diff --git a/predict/predict_yolo11seg.py b/predict/predict_yolo11seg.py index 9cdeb50..ad90d72 100644 --- a/predict/predict_yolo11seg.py +++ b/predict/predict_yolo11seg.py @@ -95,7 +95,7 @@ class InferenceResult: class YOLOSegmentationInference: """YOLO分割模型推理工具""" - def __init__(self, model_path: str, device: Optional[str] = None): + def __init__(self, model_path: Optional[str] = None, device: Optional[str] = None): """ 初始化推理工具 @@ -105,6 +105,7 @@ class YOLOSegmentationInference: """ self.model_path = model_path self.device = device + self.conf_threshold = 0.25 self.model = None self.class_names = [] self.clean_memory_per_count = 500 @@ -128,6 +129,11 @@ class YOLOSegmentationInference: (64, 64, 64), # 浅灰色 ] + def set_model_info(self, model_path, device, conf_threshold) : + self.model_path = model_path + self.device = device + self.conf_threshold = conf_threshold + def load_model(self) -> bool: """ 加载YOLO分割模型 @@ -136,7 +142,7 @@ class YOLOSegmentationInference: 加载成功返回True，否则返回False """ try: - print(f"正在加载模型: {self.model_path}") + print(f"正在加载模型: {self.model_path} 置信度：{self.conf_threshold}") self.model = YOLO(self.model_path) # 设置设备 @@ -638,7 +644,33 @@ class YOLOSegmentationInference: except Exception as e: print(f"处理目录失败: {e}") return results + + def get_model_info(self, pile_dict, road_dict, image_path) : + tmp_image_path = smb_tool.standardized_path(image_path) + img_file_name = tmp_image_path.split('/')[-1] + road_data = get_road_info(road_dict, pile_dict, img_file_name) + print(f"road_data={road_data}") + + # 获取当前脚本文件所在的目录 + script_dir = os.path.dirname(__file__) + # 构建模型文件的绝对路径 + asphalt_model_path = os.path.abspath(os.path.join(script_dir, '..', 'pt_save', 'asphalt20260212_0.391.pt')) + cream_model_path = os.path.abspath(os.path.join(script_dir, '..', 'pt_save', 'asphalt20260212_0.391.pt')) + + if road_data : + road_type_cn = road_data['路面类型（沥青/水泥/砂石）'] + if road_type_cn == '沥青' : + road_type = "asphalt" + return 0.391, asphalt_model_path + elif road_type_cn == '水泥' : + road_type = "cement" + return 0.1, cream_model_path + elif road_type_cn == '砾石' : + road_type = "gravel" + return 0.391, asphalt_model_path + return 0.391, asphalt_model_path + def process_image_directory_share_dir_circle(self, task_id, current_time, input_dir_list, user_name, pwd, output_dir: Optional[str] = None, conf_threshold: float = 0.25, iou_threshold: float = 0.5, save_mask: bool = False, save_label: bool = False, show: bool = False, @@ -685,15 +717,32 @@ class YOLOSegmentationInference: print(f"找到 {len(image_files)} 个图片文件") + # 推送识别数据到共享目录 + tmpConfig = get_conf(input_dir, user_name, pwd) + pile_dict = get_pile_dict(input_dir, user_name, pwd) + road_dict = get_road_dict(f"{tmpConfig['ip']}/{tmpConfig['share']}/{tmpConfig['excel_dir']}", user_name, pwd) + # 处理每张图片 for idx, image_path in enumerate(image_files): - # for image_path in image_files: + # 检查路面类型，切换模型 + if not self.model : + model_conf_threshold, model_path = self.get_model_info(pile_dict, road_dict, image_path) + try: + device = torch.device("cuda" if torch.cuda.is_available() else "cpu") + print(f"设备情况：{device}") + except Exception as e: + print(f"获取设备失败: {e}") + self.set_model_info(model_path, device, model_conf_threshold) + # 加载模型 + if not self.load_model(): + return + result = self.process_single_image_share_dir( image_path=image_path, user_name=user_name, pwd=pwd, output_dir=tmp_output_dir, - conf_threshold=conf_threshold, + conf_threshold=self.conf_threshold, iou_threshold=iou_threshold, save_mask=save_mask, save_label=save_label, @@ -715,18 +764,17 @@ class YOLOSegmentationInference: memory_info = process.memory_info() mem_usage = memory_info.rss / 1024 / 1024 # 返回MB print(f"清理后，内存使用: {mem_usage:.2f} MB") - - # 推送识别数据到共享目录 - tmpConfig = get_conf(input_dir, user_name, pwd) - pile_dict = get_pile_dict(input_dir, user_name, pwd) - road_dict = get_road_dict(f"{tmpConfig['ip']}/{tmpConfig['share']}/{tmpConfig['excel_dir']}", user_name, pwd) + + # 处理输出目录的文件格式 process_dir(road_dict, pile_dict, tmp_output_dir) + # 识别生成的文件压缩成zip zip_folder_shutil(tmp_output_dir) move_file_shutil(tmp_output_dir+".zip", tmp_output_dir + f"/{task_id}.zip") remote_dir = f"{tmpConfig['dir']}_识别/{task_id}/{current_time}" scanner.upload_directory(tmp_output_dir, config['share'], remote_dir=remote_dir) - del_file_shutil(tmp_output_dir) + # del_file_shutil(tmp_output_dir) + # 更新识别任务状态为已结束 DB_CONFIG = { "dbname": "postgres", @@ -896,33 +944,8 @@ def predict_images(pt_name, zip_url, output_dir="predictions", conf_threshold=0. def predict_images_share_dir(task_id, pt_name, zip_url, user_name, pwd, output_dir="predictions", conf_threshold=0.25, save_json=False): - # 本地测试模式 - 请根据实际情况修改以下路径 - # local_model_path = r"D:\project\verification\ultralytics-main\model\script\seg\pt\test.pttest.pt" - local_model_path = r"../pt_save/road_crack.pt" - local_output_dir = output_dir - # zip_url = "meta_data/ai_train_platform/train.zip" - - try: - # 加载模型 - print(f"正在加载模型: {local_model_path}") - device = torch.device("cuda" if torch.cuda.is_available() else "cpu") - print(f"模型已加载到 {device}") - except Exception as e: - print(f"处理目录失败: {e}") - - inference = YOLOSegmentationInference( - model_path=local_model_path, - device=device - ) - - # 加载模型 - if not inference.load_model(): - return - - - # zip_url = r"D:\project\verification\ultralytics-main\model\script\seg\test_seg_pic" - + inference = YOLOSegmentationInference() result_save = [] conf_threshold = 0.25 iou_threshold = 0.5 diff --git a/util/smb_tool.py b/util/smb_tool.py index 6a37bc4..db38107 100644 --- a/util/smb_tool.py +++ b/util/smb_tool.py @@ -1050,7 +1050,7 @@ def main(): # for i, path in enumerate(imgPaths, 1): # print(f"{i}. {path}") - # # 读取excel + # 读取excel # full_path = scanner.build_full_path(share_path=config['share'], file_path='西南计算机\\AA县\\每公里指标明细表（北碚）.xls') # df = scanner.read_excel(full_path) # rows = scanner.process_all_rows(df) @@ -1099,23 +1099,25 @@ def main(): # str = '\\\\192.168.110.114\\share_File\\西南计算机/北碚报送数据/3.25/图像类\\C071500109B\\Images_识别/77/20251120172316/77.zip' # print(f"standardized_path(str)={standardized_path(str)}") - road_dict_for_width = {} - df = pd.read_excel('D:/devForBdzlWork/ai-train_platform/predictions/C005500155A/nl_yy_glzb (2)_识别宽度数据读取.xls') - rows = scanner.process_all_rows(df, columns=['线路编码','区划代码','方向(上行/下行)','识别宽度（米）']) - for i, row in enumerate(rows, 1): - data = row['data'] - if pd.notna(data['线路编码']) : - up_or_down = 'A' - if data['方向(上行/下行)'] == '下行' : - up_or_down = 'B' - key = f"{data['线路编码']}{str(int(data['区划代码']))}{up_or_down}" - width = data.get('识别宽度（米）') - if width : - road_dict_for_width[key] = width - print('读取excel') + # road_dict_for_width = {} + # df = pd.read_excel('D:/devForBdzlWork/ai-train_platform/predictions/C005500155A/nl_yy_glzb (2)_识别宽度数据读取.xls') + # rows = scanner.process_all_rows(df, columns=['线路编码','区划代码','方向(上行/下行)','识别宽度（米）']) + # for i, row in enumerate(rows, 1): + # data = row['data'] + # if