Create app.py

app.py

@@ -0,0 +1,81 @@
+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)
+
+    image = processor(images=raw_image, return_tensors="pt").pixel_values
+    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("./kittens.jpeg")
+sample_labels = "a photo of a man, a photo of a dog, cats, two cats"
+
+with gr.Blocks() as demo:
+    gr.Markdown(
+    """
+    # Give possible labels to the object in the picture - 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(label="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="Upload Image", visible=False)
+    labels = gr.Textbox(value=sample_labels, label="Type a list of 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)