qgh1223

Indentation bugs

1

Why I met so many indentation bugs when using train_imagenet.py? My python env is 3.7

loss nan using centernet v 19 ese fpn lite res600 ms bs16 4x.yaml

1

meet loss nan using centernet v 19 ese fpn lite res600 ms bs16 4x.yaml.How to solve? No problem using centermask_R_50_FPN_1x.yaml Why?

NaN problem

3

I met WARNING :root:NaN or Inf in input tensor problem.Why?

predict error

10

2020-02-27 19:03:07.918249437 [W:onnxruntime:, graph.cc:73 MergeShapeInfo] Error merging shape info for output. '106_convolutional' source:{1,18,52,52} target:{1,255,52,52}. Falling back to lenient merge. 2020-02-27 19:03:07.918328307 [W:onnxruntime:, graph.cc:73 MergeShapeInfo] Error merging shape info for output....

Paper link?When uploading source code?

6

I cannot get the paper link from bing search,arxiv search and dblp search.Where? When will you upload the source code?

Training code

1

How can I train a new dataset?

When uploading source code?

4

When uploading source code?

When uploading the dataset?I want to use your dataset for research.

When downloading https://drive.google.com/file/d/1a2oHjcEcwXP8oUF95qiwrqzACb2YlUhn/view,I met this problem. 抱歉，您目前无法查看或下载此文件。 最近查看或下载此文件的用户过多。请稍后再尝试访问此文件。如果您尝试访问的文件特别大或由很多人一起共享，则可能需要长达 24 小时才能查看或下载该文件。如果 24 小时后您仍然无法访问文件，请与您的域管理员联系。

Why did I encounter this error in the tqdm dataloader line? RuntimeError: Expected object of scalar type Double but got scalar type Long for sequence element 3 in sequence argument...