Update app.py

app.py

@@ -9,7 +9,6 @@ import numpy as np
 
 # DEFINE MODEL NAME
 model_name = "DinoVdeau_Aina-large-2024_06_12-batch-size32_epochs150_freeze"
-#model_name = "dinov2-large-2024_01_24-with_data_aug_batch-size32_epochs93_freeze"
 checkpoint_name = "lombardata/" + model_name
 
 # Load the model configuration and create the model
@@ -47,12 +46,6 @@ model.to(device)
 def sigmoid(_outputs):
     return 1.0 / (1.0 + np.exp(-_outputs))
 
-def download_thresholds(repo_id, filename):
-    threshold_path = hf_hub_download(repo_id=repo_id, filename=filename)
-    with open(threshold_path, 'r') as threshold_file:
-        thresholds = json.load(threshold_file)
-    return thresholds
-
 def predict(image, slider_threshold=0.5, fixed_thresholds=None):
     # Preprocess the image
     processor = AutoImageProcessor.from_pretrained(checkpoint_name)
@@ -75,12 +68,9 @@ def predict(image, slider_threshold=0.5, fixed_thresholds=None):
 
     return slider_results, fixed_threshold_labels_str
 
-def predict_wrapper(image, slider_threshold=0.5):
-    # Download thresholds from the model repository
-    thresholds = download_thresholds(checkpoint_name, "threshold.json")
-    
+def predict_wrapper(image, slider_threshold=0.5):    
     # Get predictions from the predict function using both the slider and fixed thresholds
-    slider_results, fixed_threshold_results = predict(image, slider_threshold, thresholds)
+    slider_results, fixed_threshold_results = predict(image, slider_threshold)
     
     # Return both sets of predictions for Gradio outputs
     return slider_results, fixed_threshold_results