pd.notna(data['线路编码']) : + # up_or_down = 'A' + # if data['方向(上行/下行)'] == '下行' : + # up_or_down = 'B' + # key = f"{data['线路编码']}{str(int(data['区划代码']))}{up_or_down}" + # width = data.get('识别宽度（米）') + # if width : + # road_dict_for_width[key] = width + # print('读取excel') road_dict = {} - df = pd.read_excel('D:/devForBdzlWork/ai-train_platform/predictions/C005500155A/每公里指标明细表-农村公路技术状况评定结果表-500155.xls') + # df = pd.read_excel('D:/devForBdzlWork/ai-train_platform/predictions/C005500155A/每公里指标明细表-农村公路技术状况评定结果表-500155.xls') + # df = pd.read_csv('D:/devForBdzlWork/ai-train_platform/predictions/jlp/20260227090742/公里指标数据导出-jlp.csv') + df = pd.read_excel('D:/devForBdzlWork/ai-train_platform/predictions/jlp/20260227090742/每公里指标明细表-jlp.xlsx') rows = scanner.process_all_rows(df, columns=['线路编码','区划代码','识别宽度（米）','方向(上行/下行)','技术等级','路面类型（沥青/水泥/砂石）','起桩号（米）','止桩号（米）']) for i, row in enumerate(rows, 1): data = row['data'] @@ -1124,14 +1126,14 @@ def main(): if data['方向(上行/下行)'] == '下行' : up_or_down = 'B' key = f"{data['线路编码']}{str(int(data['区划代码']))}{up_or_down}" - width = road_dict_for_width.get(key) + width = road_dict.get(key) if width : data['识别宽度（米）'] = width if road_dict.get(key) : road_dict[key].append(row) else : road_dict[key] = [row] - print('读取excel') + print('读取excel/csv') if __name__ == "__main__": main() \ No newline at end of file diff --git a/util/yolo2pix_new.py b/util/yolo2pix_new.py index ec9ebe4..89afc8c 100644 --- a/util/yolo2pix_new.py +++ b/util/yolo2pix_new.py @@ -69,9 +69,14 @@ def draw_grid_on_image(image_path, grid_cells, cell_size=(GRID_WIDTH, GRID_HEIGH overlay = image.copy() for cname, nums in grid_cells.items(): color = (np.random.randint(64,255),np.random.randint(64,255),np.random.randint(64,255)) - for num in nums[0]: - x1,y1,x2,y2 = num_to_coord(num, cols, cell_w, cell_h) - cv2.rectangle(overlay,(x1,y1),(x2,y2),color,-1) + for cell in nums : + covered_cells = cell.get("covered_cells") + for num in covered_cells: + x1,y1,x2,y2 = num_to_coord(num, cols, cell_w, cell_h) + cv2.rectangle(overlay,(x1,y1),(x2,y2),color,-1) + # for num in nums[0]: + # x1,y1,x2,y2 = num_to_coord(num, cols, cell_w, cell_h) + # cv2.rectangle(overlay,(x1,y1),(x2,y2),color,-1) cv2.addWeighted(overlay,0.4,image,0.6,0,image) for i in range(0, w, cell_w): cv2.line(image,(i,0),(i,h),(100,100,100),1) @@ -95,15 +100,17 @@ def detect_road_type_from_content(label_file): if kw in content: return "gravel" return "gravel" -def get_road_info(summary_data, road_dict, pile_dict, img_file_name): +def get_road_info(road_dict, pile_dict, img_file_name): """获取路线信息""" parts = pile_dict.get(img_file_name) if parts : road_code = parts[0] road_info = road_dict.get(road_code) if road_info : - pile_no_min = convert_special_format(summary_data[0][0]) * 1000 - pile_no_max = convert_special_format(summary_data[len(summary_data)-1][0]) * 1000 + pile_dict_vals = list(pile_dict.values()) + pile_dict_vals_len = len(pile_dict_vals) + pile_no_min = convert_special_format(pile_dict_vals[0][1]) * 1000 + pile_no_max = convert_special_format(pile_dict_vals[pile_dict_vals_len-1][1]) * 1000 if pile_no_max < pile_no_min : #上行下行 tmp = pile_no_max pile_no_max = pile_no_min @@ -216,9 +223,19 @@ def yoloseg_to_grid_share_dir(road_dict,pile_dict,image_path,label_file,grid_wid pile_no_tmp = f"桩号:K000{pile_no}" result_lines.append(f"{cname} {pile_no_tmp} {ROAD_TYPE_EN_TO_CN.get(road_type, 'xx')} {ids_str}") if cname not in all_class_cells: all_class_cells[cname]=set() - cell_info.append(covered_cells) - cell_info.append([max_x - min_x, max_y - min_y]) + # cell_info.append(covered_cells) + # cell_info.append([max_x - min_x, max_y - min_y]) + # all_class_cells[cname] = cell_info + + if all_class_cells[cname] : + cell_info = all_class_cells[cname] + cell_info.append({ + "covered_cells":covered_cells, + "width": max_x - min_x, + "height": max_y - min_y + }) all_class_cells[cname] = cell_info + return '\n'.join(result_lines), all_class_cells, road_type, rows * cols def yoloseg_to_grid(image_path,label_file,cover_ratio=COVER_RATIO): @@ -323,11 +340,11 @@ def in_interval(increment, cur_pile_no, tmp_start, tmp_end) : return 0 # 指定间隔区间，输出基本信息+灾害数据 -def process_info(road_dict,pile_dict,summary_data,image_path,current_time,interval=10,dir="output",cell_area=CELL_AREA,grid_width=GRID_WIDTH,grid_height=GRID_HEIGHT) : +def process_info(road_dict,pile_dict,summary_data,current_time,interval=10,dir="output",cell_area=CELL_AREA,grid_width=GRID_WIDTH,grid_height=GRID_HEIGHT) : process_info_data = [] if summary_data: - img_file_name = os.path.basename(image_path) - road_data = get_road_info(summary_data, road_dict, pile_dict, img_file_name) + img_file_name = list(pile_dict.keys())[0] + road_data = get_road_info(road_dict, pile_dict, img_file_name) identify_width = road_data.get('识别宽度（米）', '3.6') up_or_down = road_data.get('方向(上行/下行)', '上行') road_code = pile_dict.get(img_file_name)[0] @@ -431,7 +448,8 @@ def process_info(road_dict,pile_dict,summary_data,image_path,current_time,interv break # 同列汇总 10m一个区间--对应5张图 - column_sums = [f"{(sum(column)/(interval / 2)):0.2f}" for column in zip(*subRows)] + tmp_interval = round((tmp_end - tmp_start) * 1000) + column_sums = [f"{(sum(column)/(tmp_interval / 2)):0.2f}" for column in zip(*subRows)] row += column_sums # f.write(','.join(row)+'\n') row += ['','','','','','','','','','','','','','',''] @@ -541,6 +559,7 @@ def process_dir(road_dict,pile_dict,dir="output",cell_area=CELL_AREA,cell_width= # 解压 # 读取桩号映射 # 遍历图片 + image_path = None summary_data = [] for root,_,files in os.walk(dir): for file in files: @@ -556,14 +575,17 @@ def process_dir(road_dict,pile_dict,dir="output",cell_area=CELL_AREA,cell_width= with open(grid_txt_path,'w',encoding='utf-8') as f: f.write(out_txt) # 生成网格可视化 - # draw_grid_on_image(image_path,class_cells,cell_size=(GRID_WIDTH, GRID_HEIGHT),save_path=os.path.splitext(image_path)[0]+"_grid.jpg") + draw_grid_on_image(image_path,class_cells,cell_size=(GRID_WIDTH, GRID_HEIGHT),save_path=os.path.splitext(image_path)[0]+"_grid.jpg") # 统计各类面积 - counts = {k:[len(v[0])*cell_area, v[1][0], v[1][1]] for k,v in class_cells.items()} + # counts = {k:[len(v[0])*cell_area, v[1][0], v[1][1]] for k,v in class_cells.items()} + counts = {k:[[len(v_child.get("covered_cells"))*cell_area, v_child.get("width"), v_child.get("height")] for v_child in v] for k,v in class_cells.items()} # total_area = sum(counts.values()) # 灾害总面积比例 merged_set = set([]) for k,v in class_cells.items() : - merged_set = merged_set.union(v[0]) + # merged_set = merged_set.union(v[0]) + for v_child in v: + merged_set = merged_set.union(v_child.get("covered_cells")) total_area = len(merged_set) # 桩号 路线编号 @@ -580,24 +602,24 @@ def process_dir(road_dict,pile_dict,dir="output",cell_area=CELL_AREA,cell_width= current_time = datetime.now().strftime("%Y%m%d%H%M%S") # 写桩号问题列表.txt - process_damage_detail_txt(road_dict, pile_dict, dir, summary_data, image_path, current_time) + process_damage_detail_txt(road_dict, pile_dict, dir, summary_data, current_time) # 