File size: 1,382 Bytes
a609e95
 
 
3bc38a4
 
 
a609e95
 
3bc38a4
5fb1056
 
 
 
 
 
 
ed80744
a609e95
 
3bc38a4
a609e95
94e11e1
8cbcd66
cfa3cbe
a609e95
 
ed80744
8d2ad89
64115b7
 
ed80744
 
 
8cbcd66
5fb1056
64115b7
a609e95
 
 
 
888841b
a609e95
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
from turtle import title
from transformers import pipeline
import numpy as np
from PIL import Image
import gradio as gr




#model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M")
#tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M")
#tokenizer.src_lang = "en"
    #encodedText = tokenizer(labels_text, return_tensors="pt")
    #generatedTokens = model.generate(**encodedText, forced_bos_token_id=tokenizer.get_lang_id("ru"))    
    #return tokenizer.batch_decode(generatedTokens, skip_special_tokens=True)[0]
    

pipe = pipeline("zero-shot-image-classification", model="openai/clip-vit-base-patch32")
images="dog.jpg"

def shot(image, labels_text):

    
    
    PIL_image = Image.fromarray(np.uint8(image)).convert('RGB')
    labels = labels_text.split(",")
    
   
    # Translate 
    
    res = pipe(images=PIL_image, 
           candidate_labels=labels,
           hypothesis_template= "This is a photo of a {}")
    
    return {dic["label"]: dic["score"] for dic in res}
     
    
iface = gr.Interface(shot, 
                    ["image", "text"], 
                    "label", 
                    examples=[["dog.jpg", "dog,cat,bird"]],                         
                    description="Add a picture and a list of labels separated by commas",
                    title="Zero-shot Image Classification")

iface.launch()