Question

我希望每个人都做得很好。您能帮我解决以下问题吗？我相信pytorch，opencv等中没有这样的功能，所以我正在尝试手动实现。

上下文：我收集了一批帧并将其推送到GPU，并保持在那里。然后，我有几个网络（YOLO）。为了使它起作用，我需要在GPU上调整图像的大小，使其达到YOLO期望的尺寸，以保持纵横比（有填充用灰色填充图像的其余部分）。按照此处所述完成操作：https://discuss.pytorch.org/t/resize-images-torch-tensor-already-loaded-on-gpu-keeping-their-aspect-ratio/83172/9

我现在需要做的是：重新调整边界框的坐标，使其相对于帧的原始大小，而不是调整给网络进行检测的尺寸。这就是我现在正在做的事情： code

@staticmethod
def rescale_bounding_box(detections: dict, current_dim: int, original_shape: tuple) -> dict:
    """
    Rescale bounding boxes predicted for image(s) of the size current_dim to the original_shape
    :param detections:
    :param current_dim:
    :param original_shape:
    :return:
    """
    original_h, original_w = original_shape
    # Added padding (check if the image was tall of short)
    pad_x = max(original_h - original_w, 0) * (current_dim / max(original_shape))
    pad_y = max(original_w - original_h, 0) * (current_dim / max(original_shape))

    # Image size after padding's been removed
    unpad_h = current_dim - pad_y
    unpad_w = current_dim - pad_x

    output = dict()
    for img_batch_index, predictions in detections.items():
        output[img_batch_index] = list()
        # On each image in the batch there's a number of detections that need to be rescaled
        for prediction in predictions:
            new_left = int((prediction[0] - pad_x // 2) * (original_w / unpad_w))
            new_top = int((prediction[1] - pad_y // 2) * (original_h / unpad_h))
            new_right = int((prediction[2] - pad_x // 2) * (original_w / unpad_w))
            new_bot = int((prediction[3] - pad_y // 2) * (original_h / unpad_h))
            obj_score = round(prediction[4], 4)
            conf = round(prediction[5], 4)
            index = int(prediction[6])

            print("Rescaled:", new_left, new_top, new_right, new_bot)
            # Save modified results
            assert all((new_left < new_right, new_top < new_bot)), "Coordinates rescaled wrong"
            assert all((new_left > 0, new_top > 0, new_right > 0, new_bot > 0)), "Coordinates rescaled wrong"
            assert all((new_right <= original_w, new_bot <= original_h)), "Coordinates rescaled wrong"
            output[img_batch_index].append(
                [new_left, new_top, new_right, new_bot, obj_score, conf, index]
            )

    return output

很遗憾，它没有传递assert语句。我的new_top值通常为<0，new_right可以超出右边缘。

detections-是字典，其中key-批次中图像的索引（对于图像为1），values-列表列表。每个嵌套列表都是网络预测的检测结果。

如果有人可以，请帮我一下。花了很多时间，没有成功。

谢谢。

相对于原始图像尺寸重新调整边框

0 个答案: