def evaluate(self): if self._distributed: comm.synchronize() self._predictions = comm.gather(self._predictions, dst=0) self._predictions = list(itertools.chain(*self._predictions)) if not comm.is_main_process(): return {} if len(self._predictions) == 0: self._logger.warning( "[COCOEvaluator] Did not receive valid predictions.") return {} if self._output_dir: PathManager.mkdirs(self._output_dir) file_path = os.path.join(self._output_dir, "instances_predictions.pth") with PathManager.open(file_path, "wb") as f: torch.save(self._predictions, f) self._results = OrderedDict() self._eval_predictions(set(self._tasks)) # Copy so the caller can do whatever with results return copy.deepcopy(self._results)
def evaluate(self): if self._distributed: comm.synchronize() self._predictions = comm.gather(self._predictions, dst=0) self._predictions = list(itertools.chain(*self._predictions)) self._targets = comm.gather(self._targets, dst=0) self._targets = list(itertools.chain(*self._targets)) if not comm.is_main_process(): return {} if len(self._predictions) == 0: self._logger.warning("[ClassificationEvaluator] Did not receive valid predictions.") return {} if self._output_dir: PathManager.mkdirs(self._output_dir) file_path = os.path.join(self._output_dir, "instances_predictions.pth") with PathManager.open(file_path, "wb") as f: torch.save(self._predictions, f) self._results = OrderedDict() assert len(self._predictions) == len(self._targets) if self._predictions[0] is not None: self._eval_classification_accuracy() if self._dump: _dump_to_markdown(self._dump_infos) # Copy so the caller can do whatever with results return copy.deepcopy(self._results)
def convert_to_coco_json(dataset_name, output_file, allow_cached=True): """ Converts dataset into COCO format and saves it to a json file. dataset_name must be registered in DatasetCatalog and in cvpods's standard format. Args: dataset_name: reference from the config file to the catalogs must be registered in DatasetCatalog and in cvpods's standard format output_file: path of json file that will be saved to allow_cached: if json file is already present then skip conversion """ # TODO: The dataset or the conversion script *may* change, # a checksum would be useful for validating the cached data PathManager.mkdirs(os.path.dirname(output_file)) with file_lock(output_file): if PathManager.exists(output_file) and allow_cached: logger.info( f"Cached annotations in COCO format already exist: {output_file}" ) else: logger.info( f"Converting dataset annotations in '{dataset_name}' to COCO format ...)" ) coco_dict = convert_to_coco_dict(dataset_name) with PathManager.open(output_file, "w") as json_file: logger.info( f"Caching annotations in COCO format: {output_file}") json.dump(coco_dict, json_file)
def default_setup(cfg, args): """ Perform some basic common setups at the beginning of a job, including: 1. Set up the cvpods logger 2. Log basic information about environment, cmdline arguments, and config 3. Backup the config to the output directory Args: cfg (BaseConfig): the full config to be used args (argparse.NameSpace): the command line arguments to be logged """ output_dir = cfg.OUTPUT_DIR if comm.is_main_process() and output_dir: PathManager.mkdirs(output_dir) rank = comm.get_rank() # setup_logger(output_dir, distributed_rank=rank, name="cvpods") logger = setup_logger(output_dir, distributed_rank=rank) logger.info("Rank of current process: {}. World size: {}".format( rank, comm.get_world_size())) logger.info("Environment info:\n" + collect_env_info()) logger.info("Command line arguments: " + str(args)) if hasattr(args, "config_file") and args.config_file != "": logger.info("Contents of args.config_file={}:\n{}".format( args.config_file, PathManager.open(args.config_file, "r").read())) adjust_config(cfg) logger.info("Running with full config:\n{}".format(cfg)) base_config = cfg.__class__.__base__() logger.info("different config with base class:\n{}".format( cfg.diff(base_config))) # if comm.is_main_process() and output_dir: # # Note: some of our scripts may expect the existence of # # config.yaml in output directory # path = os.path.join(output_dir, "config.yaml") # with PathManager.open(path, "w") as f: # f.write(cfg.dump()) # logger.info("Full config saved to {}".format(os.path.abspath(path))) # make sure each worker has a different, yet deterministic seed if specified seed = seed_all_rng(None if cfg.SEED < 0 else cfg.SEED + rank) # save seed to config for dump cfg.SEED = seed # cudnn benchmark has large overhead. It shouldn't be used considering the small size of # typical validation set. if not (hasattr(args, "eval_only") and args.eval_only): torch.backends.cudnn.benchmark = cfg.CUDNN_BENCHMARK return cfg, logger
