Python mmcv.runner.get_dist_info() Examples

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def get_root_logger(save_dir, log_level=logging.INFO, filename="log.txt"):
    logger = logging.getLogger()
    if not logger.hasHandlers():
        logging.basicConfig(
            format='%(asctime)s - %(levelname)s - %(message)s',
            level=log_level)
    rank, _ = get_dist_info()
    if rank != 0:
        logger.setLevel('ERROR')
    if save_dir:
        fh = logging.FileHandler(os.path.join(save_dir, filename))
        fh.setLevel(log_level)
        formatter = logging.Formatter("%(asctime)s - %(levelname)s: %(message)s")
        fh.setFormatter(formatter)
        logger.addHandler(fh)
        if rank != 0:
            fh.setLevel('ERROR')

    return logger 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results 

def get_root_logger(log_level=logging.INFO):
    logger = logging.getLogger()
    if not logger.hasHandlers():
        logging.basicConfig(
            format='%(asctime)s - %(levelname)s - %(message)s',
            level=log_level)
    rank, _ = get_dist_info()
    if rank != 0:
        logger.setLevel('ERROR')
    return logger 

def multi_gpu_test(model, data_loader, tmpdir=None, gpu_collect=False):
    """Test model with multiple gpus.

    This method tests model with multiple gpus and collects the results
    under two different modes: gpu and cpu modes. By setting 'gpu_collect=True'
    it encodes results to gpu tensors and use gpu communication for results
    collection. On cpu mode it saves the results on different gpus to 'tmpdir'
    and collects them by the rank 0 worker.

    Args:
        model (nn.Module): Model to be tested.
        data_loader (nn.Dataloader): Pytorch data loader.
        tmpdir (str): Path of directory to save the temporary results from
            different gpus under cpu mode.
        gpu_collect (bool): Option to use either gpu or cpu to collect results.

    Returns:
        list: The prediction results.
    """
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    if gpu_collect:
        results = collect_results_gpu(results, len(dataset))
    else:
        results = collect_results_cpu(results, len(dataset), tmpdir)
    return results 

def build_dataloader(dataset,
                     imgs_per_gpu,
                     workers_per_gpu,
                     num_gpus=1,
                     dist=True,
                     **kwargs):
    if dist:
        rank, world_size = get_dist_info()
        sampler = DistributedGroupSampler(dataset, imgs_per_gpu, world_size,
                                          rank)
        batch_size = imgs_per_gpu
        num_workers = workers_per_gpu
    else:
        if not kwargs.get('shuffle', True):
            sampler = None
        else:
            sampler = GroupSampler(dataset, imgs_per_gpu)
        batch_size = num_gpus * imgs_per_gpu
        num_workers = num_gpus * workers_per_gpu

    data_loader = DataLoader(
        dataset,
        batch_size=batch_size,
        sampler=sampler,
        num_workers=num_workers,
        collate_fn=partial(collate, samples_per_gpu=imgs_per_gpu),
        pin_memory=False,
        **kwargs)

    return data_loader 

def get_root_logger(log_level=logging.INFO):
    logger = logging.getLogger()
    if not logger.hasHandlers():
        logging.basicConfig(
            format='%(asctime)s - %(levelname)s - %(message)s',
            level=log_level)
    rank, _ = get_dist_info()
    if rank != 0:
        logger.setLevel('ERROR')
    return logger 

def collect_results(result_part, size, tmpdir=None):
    rank, world_size = get_dist_info()
    # create a tmp dir if it is not specified
    if tmpdir is None:
        MAX_LEN = 512
        # 32 is whitespace
        dir_tensor = torch.full((MAX_LEN, ),
                                32,
                                dtype=torch.uint8,
                                device='cuda')
        if rank == 0:
            tmpdir = tempfile.mkdtemp()
            tmpdir = torch.tensor(
                bytearray(tmpdir.encode()), dtype=torch.uint8, device='cuda')
            dir_tensor[:len(tmpdir)] = tmpdir
        dist.broadcast(dir_tensor, 0)
        tmpdir = dir_tensor.cpu().numpy().tobytes().decode().rstrip()
    else:
        mmcv.mkdir_or_exist(tmpdir)
    # dump the part result to the dir
    mmcv.dump(result_part, osp.join(tmpdir, 'part_{}.pkl'.format(rank)))
    dist.barrier()
    # collect all parts
    if rank != 0:
        return None
    else:
        # load results of all parts from tmp dir
        part_list = []
        for i in range(world_size):
            part_file = osp.join(tmpdir, 'part_{}.pkl'.format(i))
            part_list.append(mmcv.load(part_file))
        # sort the results
        ordered_results = []
        for res in zip(*part_list):
            ordered_results.extend(list(res))
        # the dataloader may pad some samples
        ordered_results = ordered_results[:size]
        # remove tmp dir
        shutil.rmtree(tmpdir)
        return ordered_results 

