Change learning rate, small text changes

app.py

@@ -58,6 +58,8 @@ MODEL_INFO = [
     {"org": "Imageomics", "name": "BioCLIP", "logo": "logos/imageomics.png"}
 ]
 
+DEMO_LEARNING_RATE = 0.05 # don't use default; use something more fun
+
 # load image metadata
 images_data = []
 for annotation in tqdm(data['annotations'], desc='Loading annotations'):
@@ -124,7 +126,7 @@ def get_model_predictions(chosen_idx):
         confidence = model_scores[predicted_class_idx]
 
         model_info = MODEL_INFO[model_idx]
-        predictions_list.append(f"**{model_info['org']} {model_info['name']}:** {predicted_class_name} *({confidence:.3f})*")
+        predictions_list.append(f"**{model_info['name']}:** {predicted_class_name} *({confidence:.3f})*")
 
     predictions_text = "### Model Predictions\n\n" + " | ".join(predictions_list)
 
@@ -596,6 +598,7 @@ with gr.Blocks(title="CODA: Wildlife Photo Classification Challenge",
             so that you will be equipped to provide ground truth labels. Then, watch as CODA narrows down the best model over time
             as you provide labels for the query images. You will see that with your input CODA is able to identify the best model candidate
             with as few as ten (correctly) labeled images.
+                 
             """)
 
             # Species guide content (initially hidden)
@@ -806,7 +809,8 @@ with gr.Blocks(title="CODA: Wildlife Photo Classification Challenge",
 
         # Create oracle and CODA selector for this user
         oracle = Oracle(dataset, loss_fn=loss_fn)
-        coda_selector = CODA(dataset)
+        coda_selector = CODA(dataset, 
+                             learning_rate=DEMO_LEARNING_RATE)
 
         image, status, predictions = get_next_coda_image()
         prob_plot = create_probability_chart()
@@ -844,7 +848,8 @@ with gr.Blocks(title="CODA: Wildlife Photo Classification Challenge",
 
         # Create oracle and CODA selector for this user
         oracle = Oracle(dataset, loss_fn=loss_fn)
-        coda_selector = CODA(dataset)
+        coda_selector = CODA(dataset,
+                             learning_rate=DEMO_LEARNING_RATE)
 
         # Reset all displays
         prob_plot = create_probability_chart()