Python parallel.scatter方法代碼示例

# 需要導入模塊: from mmcv import parallel [as 別名]
# 或者: from mmcv.parallel import scatter [as 別名]
def inference_detector(model, img):
    """Inference image(s) with the detector.

    Args:
        model (nn.Module): The loaded detector.
        imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
            images.

    Returns:
        If imgs is a str, a generator will be returned, otherwise return the
        detection results directly.
    """
    cfg = model.cfg
    device = next(model.parameters()).device  # model device
    # build the data pipeline
    test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
    test_pipeline = Compose(test_pipeline)
    # prepare data
    data = dict(img=img)
    data = test_pipeline(data)
    data = scatter(collate([data], samples_per_gpu=1), [device])[0]
    # forward the model
    with torch.no_grad():
        result = model(return_loss=False, rescale=True, **data)
    return result 

# 需要導入模塊: from mmcv import parallel [as 別名]
# 或者: from mmcv.parallel import scatter [as 別名]
def inference_detector(model, img):
    """Inference image(s) with the detector.

    Args:
        model (nn.Module): The loaded detector.
        imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
            images.

    Returns:
        If imgs is a str, a generator will be returned, otherwise return the
        detection results directly.
    """
    cfg = model.cfg
    device = next(model.parameters()).device  # model device
    # build the data pipeline
    test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
    test_pipeline = Compose(test_pipeline)
    # prepare data
    data = dict(img=img)
    data = test_pipeline(data)
    data = collate([data], samples_per_gpu=1)
    if next(model.parameters()).is_cuda:
        # scatter to specified GPU
        data = scatter(data, [device])[0]
    else:
        # Use torchvision ops for CPU mode instead
        for m in model.modules():
            if isinstance(m, (RoIPool, RoIAlign)):
                if not m.aligned:
                    # aligned=False is not implemented on CPU
                    # set use_torchvision on-the-fly
                    m.use_torchvision = True
        warnings.warn('We set use_torchvision=True in CPU mode.')
        # just get the actual data from DataContainer
        data['img_metas'] = data['img_metas'][0].data

    # forward the model
    with torch.no_grad():
        result = model(return_loss=False, rescale=True, **data)
    return result 

# 需要導入模塊: from mmcv import parallel [as 別名]
# 或者: from mmcv.parallel import scatter [as 別名]
def async_inference_detector(model, img):
    """Async inference image(s) with the detector.

    Args:
        model (nn.Module): The loaded detector.
        imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
            images.

    Returns:
        Awaitable detection results.
    """
    cfg = model.cfg
    device = next(model.parameters()).device  # model device
    # build the data pipeline
    test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
    test_pipeline = Compose(test_pipeline)
    # prepare data
    data = dict(img=img)
    data = test_pipeline(data)
    data = scatter(collate([data], samples_per_gpu=1), [device])[0]

    # We don't restore `torch.is_grad_enabled()` value during concurrent
    # inference since execution can overlap
    torch.set_grad_enabled(False)
    result = await model.aforward_test(rescale=True, **data)
    return result 

# 需要導入模塊: from mmcv import parallel [as 別名]
# 或者: from mmcv.parallel import scatter [as 別名]
def after_train_epoch(self, runner):
        if not self.every_n_epochs(runner, self.interval):
            return
        runner.model.eval()
        results = [None for _ in range(len(self.dataset))]
        if runner.rank == 0:
            prog_bar = mmcv.ProgressBar(len(self.dataset))
        for idx in range(runner.rank, len(self.dataset), runner.world_size):
            data = self.dataset[idx]
            data_gpu = scatter(
                collate([data], samples_per_gpu=1),
                [torch.cuda.current_device()])[0]

