search

pkuCactus / BDCN

The code for the CVPR2019 paper Bi-Directional Cascade Network for Perceptual Edge Detection
MIT License
341 stars 71 forks source link

result #17

Closed LoveSimons closed 5 years ago

LoveSimons commented 5 years ago

Hello, I am very interested in your work. I ran the test.py script and it passed. The result is as follows: [1]runfile('/home/renxue/BDCN/test.py', wdir='/home/renxue/BDCN') Time.struct_time(tm_year=2019, tm_mon=7, tm_mday=7, tm_hour=9, tm_min=15, tm_sec=6, tm_wday=6, tm_yday=188, tmisdst=0) Bdcn.py:199: UserWarning: nn.init.constant is now deprecated in favor of nn.init.constant.    Nn.init.constant(param, 0.080) (200, 200) /home/renxue/anaconda3/envs/psenet/lib/python2.7/site-packages/torch/nn/functional.py:1332: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.    Warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.") 383.229988098 Overall Time use: 383.677251816 There is no visual result in the result/fuse folder. How can I solve this problem? I look forward to your reply and wish you a happy life.

jannctu commented 5 years ago

Hi, I run and retrain this code, and it's work fine. His pretrained model ODS : 0.817 My retrain model ODS : 0.805

LoveSimons commented 5 years ago

Hi, I run and retrain this code, and it's work fine. His pretrained model ODS : 0.817 My retrain model ODS : 0.805

Thank you very much for your reply. The three evaluation indicators mentioned in the article: ODS, OIS and AP, are there tools that can directly get these three results, because the code does not involve evaluation indicators. Can you share the tools for calculating the evaluation indicators? look forward to your reply

jannctu commented 5 years ago

Yes, the evaluation code is written in Matlab. That's part of the Structured Forest paper. But, that code is also used in HED and RCF papers. it's good to read all those (HED, RCF) papers first to get better understanding.

LoveSimons commented 5 years ago

Yes, the evaluation code is written in Matlab. That's part of the Structured Forest paper. But, that code is also used in HED and RCF papers. it's good to read all those (HED, RCF) papers first to get better understanding.

Thank you very much for your reply. Based on your suggestions, I will study further and wish you a happy life.