def after_step(self): if self._profiler is None: return self._profiler.__exit__(None, None, None) PathManager.mkdirs(self._output_dir) out_file = os.path.join( self._output_dir, "profiler-trace-iter{}.json".format(self.trainer.iter)) if "://" not in out_file: self._profiler.export_chrome_trace(out_file) else: # Support non-posix filesystems with tempfile.TemporaryDirectory(prefix="cvpods_profiler") as d: tmp_file = os.path.join(d, "tmp.json") self._profiler.export_chrome_trace(tmp_file) with open(tmp_file) as f: content = f.read() with PathManager.open(out_file, "w") as f: f.write(content)
def evaluate(self): if self._distributed: comm.synchronize() self._predictions = comm.gather(self._predictions, dst=0) self._predictions = list(itertools.chain(*self._predictions)) if not comm.is_main_process(): return {} if len(self._predictions) == 0: self._logger.warning( "[COCOEvaluator] Did not receive valid predictions.") return {} if self._output_dir: PathManager.mkdirs(self._output_dir) file_path = os.path.join(self._output_dir, "instances_predictions.pth") with PathManager.open(file_path, "wb") as f: torch.save(self._predictions, f) self._results = OrderedDict() if "proposals" in self._predictions[0]: self._eval_box_proposals() if "instances" in self._predictions[0]: self._eval_predictions(set(self._tasks)) if self._dump: extra_infos = { "title": os.path.basename(os.getcwd()), "seed": self.cfg.SEED, } _dump_to_markdown(extra_infos, self._dump_infos) # Copy so the caller can do whatever with results return copy.deepcopy(self._results)
def setup_logger(output=None, distributed_rank=0, *, color=True, name="cvpods", abbrev_name=None): """ Initialize the cvpods logger and set its verbosity level to "INFO". Args: output (str): a file name or a directory to save log. If None, will not save log file. If ends with ".txt" or ".log", assumed to be a file name. Otherwise, logs will be saved to `output/log.txt`. name (str): the root module name of this logger abbrev_name (str): an abbreviation of the module, to avoid long names in logs. Set to "" to not log the root module in logs. By default, will abbreviate "cvpods" to "c2" and leave other modules unchanged. Returns: logging.Logger: a logger """ logger = logging.getLogger(name) logger.setLevel(logging.DEBUG) logger.propagate = False if abbrev_name is None: abbrev_name = "pods" if name == "cvpods" else name plain_formatter = logging.Formatter( "[%(asctime)s] %(name)s %(levelname)s: %(message)s", datefmt="%m/%d %H:%M:%S") # stdout logging: master only if distributed_rank == 0: ch = logging.StreamHandler(stream=sys.stdout) ch.setLevel(logging.DEBUG) if color: formatter = _ColorfulFormatter( colored("[%(asctime)s %(name)s]: ", "green") + "%(message)s", datefmt="%m/%d %H:%M:%S", root_name=name, abbrev_name=str(abbrev_name), ) else: formatter = plain_formatter ch.setFormatter(formatter) logger.addHandler(ch) # file logging: all workers if output is not None: if output.endswith(".txt") or output.endswith(".log"): filename = output else: filename = os.path.join(output, "log.txt") if distributed_rank > 0: filename = filename + ".rank{}".format(distributed_rank) PathManager.mkdirs(os.path.dirname(filename)) fh = logging.StreamHandler(_cached_log_stream(filename)) fh.setLevel(logging.DEBUG) fh.setFormatter(plain_formatter) logger.addHandler(fh) return logger
