Python caffe2.python.core.ScopedName() Examples

def get_net(data_loader, name):
    logger = logging.getLogger(__name__)
    blob_names = data_loader.get_output_names()
    net = core.Net(name)
    net.type = 'dag'
    for gpu_id in range(cfg.NUM_GPUS):
        with core.NameScope('gpu_{}'.format(gpu_id)):
            with core.DeviceScope(muji.OnGPU(gpu_id)):
                for blob_name in blob_names:
                    blob = core.ScopedName(blob_name)
                    workspace.CreateBlob(blob)
                net.DequeueBlobs(
                    data_loader._blobs_queue_name, blob_names)
    logger.info("Protobuf:\n" + str(net.Proto()))

    return net 

def get_net(data_loader, name):
    logger = logging.getLogger(__name__)
    blob_names = data_loader.get_output_names()
    net = core.Net(name)
    net.type = 'dag'
    for gpu_id in range(cfg.NUM_GPUS):
        with core.NameScope('gpu_{}'.format(gpu_id)):
            with core.DeviceScope(muji.OnGPU(gpu_id)):
                for blob_name in blob_names:
                    blob = core.ScopedName(blob_name)
                    workspace.CreateBlob(blob)
                net.DequeueBlobs(
                    data_loader._blobs_queue_name, blob_names)
    logger.info("Protobuf:\n" + str(net.Proto()))

    return net 

def get_net(data_loader, name):
    logger = logging.getLogger(__name__)
    blob_names = data_loader.get_output_names()
    net = core.Net(name)
    net.type = 'dag'
    for gpu_id in range(cfg.NUM_GPUS):
        with core.NameScope('gpu_{}'.format(gpu_id)):
            with core.DeviceScope(muji.OnGPU(gpu_id)):
                for blob_name in blob_names:
                    blob = core.ScopedName(blob_name)
                    workspace.CreateBlob(blob)
                net.DequeueBlobs(
                    data_loader._blobs_queue_name, blob_names)
    logger.info("Protobuf:\n" + str(net.Proto()))

    return net 

def get_net(data_loader, name):
    logger = logging.getLogger(__name__)
    blob_names = data_loader.get_output_names()
    net = core.Net(name)
    net.type = 'dag'
    for gpu_id in range(cfg.NUM_GPUS):
        with core.NameScope('gpu_{}'.format(gpu_id)):
            with core.DeviceScope(muji.OnGPU(gpu_id)):
                for blob_name in blob_names:
                    blob = core.ScopedName(blob_name)
                    workspace.CreateBlob(blob)
                net.DequeueBlobs(
                    data_loader._blobs_queue_name, blob_names)
    logger.info("Protobuf:\n" + str(net.Proto()))

    return net 

def get_net(data_loader, name):
    logger = logging.getLogger(__name__)
    blob_names = data_loader.get_output_names()
    net = core.Net(name)
    net.type = 'dag'
    for gpu_id in range(cfg.NUM_GPUS):
        with core.NameScope('gpu_{}'.format(gpu_id)):
            with core.DeviceScope(muji.OnGPU(gpu_id)):
                for blob_name in blob_names:
                    blob = core.ScopedName(blob_name)
                    workspace.CreateBlob(blob)
                net.DequeueBlobs(
                    data_loader._blobs_queue_name, blob_names)
    logger.info("Protobuf:\n" + str(net.Proto()))

    return net 

def get_net(data_loader, name):
    logger = logging.getLogger(__name__)
    blob_names = data_loader.get_output_names()
    net = core.Net(name)
    net.type = 'dag'
    for gpu_id in range(cfg.NUM_GPUS):
        with core.NameScope('gpu_{}'.format(gpu_id)):
            with core.DeviceScope(muji.OnGPU(gpu_id)):
                for blob_name in blob_names:
                    blob = core.ScopedName(blob_name)
                    workspace.CreateBlob(blob)
                net.DequeueBlobs(
                    data_loader._blobs_queue_name, blob_names)
    logger.info("Protobuf:\n" + str(net.Proto()))

