputs.Textbox(lines=1, 
+                      label="Candidate Labels"),
+    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"), 
+    gr.inputs.Textbox(lines=1, 
+                      label="Prompt Template Prompt", 
+                      default="a photo of a {}"),
+]
+images="festival.jpg"
+
+def shot(image, labels_text, model_name, hypothesis_template):
+    labels = [label.strip(" ") for label in labels_text.strip(" ").split(",")]
+    res = pipes[model_name](images=image, 
+           candidate_labels=labels,
+           hypothesis_template=hypothesis_template)
+    return {dic["label"]: dic["score"] for dic in res}
+
+iface = gr.Interface(shot, 
+            inputs, 
+            "label", 
+            examples=[["festival.jpg", "lantern, firecracker, couplet", "ViT/B-16", "a photo of a {}"], 
+                      # ["cat-dog-music.png", "音乐表演, 体育运动", "ViT/B-16", "a photo of a {}"],
+                      # ["football-match.jpg", "梅西, C罗, 马奎尔", "ViT/B-16", "a photo of a {}"]],
+            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。可点击页面最下方示例参考。<br>
+            You can duplicate this space and run it privately: <a 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")
+
+iface.launch()