def default_setup(cfg, args): """ Perform some basic common setups at the beginning of a job, including: 1. Set up the cvpods logger 2. Log basic information about environment, cmdline arguments, and config 3. Backup the config to the output directory Args: cfg (BaseConfig): the full config to be used args (argparse.NameSpace): the command line arguments to be logged """ output_dir = cfg.OUTPUT_DIR if comm.is_main_process() and output_dir: PathManager.mkdirs(output_dir) rank = comm.get_rank() # setup_logger(output_dir, distributed_rank=rank, name="cvpods") logger = setup_logger(output_dir, distributed_rank=rank) logger.info("Rank of current process: {}. World size: {}".format( rank, comm.get_world_size())) logger.info("Environment info:\n" + collect_env_info()) logger.info("Command line arguments: " + str(args)) if hasattr(args, "config_file") and args.config_file != "": logger.info("Contents of args.config_file={}:\n{}".format( args.config_file, PathManager.open(args.config_file, "r").read())) logger.info("Running with full config:\n{}".format(cfg)) base_config = cfg.__class__.__base__() logger.info("different config with base class:\n{}".format( cfg.show_diff(base_config))) # if comm.is_main_process() and output_dir: # # Note: some of our scripts may expect the existence of # # config.yaml in output directory # path = os.path.join(output_dir, "config.yaml") # with PathManager.open(path, "w") as f: # f.write(cfg.dump()) # logger.info("Full config saved to {}".format(os.path.abspath(path))) # make sure each worker has a different, yet deterministic seed if specified seed_all_rng(None if cfg.SEED < 0 else cfg.SEED + rank) # cudnn benchmark has large overhead. It shouldn't be used considering the small size of # typical validation set. if not (hasattr(args, "eval_only") and args.eval_only): torch.backends.cudnn.benchmark = cfg.CUDNN_BENCHMARK # dynamic adjust batch_size, steps according to world size base_world_size = int(cfg.SOLVER.IMS_PER_BATCH / cfg.SOLVER.IMS_PER_DEVICE) world_size = comm.get_world_size() ratio = world_size / base_world_size cfg.SOLVER.IMS_PER_BATCH = int(ratio * cfg.SOLVER.IMS_PER_BATCH) cfg.SOLVER.LR_SCHEDULER.MAX_ITER = int(cfg.SOLVER.LR_SCHEDULER.MAX_ITER / ratio) # Divided by scale ratio when using iterations rather than epochs if cfg.SOLVER.LR_SCHEDULER.MAX_EPOCH is None: cfg.SOLVER.LR_SCHEDULER.STEPS = list( (int(step / ratio) for step in cfg.SOLVER.LR_SCHEDULER.STEPS)) cfg.SOLVER.CHECKPOINT_PERIOD = int(cfg.SOLVER.CHECKPOINT_PERIOD / ratio) cfg.TEST.EVAL_PERIOD = int(cfg.TEST.EVAL_PERIOD / ratio) cfg.SOLVER.OPTIMIZER.BASE_LR = ratio * cfg.SOLVER.OPTIMIZER.BASE_LR assert cfg.SOLVER.IMS_PER_BATCH / cfg.SOLVER.IMS_PER_DEVICE == world_size return cfg, logger
def evaluate(self): """ Evaluates standard semantic segmentation metrics (http://cocodataset.org/#stuff-eval): * Mean intersection-over-union averaged across classes (mIoU) * Frequency Weighted IoU (fwIoU) * Mean pixel accuracy averaged across classes (mACC) * Pixel Accuracy (pACC) """ if self._distributed: comm.synchronize() conf_matrix_list = comm.all_gather(self._conf_matrix) self._predictions = comm.all_gather(self._predictions) self._predictions = list(itertools.chain(*self._predictions)) if not comm.is_main_process(): return self._conf_matrix = np.zeros_like(self._conf_matrix) for conf_matrix in conf_matrix_list: self._conf_matrix += conf_matrix if self._output_dir: PathManager.mkdirs(self._output_dir) file_path = os.path.join(self._output_dir, "sem_seg_predictions.json") with PathManager.open(file_path, "w") as f: f.write(json.dumps(self._predictions)) acc = np.zeros(self._num_classes, dtype=np.float) iou = np.zeros(self._num_classes, dtype=np.float) tp = self._conf_matrix.diagonal()[:-1].astype(np.float) pos_gt = np.sum(self._conf_matrix[:-1, :-1], axis=0).astype(np.float) class_weights = pos_gt / np.sum(pos_gt) pos_pred = np.sum(self._conf_matrix[:-1, :-1], axis=1).astype(np.float) acc_valid = pos_gt > 0 acc[acc_valid] = tp[acc_valid] / pos_gt[acc_valid] iou_valid = (pos_gt + pos_pred) > 0 union = pos_gt + pos_pred - tp iou[acc_valid] = tp[acc_valid] / union[acc_valid] macc = np.sum(acc) / np.sum(acc_valid) miou = np.sum(iou) / np.sum(iou_valid) fiou = np.sum(iou * class_weights) pacc = np.sum(tp) / np.sum(pos_gt) res = {} res["mIoU"] = 100 * miou res["fwIoU"] = 100 * fiou res["mACC"] = 100 * macc res["pACC"] = 100 * pacc if self._output_dir: file_path = os.path.join(self._output_dir, "sem_seg_evaluation.pth") with PathManager.open(file_path, "wb") as f: torch.save(res, f) results = OrderedDict({"sem_seg": res}) small_table = create_small_table(res) self._logger.info("Evaluation results for sem_seg: \n" + small_table) if self._dump: dump_info_one_task = { "task": "sem_seg", "tables": [small_table], } _dump_to_markdown([dump_info_one_task]) return results