    return net 

def get_net(data_loader, name):
    logger = logging.getLogger(__name__)
    blob_names = data_loader.get_output_names()
    net = core.Net(name)
    net.type = 'dag'
    for gpu_id in range(cfg.NUM_GPUS):
        with core.NameScope('gpu_{}'.format(gpu_id)):
            with core.DeviceScope(muji.OnGPU(gpu_id)):
                for blob_name in blob_names:
                    blob = core.ScopedName(blob_name)
                    workspace.CreateBlob(blob)
                net.DequeueBlobs(
                    data_loader._blobs_queue_name, blob_names)
    logger.info("Protobuf:\n" + str(net.Proto()))

    return net 

def get_net(data_loader, name):
    logger = logging.getLogger(__name__)
    blob_names = data_loader.get_output_names()
    net = core.Net(name)
    net.type = 'dag'
    for gpu_id in range(cfg.NUM_GPUS):
        with core.NameScope('gpu_{}'.format(gpu_id)):
            with core.DeviceScope(muji.OnGPU(gpu_id)):
                for blob_name in blob_names:
                    blob = core.ScopedName(blob_name)
                    workspace.CreateBlob(blob)
                net.DequeueBlobs(
                    data_loader._blobs_queue_name, blob_names)
    logger.info("Protobuf:\n" + str(net.Proto()))

    return net 

def run_net(net):
    workspace.RunNetOnce(net)
    gpu_dev = core.DeviceOption(caffe2_pb2.CUDA, 0)
    name_scope = 'gpu_{}'.format(0)
    with core.NameScope(name_scope):
        with core.DeviceScope(gpu_dev):
            data = workspace.FetchBlob(core.ScopedName('data'))
            return data 

def im_detect_mask(model, im_scale, boxes):
    """Infer instance segmentation masks. This function must be called after
    im_detect_bbox as it assumes that the Caffe2 workspace is already populated
    with the necessary blobs.

    Arguments:
        model (DetectionModelHelper): the detection model to use
        im_scales (list): image blob scales as returned by im_detect_bbox
        boxes (ndarray): R x 4 array of bounding box detections (e.g., as
            returned by im_detect_bbox)

    Returns:
        pred_masks (ndarray): R x K x M x M array of class specific soft masks
            output by the network (must be processed by segm_results to convert
            into hard masks in the original image coordinate space)
    """
    M = cfg.MRCNN.RESOLUTION
    if boxes.shape[0] == 0:
        pred_masks = np.zeros((0, M, M), np.float32)
        return pred_masks

    inputs = {'mask_rois': _get_rois_blob(boxes, im_scale)}
    # Add multi-level rois for FPN
    if cfg.FPN.MULTILEVEL_ROIS:
        _add_multilevel_rois_for_test(inputs, 'mask_rois')

    for k, v in inputs.items():
        workspace.FeedBlob(core.ScopedName(k), v)
    workspace.RunNet(model.mask_net.Proto().name)

    # Fetch masks
    pred_masks = workspace.FetchBlob(
        core.ScopedName('mask_fcn_probs')
    ).squeeze()

    if cfg.MRCNN.CLS_SPECIFIC_MASK:
        pred_masks = pred_masks.reshape([-1, cfg.MODEL.NUM_CLASSES, M, M])
    else:
        pred_masks = pred_masks.reshape([-1, 1, M, M])

    return pred_masks 

def _get_result_blobs(check_blobs):
    ret = {}
    for x in check_blobs:
        sn = core.ScopedName(x)
        if workspace.HasBlob(sn):
            ret[x] = workspace.FetchBlob(sn)
        else:
            ret[x] = None

    return ret 

def _get_result_blobs(check_blobs):
    ret = {}
    for x in check_blobs:
        sn = core.ScopedName(x)
        if workspace.HasBlob(sn):
            ret[x] = workspace.FetchBlob(sn)
        else:
            ret[x] = None

    return ret 

def im_detect_keypoints(model, im_scale, boxes):
    """Infer instance keypoint poses. This function must be called after
    im_detect_bbox as it assumes that the Caffe2 workspace is already populated
    with the necessary blobs.

