Hello and so happy to see you use Pytorch-Lightning! 🎉
Just wondering if you already heard about quite the new Pytorch Lightning (PL) ecosystem CI where we would like to invite you to... You can check out our blog post about it: Stay Ahead of Breaking Changes with the New Lightning Ecosystem CI ⚡
As you use PL framework for your cool project, we would like to enhance your experience and offer you safe updates to our future releases. At this moment, you run tests with a particular PL version, but it may accidentally happen that the next version will be incompatible with your project... 😕 We do not intend to change anything on our project side, but still here we have a solution - ecosystem CI with testing both - your and our latest development head we can find it very early and prevent releasing eventually bad version... 👍

What is needed to do?

• have some tests, including PL integration
• add config to ecosystem CI - https://github.com/PyTorchLightning/ecosystem-ci

What will you get?

• scheduled nightly testing configured for development/stable versions
• slack notification if something went wrong to investigate
• testing also on multi-GPU machine as our gift to you 🐰

cc: @Borda

Darklabel 转 MOT ，请问一下 det.txt 中的 conf 置信度和 “遮挡” 参数怎么获取呢？

作者你好，我想请问一下训练和验证自己的数据集的话，VOCdevkit这个文件夹里该怎么配置。Pascal数据集代码里的annotations_cache又是什么文件？
cachedir = os.path.join(self.devkit_path, 'annotations_cache')

dear author,

can you please tell me the dataset structure of camvid dataset.

i split images into train val and test. where should be the labels/ground truth image?

作者您好，当我运行到这句代码时self.annopath = os.path.join(VOC_test_root, 'VOC2007', 'Annotations', '{:s}.xml')，recs[imagename] = self.parse_record(annopath.format(imagename))总是报错找不到.xml文件，显示路径有错误，不知道您有没有遇到类似的问题。`

将Transformer应用在了FPN上，能涨点
https://github.com/ZHANGDONG-NJUST/FPT
https://arxiv.org/abs/2007.09451

在simple_keypoint这个部分中，regression里的test.py的65行， “NameError: name 'SIZE' is not defined”， 这里的size指的是图片的size吗？

我输出了神经网络预测的点 结果显示很多图片的输出结果为（-1，-1）这是为什么？

由于我使用的数据集来自小武，不可公开，这里提供一些可替代的公开数据集：

1. https://anti-uav.github.io/dataset/
2. http://www.csdata.org/p/387/

请问可以补充BorderDet中的提到的BAM模块到即插即用模块里么？它可以更好的精确定位box，并且付出的时间代价小
paper：BorderDet: Border Feature for Dense Object Detection
https://zhuanlan.zhihu.com/p/163044323

作者你好，我看你的知乎博文，里面提到了SEB模块，关于这个模块，这个github的代码好像并没有添加，请问作者是在哪里看到的这个SEB模块呢?

您好，AFF、iAFF的代码已经更新了pytorch版本，希望更新一下！
https://github.com/YimianDai/open-aff/blob/master/aff_pytorch/aff_net/fusion.py

utils的这个函数，shape定义错了，应当是 h,w = heatmap.shape
原来的是w,h
def draw_umich_gaussian(heatmap, center, radius, k=1):
diameter = 2 * radius + 1
gaussian = gaussian2D((diameter, diameter), sigma=diameter / 6)
# print(gaussian.shape)
# 一个圆对应内切正方形的高斯分布

x, y = int(center[0]), int(center[1])

height, width = heatmap.shape

left, right = min(x, radius), min(width - x, radius + 1)
top, bottom = min(y, radius), min(height - y, radius + 1)

masked_heatmap = heatmap[y - top:y + bottom, x - left:x + right]
masked_gaussian = gaussian[radius - top:radius +
                           bottom, radius - left:radius + right]

if min(masked_gaussian.shape) > 0 and min(masked_heatmap.shape) > 0:  # TODO debug
    np.maximum(masked_heatmap, masked_gaussian * k, out=masked_heatmap)
    # 将高斯分布覆盖到heatmap上，取最大，而不是叠加
return heatmap

hello author,

i am using your pytorch segmentation implementation. the gpu is not being used. the system is using only cpu. i have cuda device in pytorch. also, why is batch size 1 in your config and what n_workers should i use?

thank you

能不能直接用cvat或者darklabel标注视频输出gt，再与deep sort输出的result进行比较输出mota、ids这些指标

哈喽，

请问作者有没有试过heatmap方法检测多个红外目标中心点？
如果有试过的话效果如何？
还有就是，如果我想尝试这个任务的话，只需要修改dataloader应该就可以了吧？
@pprp

多谢！

hello author,

i am interested in your pytorch segmentation implementation. i faced some problem while training the bash file as follows,

File "train.py", line 27, in
from tensorboardX import SummaryWriter
File "/home/rahul/anaconda3/envs/semseg/lib/python2.7/site-packages/tensorboardX/init.py", line 5, in
from .torchvis import TorchVis
File "/home/rahul/anaconda3/envs/semseg/lib/python2.7/site-packages/tensorboardX/torchvis.py", line 11, in
from .writer import SummaryWriter
File "/home/rahul/anaconda3/envs/semseg/lib/python2.7/site-packages/tensorboardX/writer.py", line 223
logdir: Optional[str] = None,
^
SyntaxError: invalid syntax

thank you

先问一下您在使用CenterNet resdcn-18-384训练时的超参数，以及训练结果吗？

请问在windows系统编译nms的时候出现了错误应该怎么办