sky186

aqe(query_feat: torch.tensor, gallery_feat: torch.tensor, qe_times: int = 1, qe_k: int = 10, alpha: float = 3.0):

1

@hby96 您好代码里面的aqe实现我没有看的很明白，您有空可以回复一下，计算的大致过程吗？

# Read This First * Make sure to describe **all the steps** to reproduce the issue * Include full error message in the description * Add OS version, Python version,...

@wang21jun 您好，谢谢您的工程，很有用^^ 1、口罩戴到鼻子左右的地方，口罩模拟，您这边有什么建议吗？ 是制作 mask_data 数据鼻子下的口罩这样吗？

detect and classier model prunting?

1

@lmbxmu Hi ,thank you your work,it's great~ I want to ask you ,the detect model (yolo ssd) to use your code ,is OK ? same?

onnx merge bn to fc？

1

@ Now have merge bn and conv to simplify, but don't have bn to fc, Could you support it in the future ?

@clancylian mobilenet is OK feature have a little not same res50 model ,the Deconclution shape error I should know modify the two layer?, the crop param only inter. layer {...

TypeError: ONNX node of type GlobalAveragePool is not supported.

10

@MTlab Hi : I want to convert resnet to caffe,but TypeError: ONNX node of type GlobalAveragePool is not supported. I should how to solve it

data label

10

@FlyHighest 您好，谢谢你们的工作，很有用， 我这边下载的数据，统计后， 6799个 id 1256381 图片，请问是正确的吗？

SimpleSelfAttention and se

1

@sdoria Hi ,thank you for your work, is great. I have a question , SimpleSelfAttention and se (senet ) , se is a independent structure, Which is more effective? Have...

ctc+cnn 文字识别 paddle模型 转onnx 13个节点不支持？

2

@yeliang2258 您好 车牌识别的文字识别 ctc + cnn模型转换出现多个节点不支持 There's 13 ops are not supported yet =========== gru_unit =========== =========== less_than =========== =========== logical_not =========== =========== sequence_softmax =========== =========== grid_sampler =========== =========== write_to_array...