    Arguments:
        model (DetectionModelHelper): the detection model to use
        im_scales (list): image blob scales as returned by im_detect_bbox
        boxes (ndarray): R x 4 array of bounding box detections (e.g., as
            returned by im_detect_bbox)

    Returns:
        pred_heatmaps (ndarray): R x J x M x M array of keypoint location
            logits (softmax inputs) for each of the J keypoint types output
            by the network (must be processed by keypoint_results to convert
            into point predictions in the original image coordinate space)
    """
    M = cfg.KRCNN.HEATMAP_SIZE
    if boxes.shape[0] == 0:
        pred_heatmaps = np.zeros((0, cfg.KRCNN.NUM_KEYPOINTS, M, M), np.float32)
        return pred_heatmaps

    inputs = {'keypoint_rois': _get_rois_blob(boxes, im_scale)}

    # Add multi-level rois for FPN
    if cfg.FPN.MULTILEVEL_ROIS:
        _add_multilevel_rois_for_test(inputs, 'keypoint_rois')

    for k, v in inputs.items():
        workspace.FeedBlob(core.ScopedName(k), v)
    workspace.RunNet(model.keypoint_net.Proto().name)

    pred_heatmaps = workspace.FetchBlob(core.ScopedName('kps_score')).squeeze()

    # In case of 1
    if pred_heatmaps.ndim == 3:
        pred_heatmaps = np.expand_dims(pred_heatmaps, axis=0)

    return pred_heatmaps 

def im_detect_mask(model, im_scale, boxes):
    """Infer instance segmentation masks. This function must be called after
    im_detect_bbox as it assumes that the Caffe2 workspace is already populated
    with the necessary blobs.

    Arguments:
        model (DetectionModelHelper): the detection model to use
        im_scales (list): image blob scales as returned by im_detect_bbox
        boxes (ndarray): R x 4 array of bounding box detections (e.g., as
            returned by im_detect_bbox)

    Returns:
        pred_masks (ndarray): R x K x M x M array of class specific soft masks
            output by the network (must be processed by segm_results to convert
            into hard masks in the original image coordinate space)
    """
    M = cfg.MRCNN.RESOLUTION
    if boxes.shape[0] == 0:
        pred_masks = np.zeros((0, M, M), np.float32)
        return pred_masks

    inputs = {'mask_rois': _get_rois_blob(boxes, im_scale)}
    # Add multi-level rois for FPN
    if cfg.FPN.MULTILEVEL_ROIS:
        _add_multilevel_rois_for_test(inputs, 'mask_rois')

    for k, v in inputs.items():
        workspace.FeedBlob(core.ScopedName(k), v)
    workspace.RunNet(model.mask_net.Proto().name)

    # Fetch masks
    pred_masks = workspace.FetchBlob(
        core.ScopedName('mask_fcn_probs')
    ).squeeze()

    if cfg.MRCNN.CLS_SPECIFIC_MASK:
        pred_masks = pred_masks.reshape([-1, cfg.MODEL.NUM_CLASSES, M, M])
    else:
        pred_masks = pred_masks.reshape([-1, 1, M, M])

    return pred_masks 

def create_enqueue_blobs(self):
        blob_names = self.get_output_names()
        enqueue_blob_names = [
            '{}_enqueue_{}'.format(b, self._loader_id) for b in blob_names
        ]
        for gpu_id in range(self._num_gpus):
            with c2_utils.NamedCudaScope(gpu_id):
                for blob in enqueue_blob_names:
                    workspace.CreateBlob(core.ScopedName(blob))
        return enqueue_blob_names 