def collect_results(result_part, size, tmpdir=None):
    rank, world_size = get_dist_info()
    # create a tmp dir if it is not specified
    if tmpdir is None:
        MAX_LEN = 512
        # 32 is whitespace
        dir_tensor = torch.full((MAX_LEN, ),
                                32,
                                dtype=torch.uint8,
                                device='cuda')
        if rank == 0:
            tmpdir = tempfile.mkdtemp()
            tmpdir = torch.tensor(
                bytearray(tmpdir.encode()), dtype=torch.uint8, device='cuda')
            dir_tensor[:len(tmpdir)] = tmpdir
        dist.broadcast(dir_tensor, 0)
        tmpdir = dir_tensor.cpu().numpy().tobytes().decode().rstrip()
    else:
        mmcv.mkdir_or_exist(tmpdir)
    # dump the part result to the dir
    mmcv.dump(result_part, osp.join(tmpdir, 'part_{}.pkl'.format(rank)))
    dist.barrier()
    # collect all parts
    if rank != 0:
        return None
    else:
        # load results of all parts from tmp dir
        part_list = []
        for i in range(world_size):
            part_file = osp.join(tmpdir, 'part_{}.pkl'.format(i))
            part_list.append(mmcv.load(part_file))
        # sort the results
        ordered_results = []
        for res in zip(*part_list):
            ordered_results.extend(list(res))
        # the dataloader may pad some samples
        ordered_results = ordered_results[:size]
        # remove tmp dir
        shutil.rmtree(tmpdir)
        return ordered_results 

def build_dataloader(dataset,
                     imgs_per_gpu,
                     workers_per_gpu,
                     num_gpus=1,
                     dist=True,
                     shuffle=True,
                     **kwargs):
    if dist:
        rank, world_size = get_dist_info()
        if shuffle:
            sampler = DistributedGroupSampler(dataset, imgs_per_gpu,
                                              world_size, rank)
        else:
            sampler = DistributedSampler(
                dataset, world_size, rank, shuffle=False)
        batch_size = imgs_per_gpu
        num_workers = workers_per_gpu
    else:
        sampler = GroupSampler(dataset, imgs_per_gpu) if shuffle else None
        batch_size = num_gpus * imgs_per_gpu
        num_workers = num_gpus * workers_per_gpu

    data_loader = DataLoader(
        dataset,
        batch_size=batch_size,
        sampler=sampler,
        num_workers=num_workers,
        collate_fn=partial(collate, samples_per_gpu=imgs_per_gpu),
        pin_memory=False,
        **kwargs)

    return data_loader 

def collect_results_gpu(result_part, size):
    rank, world_size = get_dist_info()
    # dump result part to tensor with pickle
    part_tensor = torch.tensor(
        bytearray(pickle.dumps(result_part)), dtype=torch.uint8, device='cuda')
    # gather all result part tensor shape
    shape_tensor = torch.tensor(part_tensor.shape, device='cuda')
    shape_list = [shape_tensor.clone() for _ in range(world_size)]
    dist.all_gather(shape_list, shape_tensor)
    # padding result part tensor to max length
    shape_max = torch.tensor(shape_list).max()
    part_send = torch.zeros(shape_max, dtype=torch.uint8, device='cuda')
    part_send[:shape_tensor[0]] = part_tensor
    part_recv_list = [
        part_tensor.new_zeros(shape_max) for _ in range(world_size)
    ]
    # gather all result part
    dist.all_gather(part_recv_list, part_send)

    if rank == 0:
        part_list = []
        for recv, shape in zip(part_recv_list, shape_list):
            part_list.append(
                pickle.loads(recv[:shape[0]].cpu().numpy().tobytes()))
        # sort the results
        ordered_results = []
        for res in zip(*part_list):
            ordered_results.extend(list(res))
        # the dataloader may pad some samples
        ordered_results = ordered_results[:size]
        return ordered_results 

def build_dataloader(dataset,
                     imgs_per_gpu,
                     workers_per_gpu,
                     num_gpus=1,
                     dist=True,
                     **kwargs):
    shuffle = kwargs.get('shuffle', True)
    if dist:
        rank, world_size = get_dist_info()
        if shuffle:
            sampler = DistributedGroupSampler(dataset, imgs_per_gpu,
                                              world_size, rank)
        else:
            sampler = DistributedSampler(
                dataset, world_size, rank, shuffle=False)
        batch_size = imgs_per_gpu
        num_workers = workers_per_gpu
    else:
        sampler = GroupSampler(dataset, imgs_per_gpu) if shuffle else None
        batch_size = num_gpus * imgs_per_gpu
        num_workers = num_gpus * workers_per_gpu

    data_loader = DataLoader(
        dataset,
        batch_size=batch_size,
        sampler=sampler,
        num_workers=num_workers,
        collate_fn=partial(collate, samples_per_gpu=imgs_per_gpu),
        pin_memory=False,
        **kwargs)

    return data_loader