added chatGPT

app.py

@@ -1,6 +1,8 @@
 import os
+from pyChatGPT import ChatGPT
+
+os.system("pip install -U gradio")
 
-os.system("pip install gradio==2.4.6")
 import sys
 import gradio as gr
 
@@ -81,7 +83,19 @@ classifier = BUILDIN_CLASSIFIER[vocabulary]
 num_classes = len(metadata.thing_classes)
 reset_cls_test(predictor.model, classifier, num_classes)
 
-os.system("wget https://web.eecs.umich.edu/~fouhey/fun/desk/desk.jpg")
+session_token = os.environ.get("SessionToken")
+
+
+def get_response_from_chatbot(text):
+    try:
+        api = ChatGPT(session_token)
+        resp = api.send_message(text)
+        api.refresh_auth()
+        api.reset_conversation()
+        response = resp["message"]
+    except:
+        response = "Sorry, I'm busy. Try again later."
+    return response
 
 
 def inference(img):
@@ -93,6 +107,8 @@ def inference(img):
     out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
 
     detected_objects = []
+    object_list_str = []
+
     box_locations = outputs["instances"].pred_boxes
     box_loc_screen = box_locations.tensor.cpu().numpy()
 
@@ -110,27 +126,31 @@ def inference(img):
                 "h": int(height),
             }
         )
+        object_list_str.append(
+            f"{predicted_label} - X:({int(x0)} Y: {int(y0)} Width {int(width)} Height: {int(height)})"
+        )
 
-    return Image.fromarray(np.uint8(out.get_image())).convert("RGB"), detected_objects
+    chat_gpt_response = get_response_from_chatbot(
+        f"You are an intelligent image captioner. I will hand you the objects and their position, and you should give me a detailed description for the photo. In this photo we have the following objects\n{object_list_str}"
+    )
 
+    return (
+        Image.fromarray(np.uint8(out.get_image())).convert("RGB"),
+        detected_objects,
+        chat_gpt_response,
+    )
 
-title = "Detic"
 
-description = "Gradio demo for Detic: Detecting Twenty-thousand Classes using Image-level Supervision. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
+with gr.Blocks() as demo:
+    gr.Markdown("# Detic+ChatGPT")
+    with gr.Column():
+        inp = gr.Image(label="Input Image", type="filepath")
+        btn_detic = gr.Button("Run Detic+ChatGPT")
+    with gr.Column():
+        outviz = gr.Image(label="Visualization", type="pil")
+        output_desc = gr.Textbox(label="chatGPT Description", lines=5)
+        outputjson = gr.JSON(label="Detected Objects")
 
-article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2201.02605' target='_blank'>Detecting Twenty-thousand Classes using Image-level Supervision</a> | <a href='https://github.com/facebookresearch/Detic' target='_blank'>Github Repo</a></p>"
+    btn_detic.click(fn=inference, inputs=inp, outputs=[outviz, outputjson, output_desc])
 
-examples = [["desk.jpg"]]
-gr.Interface(
-    inference,
-    inputs=gr.inputs.Image(type="filepath"),
-    outputs=[
-        gr.outputs.Image(label="Visualization", type="pil"),
-        gr.outputs.JSON(label="Detected Objects"),
-    ],
-    enable_queue=True,
-    title=title,
-    description=description,
-    article=article,
-    examples=examples,
-).launch()
+demo.launch()