def add_training_inputs(model, roidb=None):
    """Create network input ops and blobs used for training. To be called
    *after* model_builder.create().
    """
    # Implementation notes:
    #   Typically, one would create the input ops and then the rest of the net.
    #   However, creating the input ops depends on loading the dataset, which
    #   can take a few minutes for COCO.
    #   We prefer to avoid waiting so debugging can fail fast.
    #   Thus, we create the net *without input ops* prior to loading the
    #   dataset, and then add the input ops after loading the dataset.
    #   Since we defer input op creation, we need to do a little bit of surgery
    #   to place the input ops at the start of the network op list.
    assert model.train, 'Training inputs can only be added to a trainable model'
    if roidb is not None:
        # To make debugging easier you can set cfg.DATA_LOADER.NUM_THREADS = 1
        model.roi_data_loader = RoIDataLoader(
            roidb,
            num_loaders=cfg.DATA_LOADER.NUM_THREADS,
            minibatch_queue_size=cfg.DATA_LOADER.MINIBATCH_QUEUE_SIZE,
            blobs_queue_capacity=cfg.DATA_LOADER.BLOBS_QUEUE_CAPACITY
        )
    orig_num_op = len(model.net._net.op)
    blob_names = roi_data_minibatch.get_minibatch_blob_names(is_training=True)
    for gpu_id in range(cfg.NUM_GPUS):
        with c2_utils.NamedCudaScope(gpu_id):
            for blob_name in blob_names:
                workspace.CreateBlob(core.ScopedName(blob_name))
            model.net.DequeueBlobs(
                model.roi_data_loader._blobs_queue_name, blob_names
            )
    # A little op surgery to move input ops to the start of the net
    diff = len(model.net._net.op) - orig_num_op
    new_op = model.net._net.op[-diff:] + model.net._net.op[:-diff]
    del model.net._net.op[:]
    model.net._net.op.extend(new_op) 

def create_enqueue_blobs(self):
        blob_names = self.get_output_names()
        enqueue_blob_names = [
            '{}_enqueue_{}'.format(b, self._loader_id) for b in blob_names
        ]
        for gpu_id in range(self._num_gpus):
            with c2_utils.NamedCudaScope(gpu_id):
                for blob in enqueue_blob_names:
                    workspace.CreateBlob(core.ScopedName(blob))
        return enqueue_blob_names 

def run_model_cfg(args, im, check_blobs):
    workspace.ResetWorkspace()
    model, _ = load_model(args)
    with c2_utils.NamedCudaScope(0):
        cls_boxes, cls_segms, cls_keyps = test_engine.im_detect_all(
            model, im, None, None,
        )

    boxes, segms, keypoints, classes = vis_utils.convert_from_cls_format(
        cls_boxes, cls_segms, cls_keyps)

    # sort the results based on score for comparision
    boxes, segms, keypoints, classes = _sort_results(
        boxes, segms, keypoints, classes)

    # write final results back to workspace
    def _ornone(res):
        return np.array(res) if res is not None else np.array([], dtype=np.float32)
    with c2_utils.NamedCudaScope(0):
        workspace.FeedBlob(core.ScopedName('result_boxes'), _ornone(boxes))
        workspace.FeedBlob(core.ScopedName('result_segms'), _ornone(segms))
        workspace.FeedBlob(core.ScopedName('result_keypoints'), _ornone(keypoints))
        workspace.FeedBlob(core.ScopedName('result_classids'), _ornone(classes))

    # get result blobs
    with c2_utils.NamedCudaScope(0):
        ret = _get_result_blobs(check_blobs)

    return ret 

def run_model_cfg(args, im, check_blobs):
    workspace.ResetWorkspace()
    model, _ = load_model(args)
    with c2_utils.NamedCudaScope(0):
        cls_boxes, cls_segms, cls_keyps = test_engine.im_detect_all(
            model, im, None, None
        )

    boxes, segms, keypoints, classes = vis_utils.convert_from_cls_format(
        cls_boxes, cls_segms, cls_keyps
    )

