Tong Zhu (朱桐)

I found the codes in Backprop is nothing wrong. Actually, binary classification via cross entropy with softmax has a very simple derivative formula, which is `yhat - labels`. You can...

附议。precision翻译成查准率是比较符合的（也有其它版本翻译成精准率），而accuracy的一般概念应该是准确率。现在的版本确实容易产生混淆。

因为用了DDP，需要更详细的错误信息才能定位问题。请先确认下库和版本是否和Readme对应。

嗨您好，感谢您对本项目的关注~ 论文中的图是一个示意图，可以根据需要编一个case，然后参考这里的代码进行绘制：https://matplotlib.org/stable/gallery/images_contours_and_fields/image_annotated_heatmap.html#sphx-glr-gallery-images-contours-and-fields-image-annotated-heatmap-py 如果是需要真实case的具体值，则需要hook这里的代码（比如print一下啥的），打印中间值：https://github.com/Spico197/DocEE/blob/a32b6f8bf0b2fe28b9942b0b53eff461abf561ba/dee/models/trigger_aware.py#L595

Hi there, thank you very much for using this software~ Currently I only test the functionalities on Linux (Ubuntu distribution), but it should work on Windows. I'm not sure about...

Hi there, thanks for your valuable feedback! - Ideally, the server check GPU status every second and try to assign available GPUs to clients every 5 seconds. The client would...

Or maybe we could optimize the logic in `watchmen/server/check_work.py` to make an instant GPU assignment without waiting for queue time of the last job.

1. While, the implementation is rather primitive here. It just loops and checks if the GPUs are available for a job. https://github.com/Spico197/watchmen/blob/6b2456755b6fba91f21c86fec72815d90a05c794/watchmen/server.py#L252 2-3. I'm running the experiments with a local...

```python weights = np.ones((3, 1)) ``` and I get ``` array([[1.], [1.], [1.]]) ``` where $weight \in \mathds{R}^{3 \times 1}$, so I guess you have a misunderstanding?

Here's my job status on RTE: