def setup_custom_environment(custom_module_path): """Load custom environment setup from a Python source file and run the setup function. """ module = import_file("fcos_core.utils.env.custom_module", custom_module_path) assert hasattr(module, "setup_environment") and callable( module.setup_environment), ( "Custom environment module defined in {} does not have the " "required callable attribute 'setup_environment'." ).format(custom_module_path) module.setup_environment()
def _load_file(self, f): # catalog lookup if f.startswith("catalog://"): paths_catalog = import_file("fcos_core.config.paths_catalog", self.cfg.PATHS_CATALOG, True) catalog_f = paths_catalog.ModelCatalog.get(f[len("catalog://"):]) self.logger.info("{} points to {}".format(f, catalog_f)) f = catalog_f # download url files if f.startswith("http"): # if the file is a url path, download it and cache it cached_f = cache_url(f) self.logger.info("url {} cached in {}".format(f, cached_f)) f = cached_f # convert Caffe2 checkpoint from pkl if f.endswith(".pkl"): return load_c2_format(self.cfg, f) # load native detectron.pytorch checkpoint loaded = super(DetectronCheckpointer, self)._load_file(f) if "model" not in loaded: loaded = dict(model=loaded) return loaded
def make_data_loader(cfg, is_train=True, is_distributed=False, start_iter=0): num_gpus = get_world_size() #判断gpu数量 if is_train: images_per_batch = cfg.SOLVER.IMS_PER_BATCH #16 每个batch_size的图片是16张 assert (images_per_batch % num_gpus == 0 #判断每个batch_size的图片可以均匀的分到多个gpu上面 ), "SOLVER.IMS_PER_BATCH ({}) must be divisible by the number " "of GPUs ({}) used.".format(images_per_batch, num_gpus) images_per_gpu = images_per_batch // num_gpus shuffle = True num_iters = cfg.SOLVER.MAX_ITER #40000 最大迭代次数不超过40000 else: images_per_batch = cfg.TEST.IMS_PER_BATCH assert (images_per_batch % num_gpus == 0 ), "TEST.IMS_PER_BATCH ({}) must be divisible by the number " "of GPUs ({}) used.".format(images_per_batch, num_gpus) images_per_gpu = images_per_batch // num_gpus shuffle = False if not is_distributed else True num_iters = None start_iter = 0 if images_per_gpu > 1: #提示关于训练过程中的内存不足的问题 logger = logging.getLogger(__name__) logger.warning( "When using more than one image per GPU you may encounter " "an out-of-memory (OOM) error if your GPU does not have " "sufficient memory. If this happens, you can reduce " "SOLVER.IMS_PER_BATCH (for training) or " "TEST.IMS_PER_BATCH (for inference). For training, you must " "also adjust the learning rate and schedule length according " "to the linear scaling rule. See for example: " "https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14" ) #将图片进行分组,仅仅根据两种情形分组,一种是图片的宽/高>1的,一种是其他的. # group images which have similar aspect ratio. In this case, we only # group in two cases: those with width / height > 1, and the other way around, # but the code supports more general grouping strategy aspect_grouping = [1] if cfg.DATALOADER.ASPECT_RATIO_GROUPING else [ ] #True #PATHS_CATALOG=os.path.join(os.path.dirname(__file__), "paths_catalog.py") #找出对应的加载数据集脚本的路径 paths_catalog = import_file("fcos_core.config.paths_catalog", cfg.PATHS_CATALOG, True) #DatasetCatalog 对应的是fcos_core.config.paths_catalog中的DatasetCatalog类,并对其进行实例化. DatasetCatalog = paths_catalog.DatasetCatalog #对应要训练的数据集路径 <class 'fcos_core.config.paths_catalog.DatasetCatalog'> dataset_list = cfg.DATASETS.TRAIN if is_train else cfg.DATASETS.TEST #数据集列表 训练或是测试 对应的列表中的数据集不一样 # train: ("coco_2014_train", "coco_2014_valminusminival") # test: ("coco_2014_minival",) print(dataset_list) transforms = build_transforms(cfg, is_train) #对输入图片进行变换,随机水平分割归一化等操作 datasets = build_dataset(dataset_list, transforms, DatasetCatalog, is_train) data_loaders = [] for dataset in datasets: sampler = make_data_sampler(dataset, shuffle, is_distributed) batch_sampler = make_batch_data_sampler(dataset, sampler, aspect_grouping, images_per_gpu, num_iters, start_iter) collator = BatchCollator(cfg.DATALOADER.SIZE_DIVISIBILITY) num_workers = cfg.DATALOADER.NUM_WORKERS data_loader = torch.utils.data.DataLoader( dataset, num_workers=num_workers, batch_sampler=batch_sampler, collate_fn=collator, ) data_loaders.append(data_loader) if is_train: # during training, a single (possibly concatenated) data_loader is returned assert len(data_loaders) == 1 return data_loaders[0] return data_loaders
def make_data_loader(cfg, is_train=True, is_distributed=False, start_iter=0): num_gpus = get_world_size() if is_train: images_per_batch = cfg.SOLVER.IMS_PER_BATCH assert (images_per_batch % num_gpus == 0 ), "SOLVER.IMS_PER_BATCH ({}) must be divisible by the number " "of GPUs ({}) used.".format(images_per_batch, num_gpus) images_per_gpu = images_per_batch // num_gpus shuffle = True num_iters = cfg.SOLVER.MAX_ITER else: images_per_batch = cfg.TEST.IMS_PER_BATCH assert (images_per_batch % num_gpus == 0 ), "TEST.IMS_PER_BATCH ({}) must be divisible by the number " "of GPUs ({}) used.".format(images_per_batch, num_gpus) images_per_gpu = images_per_batch // num_gpus shuffle = False if not is_distributed else True num_iters = None start_iter = 0 if images_per_gpu > 1: logger = logging.getLogger(__name__) logger.warning( "When using more than one image per GPU you may encounter " "an out-of-memory (OOM) error if your GPU does not have " "sufficient memory. If this happens, you can reduce " "SOLVER.IMS_PER_BATCH (for training) or " "TEST.IMS_PER_BATCH (for inference). For training, you must " "also adjust the learning rate and schedule length according " "to the linear scaling rule. See for example: " "https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14" ) # group images which have similar aspect ratio. In this case, we only # group in two cases: those with width / height > 1, and the other way around, # but the code supports more general grouping strategy aspect_grouping = [1] if cfg.DATALOADER.ASPECT_RATIO_GROUPING else [] paths_catalog = import_file("fcos_core.config.paths_catalog", cfg.PATHS_CATALOG, True) DatasetCatalog = paths_catalog.DatasetCatalog dataset_list = cfg.DATASETS.TRAIN if is_train else cfg.DATASETS.TEST # If bbox aug is enabled in testing, simply set transforms to None and we will apply transforms later transforms = None if not is_train and cfg.TEST.BBOX_AUG.ENABLED else build_transforms( cfg, is_train) datasets = build_dataset(dataset_list, transforms, DatasetCatalog, is_train) data_loaders = [] for dataset in datasets: sampler = make_data_sampler(dataset, shuffle, is_distributed) batch_sampler = make_batch_data_sampler(dataset, sampler, aspect_grouping, images_per_gpu, num_iters, start_iter) collator = BBoxAugCollator() if not is_train and cfg.TEST.BBOX_AUG.ENABLED else \ BatchCollator(cfg.DATALOADER.SIZE_DIVISIBILITY) num_workers = cfg.DATALOADER.NUM_WORKERS data_loader = torch.utils.data.DataLoader( dataset, num_workers=num_workers, batch_sampler=batch_sampler, collate_fn=collator, ) data_loaders.append(data_loader) if is_train: # during training, a single (possibly concatenated) data_loader is returned assert len(data_loaders) == 1 return data_loaders[0] return data_loaders
num_workers=num_workers, batch_sampler=batch_sampler, collate_fn=collator, ) data_loaders.append(data_loader) if is_train: # during training, a single (possibly concatenated) data_loader is returned assert len(data_loaders) == 1 return data_loaders[0] return data_loaders import os from fcos_core.config import defaults as cfg if __name__ == "__main__": PATHS_CATALOG = "/home/sifan/slam-package/FCOS/fcos_core/config/paths_catalog.py" paths_catalog = import_file("fcos_core.config.paths_catalog", PATHS_CATALOG, True) DatasetCatalog = paths_catalog.DatasetCatalog dataset_list = () if True else () is_train = True transforms = build_transforms(cfg, is_train) data = { 'factory': 'COCODataset', 'args': { 'root': 'datasets/coco/train2014', 'ann_file': 'datasets/coco/annotations/instances_train2014.json' } } #factory = getattr(D, data["factory"]) #print(factory)