    # sort the results based on score for comparision
    boxes, segms, keypoints, classes = _sort_results(boxes, segms, keypoints, classes)

    # write final results back to workspace
    def _ornone(res):
        return np.array(res) if res is not None else np.array([], dtype=np.float32)

    with c2_utils.NamedCudaScope(0):
        workspace.FeedBlob(core.ScopedName("result_boxes"), _ornone(boxes))
        workspace.FeedBlob(core.ScopedName("result_segms"), _ornone(segms))
        workspace.FeedBlob(core.ScopedName("result_keypoints"), _ornone(keypoints))
        workspace.FeedBlob(core.ScopedName("result_classids"), _ornone(classes))

    # get result blobs
    with c2_utils.NamedCudaScope(0):
        ret = _get_result_blobs(check_blobs)

    return ret 

def run_net(net):
    workspace.RunNetOnce(net)
    gpu_dev = core.DeviceOption(caffe2_pb2.CUDA, 0)
    name_scope = 'gpu_{}'.format(0)
    with core.NameScope(name_scope):
        with core.DeviceScope(gpu_dev):
            data = workspace.FetchBlob(core.ScopedName('data'))
            return data 

def add_training_inputs(model, roidb=None):
    """Create network input ops and blobs used for training. To be called
    *after* model_builder.create().
    """
    # Implementation notes:
    #   Typically, one would create the input ops and then the rest of the net.
    #   However, creating the input ops depends on loading the dataset, which
    #   can take a few minutes for COCO.
    #   We prefer to avoid waiting so debugging can fail fast.
    #   Thus, we create the net *without input ops* prior to loading the
    #   dataset, and then add the input ops after loading the dataset.
    #   Since we defer input op creation, we need to do a little bit of surgery
    #   to place the input ops at the start of the network op list.
    assert model.train, 'Training inputs can only be added to a trainable model'
    if roidb is not None:
        # To make debugging easier you can set cfg.DATA_LOADER.NUM_THREADS = 1
        model.roi_data_loader = RoIDataLoader(
            roidb,
            num_loaders=cfg.DATA_LOADER.NUM_THREADS,
            minibatch_queue_size=cfg.DATA_LOADER.MINIBATCH_QUEUE_SIZE,
            blobs_queue_capacity=cfg.DATA_LOADER.BLOBS_QUEUE_CAPACITY
        )
    orig_num_op = len(model.net._net.op)
    blob_names = roi_data_minibatch.get_minibatch_blob_names(is_training=True)
    for gpu_id in range(cfg.NUM_GPUS):
        with c2_utils.NamedCudaScope(gpu_id):
            for blob_name in blob_names:
                workspace.CreateBlob(core.ScopedName(blob_name))
            model.net.DequeueBlobs(
                model.roi_data_loader._blobs_queue_name, blob_names
            )
    # A little op surgery to move input ops to the start of the net
    diff = len(model.net._net.op) - orig_num_op
    new_op = model.net._net.op[-diff:] + model.net._net.op[:-diff]
    del model.net._net.op[:]
    model.net._net.op.extend(new_op) 

def create_enqueue_blobs(self):
        blob_names = self.get_output_names()
        enqueue_blob_names = [
            '{}_enqueue_{}'.format(b, self._loader_id) for b in blob_names
        ]
        for gpu_id in range(self._num_gpus):
            with c2_utils.NamedCudaScope(gpu_id):
                for blob in enqueue_blob_names:
                    workspace.CreateBlob(core.ScopedName(blob))
        return enqueue_blob_names 

def run_model_cfg(args, im, check_blobs):
    workspace.ResetWorkspace()
    model, _ = load_model(args)
    with c2_utils.NamedCudaScope(0):
        cls_boxes, cls_segms, cls_keyps = test_engine.im_detect_all(
            model, im, None, None,
        )

    boxes, segms, keypoints, classes = vis_utils.convert_from_cls_format(
        cls_boxes, cls_segms, cls_keyps)

