WuQiang

Results 18 issues of WuQiang

I want to train my own R-CNN detector on my own database .I must prepare my files like VOC database. Anyone can give me some ideas? Thanks!

what i only do is to produce files like 'window_file_voc_2012_train.txt"; /path/to/VOC2012/VOCdevkit/VOC2012/JPEGImages/2008_000008.jpg -> picture's name 3 channels 442 ->rows 500 ->cols 2753 -> the number of the boxes 13 1.000 52...

@luoyetx When a human face in an image is just on the edge of the image. There is always such a problem: out of bounds.Because in the process of recognition,...

I have a question.In the training, the results of the previous level of training are not used for the latter level of training. However, in the test phase, the previous...

Without changing other paramers, trainging again can get better (maybe worse) results?

After training by using bootstrap.sh, I get the wrong result . ![4febec6cd3fa9e75d2a28023c0b0bc76](https://cloud.githubusercontent.com/assets/7983007/13692196/5870bc9a-e77a-11e5-8d9d-4b997b4fae73.jpg) ![b656dd97cb9670160ad455223cd61a6c](https://cloud.githubusercontent.com/assets/7983007/13692197/5b613588-e77a-11e5-8149-d5dddf0a064c.jpg) I use HDFView the 1_F/train.hd5 file,what are the meaning of data and landmark? (1)landmark,first six rows: 0.27142859...

the cpu mode is oK; But the gpu mode gets much error: . . . . /usr/include/c++/4.8/cmath(278): error: inline specifier allowed on function declarations only /usr/include/c++/4.8/cmath(278): error: variable "std::constexpr" has...

Can anyone share the noisy data, General Series 6000 Combo and NOISEX-92.

没有检测结果的输出提示如下: Tengine plugin allocator TIMVX is registered. vsiplugin reshape output tensor addr is 0x55a4c31d10 vsiplugin reshape output tensor addr is 0x55a4c31db0 vsiplugin reshape output tensor addr is 0x55a4c31e50 vsiplugin reshape...

**bug描述** 0.4.0版本的EIseg,因为图像太大(2000像素),采用宫格模式标记之后保存为json文件是空的,但是生成的pseudo.png是正确的,导致重新加载的标记的图像,没有了标记的轮廓信息了。 **运行环境(请尽量填写,这可以帮助我们定位问题):** - 系统: [ Windows] - 安装方式:[pip] - 软件版本:[0.4.0]

bug