fix outputs

.gradio/flagged/dataset1.csv

@@ -0,0 +1,2 @@
+image,output,timestamp
+.gradio/flagged/image/b71cfb0c013a7fad3f6a/header_chiffre_0.jpg,"{""label"": ""Sydney Harbour Bridge"", ""confidences"": [{""label"": ""Sydney Harbour Bridge"", ""confidence"": 0.997890055179596}, {""label"": ""Eiffel Tower"", ""confidence"": 0.9969549179077148}, {""label"": ""Forth Bridge"", ""confidence"": 0.905195415019989}, {""label"": ""Brooklyn Bridge"", ""confidence"": 0.9011015892028809}, {""label"": ""Monumento a la Revolucion"", ""confidence"": 0.8767676949501038}]}",2025-01-23 20:53:44.732426

app.py

@@ -1,22 +1,18 @@
-from transformers import pipeline
 import gradio as gr
+from classifier import LandmarkClassifier
+from custom_theme import custom_theme
 
-# Load your model from the Hugging Face Hub
-model_name = "bsvaz/landmark-classification-vit"  # Replace with your model's path on the Hub
-classifier = pipeline("image-classification", model=model_name)
+# Initialize classifier
+classifier = LandmarkClassifier()
 
-# Define the prediction function
-def classify_image(image):
-    results = classifier(image)
-    return {result["label"]: result["score"] for result in results}
-
-# Create a Gradio interface
+# Create interface with Label component configured for dictionaries
 iface = gr.Interface(
-    fn=classify_image,
+    fn=classifier.classify_image,
     inputs=gr.Image(type="pil"),
-    outputs="label",
-    title="Image Classification",
-    description="Upload an image to classify it."
+    outputs=gr.Label(num_top_classes=5), 
+    title="Landmark Image Classification",
+    description="Upload an image to identify famous landmarks.",
+    theme=custom_theme  # Apply the custom theme
 )
 
 iface.launch()

classifier.py

@@ -0,0 +1,15 @@
+from transformers import AutoModelForImageClassification, AutoImageProcessor
+import torch
+
+class LandmarkClassifier:
+    def __init__(self, model_name="bsvaz/landmark-classification-vit"):
+        self.model = AutoModelForImageClassification.from_pretrained(model_name)
+        self.processor = AutoImageProcessor.from_pretrained(model_name)
+
+    def classify_image(self, image):
+        inputs = self.processor(image, return_tensors="pt")
+        with torch.no_grad():
+            outputs = self.model(**inputs)
+        probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        scores = probabilities[0].tolist()
+        return {self.model.config.id2label[i]: score for i, score in enumerate(scores)}

custom_theme.py

@@ -0,0 +1,18 @@
+import gradio as gr
+
+# Define a custom theme with purple as the main color and yellow for contrast
+custom_theme = gr.themes.Default(
+    primary_hue="purple",
+    secondary_hue="yellow",
+    neutral_hue="gray",
+).set(
+    body_background_fill='*primary_100',  # Light purple background
+    body_text_color='*neutral_900',       # Dark gray text for contrast
+    button_primary_background_fill='*primary_500',  # Purple buttons
+    button_primary_text_color='white',              # White text on buttons
+    button_primary_background_fill_hover='*primary_600',  # Darker purple on hover
+    slider_color='*primary_500',                    # Purple slider
+    checkbox_background_color='*primary_500',       # Purple checkbox
+    input_background_fill='*neutral_100',           # Light gray input background
+    input_border_color='*primary_500',              # Purple input border
+)