Function get_eval_dataflow

examples/FasterRCNN/data.py:373–396

Args: name (str): name of the dataset to evaluate shard, num_shards: to get subset of evaluation data

(name, shard=0, num_shards=1)

def get_eval_dataflow(name, shard=0, num_shards=1):
    """
    Args:
        name (str): name of the dataset to evaluate
        shard, num_shards: to get subset of evaluation data
    """
    roidbs = DatasetRegistry.get(name).inference_roidbs()
    logger.info("Found {} images for inference.".format(len(roidbs)))

    num_imgs = len(roidbs)
    img_per_shard = num_imgs // num_shards
    img_range = (shard * img_per_shard, (shard + 1) * img_per_shard if shard + 1 < num_shards else num_imgs)

    # no filter for training
    ds = DataFromListOfDict(roidbs[img_range[0]: img_range[1]], ["file_name", "image_id"])

    def f(fname):
        im = cv2.imread(fname, cv2.IMREAD_COLOR)
        assert im is not None, fname
        return im

    ds = MapDataComponent(ds, f, 0)
    # Evaluation itself may be multi-threaded, therefore don't add prefetch here.
    return ds


if __name__ == "__main__":