adding code code for counting, but still buggy so is commented

inference.py

@@ -153,6 +153,7 @@ model = init_detector(config_file, checkpoint_file, device='cuda:0')  # or devic
 model.dataset_meta['palette'] = model.dataset_meta['palette'] + model.dataset_meta['palette'][-23:]
 model.dataset_meta['classes'] = classes
 print(model.cfg.visualizer)
+
 # init visualizer(run the block only once in jupyter notebook)
 visualizer = VISUALIZERS.build(model.cfg.visualizer)
 visualizer.img_save_dir ='temp'
@@ -165,12 +166,16 @@ palette = visualizer.dataset_meta.get('palette', None)
 
 print(len(classes))
 print(len(palette))
+
+
+
 def inference_frame_serial(image, visualize = True):
     #start = time()
     result = inference_detector(model, image)
     #print(f'inference time: {time()-start}')
     # show the results
     if visualize:
+        
         visualizer.add_datasample(
         'result',
         image,
@@ -178,6 +183,7 @@ def inference_frame_serial(image, visualize = True):
         draw_gt = None,
         show=False
         )
+       
         frame = visualizer.get_image()
     else:
         frame = None

metrics.py

@@ -1,8 +1,56 @@
 import numpy as np
 import matplotlib.pyplot as plt
 
+import numpy as np 
+def mask_to_boxes(mask):
+    """ Convert a boolean (Height x Width) mask into a (N x 4) array of NON-OVERLAPPING bounding boxes
+    surrounding "islands of truth" in the mask.  Boxes indicate the (Left, Top, Right, Bottom) bounds
+    of each island, with Right and Bottom being NON-INCLUSIVE (ie they point to the indices AFTER the island).
 
-def get_top_predictions(prediction = None, threshold = 0.7):
+    This algorithm (Downright Boxing) does not necessarily put separate connected components into
+    separate boxes.
+
+    You can "cut out" the island-masks with
+        boxes = mask_to_boxes(mask)
+        island_masks = [mask[t:b, l:r] for l, t, r, b in boxes]
+    """
+    max_ix = max(s+1 for s in mask.shape)   # Use this to represent background
+    # These arrays will be used to carry the "box start" indices down and to the right.
+    x_ixs = np.full(mask.shape, fill_value=max_ix)
+    y_ixs = np.full(mask.shape, fill_value=max_ix)
+
+    # Propagate the earliest x-index in each segment to the bottom-right corner of the segment
+    for i in range(mask.shape[0]):
+        x_fill_ix = max_ix
+        for j in range(mask.shape[1]):
+            above_cell_ix = x_ixs[i-1, j] if i>0 else max_ix
+            still_active = mask[i, j] or ((x_fill_ix != max_ix) and (above_cell_ix != max_ix))
+            x_fill_ix = min(x_fill_ix, j, above_cell_ix) if still_active else max_ix
+            x_ixs[i, j] = x_fill_ix
+
+    # Propagate the earliest y-index in each segment to the bottom-right corner of the segment
+    for j in range(mask.shape[1]):
+        y_fill_ix = max_ix
+        for i in range(mask.shape[0]):
+            left_cell_ix = y_ixs[i, j-1] if j>0 else max_ix
+            still_active = mask[i, j] or ((y_fill_ix != max_ix) and (left_cell_ix != max_ix))
+            y_fill_ix = min(y_fill_ix, i, left_cell_ix) if still_active else max_ix
+            y_ixs[i, j] = y_fill_ix
+
+    # Find the bottom-right corners of each segment
+    new_xstops = np.diff((x_ixs != max_ix).astype(np.int32), axis=1, append=False)==-1
+    new_ystops = np.diff((y_ixs != max_ix).astype(np.int32), axis=0, append=False)==-1
+    corner_mask = new_xstops & new_ystops
+    y_stops, x_stops = np.array(np.nonzero(corner_mask))
+
+    # Extract the boxes, getting the top-right corners from the index arrays
+    x_starts = x_ixs[y_stops, x_stops]
+    y_starts = y_ixs[y_stops, x_stops]
+    ltrb_boxes = np.hstack([x_starts[:, None], y_starts[:, None], x_stops[:, None]+1, y_stops[:, None]+1])
+    return ltrb_boxes
+
+
+def get_top_predictions(prediction = None, threshold = 0.1):
     if prediction is None:
         return None, None
     else:
@@ -141,9 +189,17 @@ def _calculate_dist_estimate(bbox1, bbox2, labels, class_sizes = None, measureme
 # 3 x2 (right, higher pixel number)
 # 4 y2 (bottom, higher pixel number)
 
+
 def process_results_for_plot(predictions = None, threshold = 0.5, classes = None,
                              class_sizes = None, dangerous_distance = 100):
     
+    # Attempt to create bounding boxes for humans(surfers) detected.  
+    # mask = predictions.pred_panoptic_seg.sem_seg[0]
+    # print(np.unique(mask))
+    # mask = mask >2000
+    # bboxes = mask_to_boxes(mask)
+    # bboxes = [box for box in bboxes if box[2]*box[3]>100]
+    
     top_pred = get_top_predictions(predictions, threshold = threshold)
     top_pred = add_class_labels(top_pred, class_labels = classes)
     top_pred = add_class_sizes(top_pred, class_sizes = class_sizes)
@@ -160,6 +216,7 @@ def process_results_for_plot(predictions = None, threshold = 0.5, classes = None
             'shark_sighted': top_pred['shark_n'] > 0,
             'human_sighted': top_pred['human_n'] > 0,
             'shark_n': top_pred['shark_n'],
+            #'human_n': max(top_pred['human_n'],len(bboxes)-top_pred['shark_n']),
             'human_n': top_pred['human_n'],
             'human_and_shark': (top_pred['shark_n'] > 0) and (top_pred['human_n'] > 0),
             'dangerous_dist': min_dist['dangerous_dist'],