Tianning Yuan

Sorry, I am not clear about your custom dataset. Please describe the error in detail.

`--eval mAP` can work on all custom data converted in VOC format. In your custom dataset, what are the 22 classes? What is special about that class with 509800 detection...

OK. What I mean is that, what types are these classes belong to? For example, they may be cats, dogs or cars. And what is special for class 20? For...

Please ensure that you have prepared the dataset and code as described [here](https://github.com/open-mmlab/mmdetection/blob/v2.3.0/docs/tutorials/new_dataset.md).

Have you followed the step 5 in [Section Environment Installation](https://github.com/yuantn/MI-AOD/blob/master/docs/installation.md#environment-installation), especially the compilation?

Please follow the step 5 in [Section Environment Installation](https://github.com/yuantn/MI-AOD/blob/master/docs/installation.md#environment-installation). It includes __THE COMPILATION PART__.

Please refer to Issue #81, and __READ IT CAREFULLY__.

你好，改动部分可以参见说明文档中的 [代码结构](../blob/master/README_cn.md#代码结构) 部分。 --- Hello, for the modified codes, please refer to the [Code Structure](../../MI-AOD#code-structure) in the README.md.

当 epoch 数目为 300 时，对应检测网络为 SSD，[这里](../blob/master/configs/MIAOD_SSD.py) 是其配置文件的链接。 以下这些变量决定了总 epoch 数：第 82 行的 `epoch_ratio`、86 行的 `epoch`、89 行的 `X_L_repeat` 和 90 行的 `X_U_repeat`，这些变量上方的 1~2 行的注释为其表示的意义。 例如，总 epoch 数为 300 时，中间的计算过程为 `(5+(1+1+5)*2)*16=304≈300`。 你可以看看修改哪个变量比较合适，推荐仅同步修改...

> 您好，想請教關於baseline中 random selection 不採用 IUL, IUR 的設定為何？我正在重現該實驗，感謝您的回覆 > > Thanks for the amazing work, I wanted to ask the setting of random selection without IUL and IUR in baseline...