Junhao Huang

> 您好上面图片中展示的是我自己用摄像头拍摄的照片再模型中的可视化结果，是因为我用摄像头拍摄图片中的停车位是斜的导致出现这样的结果？ 是的。 > 您对解决这种情况有什么好的idea呢？ 可以参考我们之前的一个工作 [https://cslinzhang.github.io/deepps/](https://cslinzhang.github.io/deepps/) ，通过标定多台摄像机合成鸟瞰环视图。 > 是要拍摄图片重新训练得到自己的训练权重还是说我将摄像头置于图像上方拍垂直的图片呢？ 我们的方法无法处理非俯视视角的图片。把摄像头置于上方垂直向下拍也是一种方法，理论上可行。

Did you run your training on windows? It looks similar to this [issue](https://discuss.pytorch.org/t/cant-pickle-local-object-dataloader-init-locals-lambda/31857). You can try the solutions inside, replacing lambda with a normally defined function, or setting `num_workers` to...

ps2.0 数据中不包含泊车位标记点形状信息的标注。 上图你看到的形状标注是代码根据 ps2.0 泊车位信息初始化出来的，并非正确的标注，仅仅是提供参考方便标注人员进行标注。 正确的标注是 [label](https://drive.google.com/open?id=1o6yXxc3RjIs6r01LtwMS_zH91Tk9BFRB)，在 README 中有。 L 型标记点的标注方法可参考论文 Section 2 关于 orientation 的解释。

Hello, Anil. In DMPR-PS, we only consider two types of marking-point shape, L-shaped marking-point and T-shaped marking-point. Thus we treat regression of marking-point shape as a binary classification problem and...

Hello, Anil. Your sugestions on modifying the neural network architechture are all feasible. I think these modifications will lead to a small decrease of detection performance but an improvement of...

Hello Anil. DMPR-PS is unable to detect slant type parking-slots due to its mechanism. We excluded slant type parking-slots from dataset during training and testing.

You misunderstood the output results of `calc_precision_recall`. This function adjusts thresholds automatically and produce the curve of precision-recall. You can plot the curve and pick any point of them as...

The threshold I was talking about is the confidence threshold. Anyway, here are the specific steps to reproduce the results. 1. Download dataset and weights. 2. Start visdom server with...

> 您好，请问用监控摄像头里的图片制作数据集从而代替AVM环视图以及PS2.0的数据集，然而我发现我这样提取出来的图片不是垂直的停车位，这样的话用您的标注工具手动输入一些信息的话，能用您这个网络训练吗？ 理论上不能，这个方法接受的输入是俯视视角的泊车位图片。 > 或者说我现在将摄像头仅仅垂直的放在若干个停车位的上方，这样的话采集过来的图片能用该网络跑吗？ 如果摄像头没有畸变，理论上可以。

Average precision is a metric different from precision and recall. Take a look at [https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Average_precision](https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Average_precision) for details. If you wish to reproduce the precision recall in the paper, please refer...