Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
workaround for large overlapping bboxes
Dillon DuPont0836bb7e8f83
diff --git a/libs/som/som/detect.py b/libs/som/som/detect.pyindex 41ab9ca3e7..79e648864f 100644--- a/libs/som/som/detect.py+++ b/libs/som/som/detect.py@@ -232,17 +232,31 @@ class OmniParser:],)- # Merge detections using NMSif elements and text_elements:- # Get all bounding boxes and scores+ # Filter out non-OCR elements that have OCR elements with center points colliding with them+ filtered_elements = []+ for elem in elements: # elements at this point contains only non-OCR elements+ should_keep = True+ for text_elem in text_elements:+ # Calculate center point of the text element+ center_x = (text_elem.bbox.x1 + text_elem.bbox.x2) / 2+ center_y = (text_elem.bbox.y1 + text_elem.bbox.y2) / 2++ # Check if this center point is inside the non-OCR element+ if (center_x >= elem.bbox.x1 and center_x <= elem.bbox.x2 and+ center_y >= elem.bbox.y1 and center_y <= elem.bbox.y2):+ should_keep = False+ break++ if should_keep:+ filtered_elements.append(elem)+ elements = filtered_elements++ # Merge detections using NMSall_elements = elements + text_elementsboxes = torch.tensor([elem.bbox.coordinates for elem in all_elements])scores = torch.tensor([elem.confidence for elem in all_elements])-- # Apply NMS with iou_thresholdkeep_indices = torchvision.ops.nms(boxes, scores, iou_threshold)-- # Keep only the elements that passed NMSelements = [all_elements[i] for i in keep_indices]else:# Just add text elements to the list if IOU doesn't need to be applieddiff --git a/libs/som/som/visualization.py b/libs/som/som/visualization.pyindex 5c270c2825..038af0f5ae 100644--- a/libs/som/som/visualization.py+++ b/libs/som/som/visualization.py@@ -174,22 +174,31 @@ class BoxAnnotator:lambda: (x1 - box_width - spacing, y2 + spacing),]- def check_collision(x, y):- """Check if a label box collides with any existing ones or is inside bbox."""+ def check_occlusion(x, y):+ """Check if a label box occludes any existing ones or is inside bbox."""# First check if it's inside the bounding boxif is_inside_bbox(x, y):return True# Then check collision with other labelsnew_box = (x, y, x + box_width, y + box_height)+ label_width = new_box[2] - new_box[0]+ label_height = new_box[3] - new_box[1]+for used_box in used_areas:if not (new_box[2] < used_box[0] # new box is left of used boxor new_box[0] > used_box[2] # new box is right of used boxor new_box[3] < used_box[1] # new box is above used box- or new_box[1] > used_box[3]- ): # new box is below used box- return True+ or new_box[1] > used_box[3] # new box is below used box+ ):+ # Calculate dimensions of the used box+ used_box_width = used_box[2] - used_box[0]+ used_box_height = used_box[3] - used_box[1]++ # Only consider as collision if used box is NOT more than 5x bigger in both dimensions+ if not (used_box_width > 5 * label_width and used_box_height > 5 * label_height):+ return Truereturn False# Try each position until we find one without collision@@ -201,7 +210,7 @@ class BoxAnnotator:# Ensure position is within image boundsif x < 0 or y < 0 or x + box_width > image.width or y + box_height > image.height:continue- if not check_collision(x, y):+ if not check_occlusion(x, y):label_x = xlabel_y = ybreak