debug: dff_nmf incorrect factorisation output

yolov8.py

@@ -174,48 +174,35 @@ def dff_nmf(image, target_lyr, n_components):
                                    computation_on_concepts=None)
 
     concepts, batch_explanations, explanations = dff(input_tensor, model, n_components)
-
-    # Getting predictions directly from YOLO
-    with torch.no_grad():
-        results = model(input_tensor)
-
-    # Assuming results is a list, extract the first element
-    detections = results[0]  # The first element should contain the detection data
-
-    # Access detection results
-    #boxes = detections.boxes.xyxy.cpu().numpy()  # Bounding box coordinates (xyxy)
-    #probs = detections.probs.cpu().numpy()      # Confidence scores (probabilities)
-    #classes = detections.classes.cpu().numpy()  # Class IDs
-
-    # Filter detections with confidence score > threshold (e.g., 0.5)
-    #high_conf_indices = probs > 0.5
-    #high_conf_boxes = boxes[high_conf_indices]
-    #high_conf_classes = classes[high_conf_indices]
-    #high_conf_probs = probs[high_conf_indices]
-
-    # Example visualization and output processing
-    fig, ax = plt.subplots(1, figsize=(8, 8))
-    ax.axis("off")
-    ax.imshow(rgb_img_float)
-
-    #for box, cls, prob in zip(high_conf_boxes, high_conf_classes, high_conf_probs):
-     #   x1, y1, x2, y2 = box
-      #  rect = patches.Rectangle((x1, y1), x2 - x1, y2 - y1,
-      #                           linewidth=2, edgecolor='r', facecolor='none')
-      #  ax.add_patch(rect)
-      #  ax.text(x1, y1, f"Class {cls}, Prob {prob:.2f}", color='r', fontsize=12, verticalalignment='top')
-
-    plt.subplots_adjust(left=0, right=1, top=1, bottom=0)
-    fig.canvas.draw()
-    image_array = np.array(fig.canvas.renderer.buffer_rgba())
-    image_resized = cv2.resize(image_array, (640, 640))
-    rgba_channels = cv2.split(image_resized)
-    alpha_channel = rgba_channels[3]
-    rgb_channels = np.stack(rgba_channels[:3], axis=-1)
-
-    visualization = show_factorization_on_image(rgb_img_float, np.transpose(rgb_channels, (2, 0, 1)), image_weight=0.3)
-
-    return rgb_img_float, batch_explanations, visualization
+    print("#################shapes###############")
+    print(concepts.shape, batch_explanations.shape, explanations.shape)
+    results = []
+    for indx in range(explanations[0].shape[0]):
+        upsampled_input =  explanations[0][indx]
+        upsampled_input = torch.tensor(upsampled_input)
+        device = next(model.parameters()).device
+        input_tensor = upsampled_input.unsqueeze(0)
+        input_tensor = input_tensor.unsqueeze(1).repeat(1, 128, 1, 1)   
+        fig, ax = plt.subplots(1, figsize=(8, 8))
+        ax.axis("off")
+        ax.imshow(torch.tensor(batch_explanations[0][indx]).cpu().numpy(), cmap="plasma")  # Display i
+        plt.subplots_adjust(left=0, right=1, top=1, bottom=0)
+        fig.canvas.draw()  # Draw the canvas to make sure the image is rendered
+        image_array = np.array(fig.canvas.renderer.buffer_rgba())  # Convert to numpy array
+        print("____________image_arrya", image_array.shape)
+        image_resized = cv2.resize(image_array, (640, 640))
+        rgba_channels = cv2.split(image_resized)
+        alpha_channel = rgba_channels[3] 
+        rgb_channels = np.stack(rgba_channels[:3], axis=-1)
+        #overlay_img = (alpha_channel[..., None] * image) + ((1 - alpha_channel[..., None]) * rgb_channels)
+        
+        #temp = image_array.reshape((rgb_img_float.shape[0],rgb_img_float.shape[1]) )
+        #visualization = show_factorization_on_image(rgb_img_float, image_array.resize((rgb_img_float.shape)) , image_weight=0.3)
+        visualization = show_factorization_on_image(rgb_img_float, np.transpose(rgb_channels, (2, 0, 1)), image_weight=0.3)
+        results.append(visualization)
+        plt.clf()  
+        
+    return rgb_img_float, batch_explanations, results
 
 
 def visualize_batch_explanations(rgb_img_float, batch_explanations, image_weight=0.7):