EFGRNet icon indicating copy to clipboard operation
EFGRNet copied to clipboard

Enriched Feature Guided Refinement Network for Detection,ICCV2019.

Results 11 EFGRNet issues
Sort by recently updated
recently updated
newest added

What is the solution to this error? Thanks.

我用您给的代码自己训练得到的精度并没有论文中那么高,请问怎么回事。

Hello, can you share the code of feature map visualization? ![image](https://user-images.githubusercontent.com/26458922/93051127-94312f00-f696-11ea-82bd-60ff043757f7.png)

hi, Thank you for your contribution. I have some marginal questions. In evaluation file, what is the backbone time? and do you have any method to reduce the time ?...

Can I ask you some question?I want to know whether your train_coco.py contain the function of training VOC Dataset or not.

RuntimeError: max_pool2d_with_indices_out_cuda_frame failed with error code 0 File "/data_1/software/yes/envs/pytorch/lib/python3.6/site-packages/torch/nn/functional.py", line 488, in _max_pool2d input, kernel_size, stride, padding, dilation, ceil_mode) RuntimeError: **max_pool2d_with_indices_out_cuda_frame failed with error code 0** 请问,这是什么原因导致呢?测试图像需要提前resize到320*320尺寸才能用吗?

hello, I can't find the code of the multi-scale inference in the project, can you help me?

In the paper,for MS COCO dataset, the learning rate is change at 90, 120 and 140 epoch, respectively. But in the yaml, the learning rate is change at 90, 110...