    # sort the results based on score for comparision
    boxes, segms, keypoints, classes = _sort_results(
        boxes, segms, keypoints, classes)

    # write final results back to workspace
    def _ornone(res):
        return np.array(res) if res is not None else np.array([], dtype=np.float32)
    with c2_utils.NamedCudaScope(0):
        workspace.FeedBlob(core.ScopedName('result_boxes'), _ornone(boxes))
        workspace.FeedBlob(core.ScopedName('result_segms'), _ornone(segms))
        workspace.FeedBlob(core.ScopedName('result_keypoints'), _ornone(keypoints))
        workspace.FeedBlob(core.ScopedName('result_classids'), _ornone(classes))

    # get result blobs
    with c2_utils.NamedCudaScope(0):
        ret = _get_result_blobs(check_blobs)

    return ret 

def _get_result_blobs(check_blobs):
    ret = {}
    for x in check_blobs:
        sn = core.ScopedName(x)
        if workspace.HasBlob(sn):
            ret[x] = workspace.FetchBlob(sn)
        else:
            ret[x] = None

    return ret 

def im_detect_keypoints(model, im_scale, boxes):
    """Infer instance keypoint poses. This function must be called after
    im_detect_bbox as it assumes that the Caffe2 workspace is already populated
    with the necessary blobs.

    Arguments:
        model (DetectionModelHelper): the detection model to use
        im_scales (list): image blob scales as returned by im_detect_bbox
        boxes (ndarray): R x 4 array of bounding box detections (e.g., as
            returned by im_detect_bbox)

    Returns:
        pred_heatmaps (ndarray): R x J x M x M array of keypoint location
            logits (softmax inputs) for each of the J keypoint types output
            by the network (must be processed by keypoint_results to convert
            into point predictions in the original image coordinate space)
    """
    M = cfg.KRCNN.HEATMAP_SIZE
    if boxes.shape[0] == 0:
        pred_heatmaps = np.zeros((0, cfg.KRCNN.NUM_KEYPOINTS, M, M), np.float32)
        return pred_heatmaps

    inputs = {'keypoint_rois': _get_rois_blob(boxes, im_scale)}

    # Add multi-level rois for FPN
    if cfg.FPN.MULTILEVEL_ROIS:
        _add_multilevel_rois_for_test(inputs, 'keypoint_rois')

    for k, v in inputs.items():
        workspace.FeedBlob(core.ScopedName(k), v)
    workspace.RunNet(model.keypoint_net.Proto().name)

    pred_heatmaps = workspace.FetchBlob(core.ScopedName('kps_score')).squeeze()

    # In case of 1
    if pred_heatmaps.ndim == 3:
        pred_heatmaps = np.expand_dims(pred_heatmaps, axis=0)

    return pred_heatmaps 

def im_detect_mask(model, im_scale, boxes):
    """Infer instance segmentation masks. This function must be called after
    im_detect_bbox as it assumes that the Caffe2 workspace is already populated
    with the necessary blobs.

    Arguments:
        model (DetectionModelHelper): the detection model to use
        im_scales (list): image blob scales as returned by im_detect_bbox
        boxes (ndarray): R x 4 array of bounding box detections (e.g., as
            returned by im_detect_bbox)