            # compute output
            with torch.no_grad():
                result = runner.model(
                    return_loss=False, rescale=True, **data_gpu)
            results[idx] = result

            batch_size = runner.world_size
            if runner.rank == 0:
                for _ in range(batch_size):
                    prog_bar.update()

        if runner.rank == 0:
            print('\n')
            dist.barrier()
            for i in range(1, runner.world_size):
                tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
                tmp_results = mmcv.load(tmp_file)
                for idx in range(i, len(results), runner.world_size):
                    results[idx] = tmp_results[idx]
                os.remove(tmp_file)
            self.evaluate(runner, results)
        else:
            tmp_file = osp.join(runner.work_dir,
                                'temp_{}.pkl'.format(runner.rank))
            mmcv.dump(results, tmp_file)
            dist.barrier()
        dist.barrier() 

# 需要導入模塊: from mmcv import parallel [as 別名]
# 或者: from mmcv.parallel import scatter [as 別名]
def async_inference_detector(model, img):
    """Async inference image(s) with the detector.

    Args:
        model (nn.Module): The loaded detector.
        imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
            images.

    Returns:
        Awaitable detection results.
    """
    cfg = model.cfg
    device = next(model.parameters()).device  # model device
    # build the data pipeline
    test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
    test_pipeline = Compose(test_pipeline)
    # prepare data
    data = dict(img=img)
    data = test_pipeline(data)
    data = scatter(collate([data], samples_per_gpu=1), [device])[0]

    # We don't restore `torch.is_grad_enabled()` value during concurrent
    # inference since execution can overlap
    torch.set_grad_enabled(False)
    result = await model.aforward_test(rescale=True, **data)
    return result


# TODO: merge this method with the one in BaseDetector 

# 需要導入模塊: from mmcv import parallel [as 別名]
# 或者: from mmcv.parallel import scatter [as 別名]
def inference_detector(model, img):
    """Inference image(s) with the detector.

    Args:
        model (nn.Module): The loaded detector.
        imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
            images.

    Returns:
        If imgs is a str, a generator will be returned, otherwise return the
        detection results directly.
    """
    cfg = model.cfg
    device = next(model.parameters()).device  # model device
    # build the data pipeline
    test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
    test_pipeline = Compose(test_pipeline)
    # prepare data
    data = dict(img=img)
    data = test_pipeline(data)
    data = scatter(collate([data], samples_per_gpu=1), [device])[0]
    # forward the model
    with torch.no_grad():
        result = model(return_loss=False, rescale=True, **data)

    return result


# TODO: merge this method with the one in BaseDetector 

# 需要導入模塊: from mmcv import parallel [as 別名]
# 或者: from mmcv.parallel import scatter [as 別名]
def after_train_epoch(self, runner):
        if not self.every_n_epochs(runner, self.interval):
            return
        runner.model.eval()
        results = [None for _ in range(len(self.dataset))]
        prog_bar = mmcv.ProgressBar(len(self.dataset))
        for idx in range(runner.rank, len(self.dataset), runner.world_size):
            data = self.dataset[idx]
            data_gpu = scatter(
                collate([data], samples_per_gpu=1),
                [torch.cuda.current_device()])[0]

            # compute output
            with torch.no_grad():
                result = runner.model(
                    return_loss=False, rescale=True, **data_gpu)
            results[idx] = result

            batch_size = runner.world_size
            for _ in range(batch_size):
                prog_bar.update()

        if runner.rank == 0:
            print('\n')
            self._barrier(runner.rank, runner.world_size)
            for i in range(1, runner.world_size):
                tmp_file = osp.join(runner.work_dir, 'temp_{}.pkl'.format(i))
                tmp_results = mmcv.load(tmp_file)
                for idx in range(i, len(results), runner.world_size):
                    results[idx] = tmp_results[idx]
                os.remove(tmp_file)
            self.evaluate(runner, results)
        else:
            tmp_file = osp.join(runner.work_dir,
                                'temp_{}.pkl'.format(runner.rank))
            mmcv.dump(results, tmp_file)
            self._barrier(runner.rank, runner.world_size)
        self._barrier(runner.rank, runner.world_size) 

# 需要導入模塊: from mmcv import parallel [as 別名]
# 或者: from mmcv.parallel import scatter [as 別名]
def _data_func(data, device_id):
    data = scatter(collate([data], samples_per_gpu=1), [device_id])[0]
    return dict(return_loss=False, rescale=True, **data)