CHENS

maskrcnn在没有缺陷检出时，报错

1

### 问题确认 Search before asking - [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues)，没有报过同样bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/issues) and found no similar bug report. ### bug描述 Describe the Bug 或者使用一张黑图，用mask rcnn模型去infer一下 在静态图infer中，我这样改就不会报错了 ### 复现环境 Environment _No...

训练epoch

1

你好，请问你给的训练脚本没有给epochs参数，我看了一下你的options脚本是默认500epoch。实际上也是训练了500epochs吗？

Hi, in line 94, there is an error "Error when checking target: expected time_distributed_1 to have 3 dimensions." Please help me why to use the TimeDistributed layer after the Dense...

About the experimesnt of 'Effect of Number of Positives'

2

How did you do this experiment? That is, how to control the number of positive samples? My understanding is that when the number of positive samples is 5, that is,...

Has anyone tried adding self-supervised constrative loss to SCL?

1

That is to say, supervised contrastive loss and self-supervised constrative loss, the former can be regarded as global and the latter is local.

Reproduce results on the SUN dataset

6

Hi, I run your code but get unsatisfactory result. In your paper, the results on SUN dataset are 38.1, 89.9, 53.4, but in the process of running your code, the...

Hi, Liheng. I have reproduced supervised NIN as the paper setting, which is 88.23 in my experiment results, but the result of the paper report is 92.80. Will 92.8 be...

Where is the prob.dat file?

2

Hi, please tell me where is the prob.dat file? Thanks.

Can you share the source file data of YFCC100M, that is, the public urls?

3

Hi, Can you share the source file data of YFCC100M, that is, the public urls? It may be because of the network of mine, the metadata of the YFCC100M is...