    Returns:
        pred_masks (ndarray): R x K x M x M array of class specific soft masks
            output by the network (must be processed by segm_results to convert
            into hard masks in the original image coordinate space)
    """
    M = cfg.MRCNN.RESOLUTION
    if boxes.shape[0] == 0:
        pred_masks = np.zeros((0, M, M), np.float32)
        return pred_masks

    inputs = {'mask_rois': _get_rois_blob(boxes, im_scale)}
    # Add multi-level rois for FPN
    if cfg.FPN.MULTILEVEL_ROIS:
        _add_multilevel_rois_for_test(inputs, 'mask_rois')

    for k, v in inputs.items():
        workspace.FeedBlob(core.ScopedName(k), v)
    workspace.RunNet(model.mask_net.Proto().name)

    # Fetch masks
    pred_masks = workspace.FetchBlob(
        core.ScopedName('mask_fcn_probs')
    ).squeeze()

    if cfg.MRCNN.CLS_SPECIFIC_MASK:
        pred_masks = pred_masks.reshape([-1, cfg.MODEL.NUM_CLASSES, M, M])
    else:
        pred_masks = pred_masks.reshape([-1, 1, M, M])

    return pred_masks 

def run_net(net):
    workspace.RunNetOnce(net)
    gpu_dev = core.DeviceOption(caffe2_pb2.CUDA, 0)
    name_scope = 'gpu_{}'.format(0)
    with core.NameScope(name_scope):
        with core.DeviceScope(gpu_dev):
            data = workspace.FetchBlob(core.ScopedName('data'))
            return data 

def add_training_inputs(model, roidb=None):
    """Create network input ops and blobs used for training. To be called
    *after* model_builder.create().
    """
    # Implementation notes:
    #   Typically, one would create the input ops and then the rest of the net.
    #   However, creating the input ops depends on loading the dataset, which
    #   can take a few minutes for COCO.
    #   We prefer to avoid waiting so debugging can fail fast.
    #   Thus, we create the net *without input ops* prior to loading the
    #   dataset, and then add the input ops after loading the dataset.
    #   Since we defer input op creation, we need to do a little bit of surgery
    #   to place the input ops at the start of the network op list.
    assert model.train, 'Training inputs can only be added to a trainable model'
    if roidb is not None:
        # To make debugging easier you can set cfg.DATA_LOADER.NUM_THREADS = 1
        model.roi_data_loader = RoIDataLoader(
            roidb,
            num_loaders=cfg.DATA_LOADER.NUM_THREADS,
            minibatch_queue_size=cfg.DATA_LOADER.MINIBATCH_QUEUE_SIZE,
            blobs_queue_capacity=cfg.DATA_LOADER.BLOBS_QUEUE_CAPACITY
        )
    orig_num_op = len(model.net._net.op)
    blob_names = roi_data_minibatch.get_minibatch_blob_names(is_training=True)
    for gpu_id in range(cfg.NUM_GPUS):
        with c2_utils.NamedCudaScope(gpu_id):
            for blob_name in blob_names:
                workspace.CreateBlob(core.ScopedName(blob_name))
            model.net.DequeueBlobs(
                model.roi_data_loader._blobs_queue_name, blob_names
            )
    # A little op surgery to move input ops to the start of the net
    diff = len(model.net._net.op) - orig_num_op
    new_op = model.net._net.op[-diff:] + model.net._net.op[:-diff]
    del model.net._net.op[:]
    model.net._net.op.extend(new_op) 

def create_enqueue_blobs(self):
        blob_names = self.get_output_names()
        enqueue_blob_names = [
            '{}_enqueue_{}'.format(b, self._loader_id) for b in blob_names
        ]
        for gpu_id in range(self._num_gpus):
            with c2_utils.NamedCudaScope(gpu_id):
                for blob in enqueue_blob_names:
                    workspace.CreateBlob(core.ScopedName(blob))
        return enqueue_blob_names 

def im_conv_body_only(model, im):
    """Runs `model.conv_body_net` on the given image `im`."""
    im_blob, im_scale_factors = _get_image_blob(im)
    workspace.FeedBlob(core.ScopedName('data'), im_blob)
    workspace.RunNet(model.conv_body_net.Proto().name)
    return im_scale_factors