How to set parameter "radius" of center sample

[18804601171]

[yqyao]

You can add it in config file (configs/fcos/fcos_R_50_FPN_1x_center_giou.yaml) @18804601171

[18804601171]

@yqyao gt = gt[None].expand(K, num_gts, 4),in this line have a error,RuntimeError: expand(torch.cuda.FloatTensor{[1, 8525, 70, 4]}, size=[8525, 8525, 4]): the number of sizes provided (3) must be greater or equal to the number of dimensions in the tensor (4) ,expand shouldn't have error,why do you know

[18804601171]

in addition,how to set the value of radius is suitable?

[yqyao]

In my experiment, 1.5 is the best. @18804601171

[18804601171]

@yqyao why expand gt's dim,why not use original dim

[yqyao]

Gt will be implicitly expanded in this line, I just expanded it in advance. @18804601171

FCOS_PLUS/maskrcnn_benchmark/modeling/rpn/fcos/loss.py

Line 66 in 0d20ba3

left = gt_xs[:, None] - center_gt[..., 0]

[18804601171]

How many dim of gt are passed into function get sample region @yqyao

[yqyao]

I don't understand your question very well, I think all gt will be passed into function to get sample region. Maybe you need to read our recent paper https://arxiv.org/abs/1912.02424. @18804601171

[18804601171]

@yqyao The size of radius only determines the sampling range. If it is beyond gt, is it still possible to sample in the original gt，So why does its size affect the final result？