Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / shi-labs/decoupled-classification-refinement issues and pull requests
#20 - Checking my understanding for the intuition
Issue -
State: open - Opened by ydixon about 4 years ago
#20 - Checking my understanding for the intuition
Issue -
State: open - Opened by ydixon about 4 years ago
#19 - How to sample boxes in the DCRV2?
Issue -
State: open - Opened by HuangLian126 about 4 years ago
#19 - How to sample boxes in the DCRV2?
Issue -
State: open - Opened by HuangLian126 about 4 years ago
#18 - Could you please give a detailed explaination about testing DCR-v1 ?
Issue -
State: open - Opened by wirevoid about 5 years ago
#18 - Could you please give a detailed explaination about testing DCR-v1 ?
Issue -
State: open - Opened by wirevoid about 5 years ago
#17 - Could this code run on the envirornment of CUDA Version 9.0.176?
Issue -
State: open - Opened by ShihuaiXu over 5 years ago
- 1 comment
#17 - Could this code run on the envirornment of CUDA Version 9.0.176?
Issue -
State: open - Opened by ShihuaiXu over 5 years ago
- 1 comment
#16 - How to combine scores of stage1 and stage2
Issue -
State: open - Opened by emergencyd over 5 years ago
- 1 comment
#15 - Question about technical details
Issue -
State: open - Opened by hdjang almost 6 years ago
- 1 comment
#14 - what is the meaning of 'class agnostic' ?
Issue -
State: closed - Opened by hdjsjyl almost 6 years ago
- 2 comments
#13 - Question about Boxes used in RCNN
Issue -
State: closed - Opened by JunweiLiang almost 6 years ago
- 5 comments
#12 - Any suggestion about model ensemble for faster rcnn?
Issue -
State: open - Opened by BasisPoint almost 6 years ago
- 1 comment
#11 - And for plain faster rcnn, when I use my own faster rcnn, and faster rcnn implemented by you to fit my dataset with the same parameter setting, the results are different and have a big difference. Do you think I should set different parameters? Do you have any advice about that? Thanks
Issue -
State: closed - Opened by hdjsjyl almost 6 years ago
- 4 comments
#10 - During training, the accuracy of RCNN is decreasing from the beginning to 92.5498, is it normal?
Issue -
State: closed - Opened by hdjsjyl about 6 years ago
- 3 comments
#9 - After training the model, the bounding boxes of final predictions are very strange?
Issue -
State: closed - Opened by hdjsjyl about 6 years ago
- 2 comments
#8 - Can you upload your training log?
Issue -
State: closed - Opened by hdjsjyl about 6 years ago
- 2 comments
#7 - When I use image with large size (800, 1200) or (1200, 1600), the RPN loss is large, 5.123 or nan?
Issue -
State: closed - Opened by hdjsjyl about 6 years ago
- 6 comments
#6 - How can I add a new batchnorm layer?
Issue -
State: open - Opened by EyreEyre about 6 years ago
- 4 comments
#5 - 1
Issue -
State: closed - Opened by yongqiangzhang1 about 6 years ago
#4 - How can I train my own data? PASCAL VOC2007 format.
Issue -
State: open - Opened by dby2017 about 6 years ago
- 3 comments
#3 - Can you give a detailed explaination about DCR-v1 ? Especially the two .py codes in ./dcr_v1/.
Issue -
State: open - Opened by KimSoybean over 6 years ago
- 15 comments
#2 - add cited reference
Pull Request -
State: closed - Opened by weiyc over 6 years ago
#1 - Ready to release code
Pull Request -
State: closed - Opened by bowenc0221 over 6 years ago