File size: 3,570 Bytes
821db2a 73753ad 821db2a 3d952fe 821db2a 3d952fe 821db2a c04992d 821db2a b3943d4 821db2a c04992d 3d952fe 821db2a |
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 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
from transformers.utils import logging
from transformers import AutoProcessor
from transformers import CLIPModel
import gradio as gr
import torch
import requests
from PIL import Image
logging.set_verbosity_error()
model = CLIPModel.from_pretrained(
"openai/clip-vit-large-patch14")
processor = AutoProcessor.from_pretrained(
"openai/clip-vit-large-patch14")
def process_image(input_type, image_url, image_upload, labels):
if input_type == "URL":
raw_image = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
else:
raw_image = image_upload
labels = [l.strip() for l in labels.split(",")]
print(labels)
inputs = processor(text=labels, images=raw_image, return_tensors="pt", padding=True)
outputs = model(**inputs)
probs = outputs.logits_per_image.softmax(dim=1)[0]
probs = list(probs)
for i in range(len(labels)):
print(f"label: {labels[i]} - probability of detected object being {probs[i].item():.4f}%")
answer = str(labels[probs.index(max(probs))]).capitalize()
print(answer)
answer = (
f"""<div>
<h2 style='text-align: center; font-size: 30px; color: blue;'>The detected object is </h2>
<h1 style='text-align: center; font-size: 50px; color: orange;'>{answer}</h1>
<h2 style='text-align: center; font-size: 30px; color: blue;'> with a probability of </h2>
<h1 style='text-align: center; font-size: 50px; color: orange;'>{max(probs)*100:.2f}</h1>
</div>"""
)
return answer
def display_image_from_url(image_url):
if image_url:
image = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
return image
return None
def toggle_inputs(input_type):
if input_type == "URL":
return gr.update(visible=True), gr.update(visible=True), gr.update(visible=False), gr.update(visible=True)
else:
return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True), gr.update(visible=True)
sample_image = Image.open("./huggingface_friends.jpg")
sample_labels = "a photo of a man, a photo of a dog, cats, two cats, group of friends dining, food, people eating, men and women"
with gr.Blocks() as demo:
gr.Markdown(
"""
# Determine best label for the picture out of a set of possible labels - test & demo app by Srinivas.V..
Paste either URL of an image or upload the image, type-in your label choices for the image,
seperated by comma (',') and submit.
""")
input_type = gr.Radio(choices=["URL", "Upload"], label="Input Type")
image_url = gr.Textbox(value= 'https://huggingface.co/spaces/vsrinivas/Determine_Best_Label_from_Set_of_Given_Labels/resolve/main/huggingface_friends.jpg', label="Type-in/ Paste Image URL", visible=False)
url_image = gr.Image(value=sample_image,type="pil", label="URL Image", visible=False)
image_upload = gr.Image(value=sample_image,type="pil", label="Uploaded Image", visible=False)
labels = gr.Textbox(value=sample_labels, label="Type in your labels seperated by comma(',')", visible=False, lines=2)
input_type.change(fn=toggle_inputs, inputs=input_type, outputs=[image_url, url_image, image_upload, labels])
image_url.change(fn=display_image_from_url, inputs=image_url, outputs=url_image)
submit_btn = gr.Button("Submit")
processed_image = gr.HTML(label="The Answer")
submit_btn.click(fn=process_image, inputs=[input_type, image_url, image_upload, labels], outputs=processed_image)
demo.launch(debug=True, share=True) |