Add reqs, adapted gradio demo, changed prediction output

.gitignore

@@ -1,3 +1,4 @@
 .idea/
 .idea
-data/
+data/
+__pycache__

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from helpers import load_video_from_url, detect_deepfake
+from generate_prediction import generate_prediction
 
 theme = gr.themes.Default(
     primary_hue="stone",
@@ -10,61 +10,29 @@ theme = gr.themes.Default(
     font=[gr.themes.GoogleFont("IBM Plex Mono"), "system-ui"]
 )
 
-callback = gr.CSVLogger()
+def predict_image(image):
+    # Save the uploaded image to /image.jpeg
+    image_path = "./image.jpeg"
+    image.save(image_path)
 
-with gr.Blocks(theme=theme) as demo:
-    # DEFINE COMPONENTS
-
-    # Text box for inputting Youtube URL
-    urlInput = gr.Textbox(
-        label="YOUTUBE VIDEO URL",
-        value="https://www.youtube.com/watch?v=BmrUJhY9teE"
-    )
-
-    # Button for downloading the video and previewing sample frames
-    loadVideoBtn = gr.Button("Load Video")
-
-    # Text box for displaying video title
-    videoTitle = gr.Textbox(
-        label="VIDEO TITLE",
-        lines=1,
-        interactive=False
-    )
+    # Call your model's prediction function
+    prediction = generate_prediction(image_path)  # Assuming load_and_predict function exists in your model file
 
-    # Image Gallery for previewing sample frames
-    sampleFrames = gr.Gallery(
-        label="SAMPLE FRAMES",
-        elem_id="gallery",
-        columns=[3],
-        rows=[1],
-        object_fit="contain",
-        height="auto"
-    )
+    return prediction
 
-    # Button for generating video prediction
-    predVideoBtn = gr.Button(value="Classify Video", visible=False)
-
-    # Label for displaying prediction
-    predOutput = gr.Label(
-        label="DETECTED LABEL (AND CONFIDENCE LEVEL)",
-        num_top_classes=2,
-        visible=False
-    )
-
-    # Button for flagging the output
-    flagBtn = gr.Button(value="Flag Output", visible=False)
-
-    # DEFINE FUNCTIONS
-    # Load video from URL, display sample frames, and enable prediction button
-    loadVideoBtn.click(fn=load_video_from_url, inputs=[urlInput], outputs=[videoTitle, sampleFrames, predVideoBtn, predOutput])
+with gr.Blocks(theme=theme) as demo:
+    # DEFINE COMPONENTS
+    gr.Markdown("# MindReader Quantum")
 
-    # Generate video prediction
-    predVideoBtn.click(fn=detect_deepfake, outputs=[predOutput, flagBtn])
+    # Uploading the image input
+    with gr.Row():
+        image_input = gr.Image(type="pil", label="Upload Image")
+        output_label = gr.Label(label="Prediction")
 
-    # Define flag callback
-    callback.setup([urlInput], "flagged_data_points")
+    # Button to submit and show the prediction
+    with gr.Row():
+        submit_btn = gr.Button("Submit")
 
-    # Flag output
-    flagBtn.click(fn=lambda *args: callback.flag(args), inputs=[urlInput], outputs=None)
+    submit_btn.click(fn=predict_image, inputs=image_input, outputs=output_label)
 
 demo.launch()

generate_prediction.py

@@ -1,9 +1,14 @@
 import torch
+import numpy as np
 import pennylane as qml
 from model import build_hybrid_model
 from data_loaders import load_single_image, load_dataset, get_class_names
 from helpers import imshow
 
+def softmax(x):
+    """Compute softmax values for each set of scores in x."""
+    e_x = np.exp(x - np.max(x))  # Subtracting max for numerical stability
+    return e_x / e_x.sum(axis=0)
 
 def generate_prediction(img_path="./image.jpeg"):
 
@@ -42,13 +47,12 @@ def generate_prediction(img_path="./image.jpeg"):
             _, preds = torch.max(output, 1)
 
     # Load Dataset for class_names
-    # TODO: Clean this up
     class_names = get_class_names(load_dataset())
     print("OUTPUT VEC:",output[0])
     print("HOT INDEX:",preds[0])
-    print(class_names)
 
     # Return Model Prediction
-    prediction = class_names[preds[0]]
+    probabilities = softmax(output[0].cpu().numpy())
+    prediction = {class_name.replace("_", " "): prob for class_name, prob in zip(class_names, probabilities)}
 
     return prediction

requirements.txt

@@ -0,0 +1,6 @@
+gradio==4.44.0
+matplotlib==3.9.2
+PennyLane==0.38.0
+Pillow==10.4.0
+torch==2.4.1
+torchvision==0.19.1