灾害数据.txt - process_damage_txt(road_dict, pile_dict, dir, summary_data, image_path, current_time) + process_damage_txt(road_dict, pile_dict, dir, summary_data, current_time) # 病害明细列表.xlsx - img_file_path = process_damage_detail_excel(road_dict, pile_dict, dir, cell_area, cell_width, cell_height, summary_data, image_path) + process_damage_detail_excel(road_dict, pile_dict, dir, cell_area, cell_width, cell_height, summary_data) # 综合明细表.xlsx - process_damage_composite_excel(road_dict, pile_dict, summary_data, image_path, current_time, img_file_path) + process_damage_composite_excel(road_dict, pile_dict, dir, summary_data, current_time) -def process_damage_composite_excel(road_dict, pile_dict, summary_data, image_path, current_time, img_file_path): +def process_damage_composite_excel(road_dict, pile_dict, dir, summary_data, current_time): print("输出:综合明细表.xlsx") heads = ['路线编码','起点','终点','车道编码','上下行','公路等级','路面类型','PQI','PQI等级','DR(%)','PCI','PCI等级','IRI','RQI','RQI等级','RD','RDI','RDI等级','SMTD','PBI','PBI等级','WR','PWI','PWI等级','备注'] - data1 = process_info(road_dict,pile_dict,summary_data,image_path,current_time,10) - data2 = process_info(road_dict,pile_dict,summary_data,image_path,current_time,100) - data3 = process_info(road_dict,pile_dict,summary_data,image_path,current_time,1000) + data1 = process_info(road_dict,pile_dict,summary_data,current_time,10) + data2 = process_info(road_dict,pile_dict,summary_data,current_time,100) + data3 = process_info(road_dict,pile_dict,summary_data,current_time,1000) excel_data = [ { @@ -619,13 +641,13 @@ def process_damage_composite_excel(road_dict, pile_dict, summary_data, image_pat 'data': data3 } ] - create_multiple_sheets_with_multiple_headers(img_file_path + '/excel/综合明细表.xlsx', excel_data) + create_multiple_sheets_with_multiple_headers(f"{dir}/excel/综合明细表.xlsx", excel_data) -def process_damage_detail_txt(road_dict, pile_dict, dir, summary_data, image_path, current_time): +def process_damage_detail_txt(road_dict, pile_dict, dir, summary_data, current_time): if summary_data: - img_file_name = os.path.basename(image_path) - road_data = get_road_info(summary_data, road_dict, pile_dict, img_file_name) + img_file_name = list(pile_dict.keys())[0] + road_data = get_road_info(road_dict, pile_dict, img_file_name) road_code = pile_dict.get(img_file_name)[0] road_type = summary_data[0][3] @@ -645,20 +667,22 @@ def process_damage_detail_txt(road_dict, pile_dict, dir, summary_data, image_pat else: keys = list(CLASS_MAP_GRAVEL.keys()) for k in keys: - row.append(f"{counts.get(k,[0,0,0])[0]:.2f}") + # row.append(f"{counts.get(k,[0,0,0])[0]:.2f}") + sum_count = sum(count[0] for count in counts.get(k, [[0, 0, 0]])) + row.append(f"{sum_count:.2f}") f.write(','.join(row)+'\n') + print(f"输出完成: {out_file}") -def process_damage_detail_excel(road_dict, pile_dict, dir, cell_area, cell_width, cell_height, summary_data, image_path): +def process_damage_detail_excel(road_dict, pile_dict, dir, cell_area, cell_width, cell_height, summary_data): print("输出:病害明细列表.xlsx") os.makedirs(f"{dir}/excel", exist_ok=True) headers = ['序号','路线编码','方向','桩号','路面类型','病害名称','程度','长度(m)',' 宽度(m)',' 面积(㎡)',' 横向位置','备注'] data_list = [] if summary_data: - img_file_path = os.path.dirname(image_path) - img_file_name = os.path.basename(image_path) - road_data = get_road_info(summary_data, road_dict, pile_dict, img_file_name) + img_file_name = list(pile_dict.keys())[0] + road_data = get_road_info(road_dict, pile_dict, img_file_name) road_code, pile_no, road_type = detect_road_type_from_road_dict(road_dict, pile_dict, img_file_name) identify_width = road_data.get('识别宽度（米）', '3.6') up_or_down = road_data.get('方向(上行/下行)', '上行') @@ -666,18 +690,18 @@ def process_damage_detail_excel(road_dict, pile_dict, dir, cell_area, cell_width for data in summary_data: damage_data = data[2] for attr_name, attr_value in damage_data.items(): - excel_data = [excel_index, road_code, up_or_down, f"K000{data[0]}", ROAD_TYPE_EN_TO_CN.get(road_type), attr_name, '', attr_value[1]*cell_width, attr_value[2]*cell_height, attr_value[0], '', ''] - data_list.append(excel_data) + for attr_value_child in attr_value : + excel_data = [excel_index, road_code, up_or_down, f"K000{data[0]}", ROAD_TYPE_EN_TO_CN.get(road_type), attr_name, '', attr_value_child[1]*cell_width, attr_value_child[2]*cell_height, attr_value_child[0], '', ''] + data_list.append(excel_data) all_data = [headers] + data_list - smb_tool.write_to_excel_pandas(all_data, img_file_path + '/excel/病害明细列表.xlsx') - return img_file_path + smb_tool.write_to_excel_pandas(all_data, f"{dir}/excel/病害明细列表.xlsx") -def process_damage_txt(road_dict, pile_dict, dir, summary_data, image_path, current_time): +def process_damage_txt(road_dict, pile_dict, dir, summary_data, current_time): if summary_data: - img_file_name = os.path.basename(image_path) - road_data = get_road_info(summary_data, road_dict, pile_dict, img_file_name) + img_file_name = list(pile_dict.keys())[0] + road_data = get_road_info(road_dict, pile_dict, img_file_name) identify_width = road_data.get('识别宽度（米）', '3.6') up_or_down = road_data.get('方向(上行/下行)', '上行') road_code = pile_dict.get(img_file_name)[0] @@ -780,14 +804,17 @@ def process_damage_txt(road_dict, pile_dict, dir, summary_data, image_path, curr else: keys = list(CLASS_MAP_GRAVEL.keys()) for k in keys: - tmp_row.append(counts.get(k, [0,0,0])[0]) + # tmp_row.append(counts.get(k, [0,0,0])[0]) + sum_count = sum(count[0] for count in counts.get(k, [[0, 0, 0]])) + tmp_row.append(sum_count) subRows.append(tmp_row) index = index + 1 else : break # 同列汇总 10m一个区间--对应5张图 - column_sums = [f"{(sum(column)/5):0.2f}" for column in zip(*subRows)] + tmp_interval = round((tmp_end - tmp_start) * 1000) + column_sums = [f"{(sum(column)/tmp_interval):0.2f}" for column in zip(*subRows)] row += column_sums f.write(','.join(row)+'\n') else : @@ -879,10 +906,11 @@ def get_road_dict(local_dir): dict: 路线编码到路线信息的映射字典 """ # 查找匹配的Excel文件 - pattern = os.path.join(local_dir, '每公里指标明细表*.xls') - found_paths = glob.glob(pattern) + pattern_xls = os.path.join(local_dir, '每公里指标明细表*.xls') + pattern_xlsx = os.path.join(local_dir, '每公里指标明细表*.xlsx') + found_paths = glob.glob(pattern_xls) + glob.glob(pattern_xlsx) - print(f"\n找到 {len(found_paths)} 个 '每公里指标明细表*.xls' 文件:") + print(f"\n找到 {len(found_paths)} 个 '每公里指标明细表*.xls/xlsx' 文件:") for i, path in enumerate(found_paths, 1): print(f"{i}. {path}") @@ -961,7 +989,7 @@ if __name__=="__main__": # calc_cell_area, calc_grid_width, calc_grid_height = calc_grid_param(2048, 4096, 3.6, 2) # print(f"calc_cell_area={calc_cell_area}, calc_grid_width={calc_grid_width}, calc_grid_height={calc_grid_height}") - output_dir = "D:/devForBdzlWork/ai-train_platform/predictions/C234500155A" + output_dir = "D:/devForBdzlWork/ai-train_platform/predictions/jlp/20260227090742" pile_dict = get_pile_dict(output_dir) road_dict = get_road_dict(output_dir) process_dir(road_dict, pile_dict, output_dir)