Context-Transformer

Context-Transformer copied to clipboard

Pretraining RFBNet on source domain dataset COCO60, it shows loss nan

7

Hello, I really appreciate your work! When I pretrain RFBNet on source domain dataset COCO60, it shows loss nan. Is it correct and why?

LexieYang

[Errno 2] No such file or directory: './data/COCO/annotations/instances_valminusminival2014.json'

5

I run the python data/split_coco_dataset_voc_nonvoc.py ，and I get this problem, how can I solve it. Split 1: 346721 anns; save to ./data/COCO/annotations/split_voc_instances_train2014.json Split 2: 258186 anns; save to ./data/COCO/annotations/split_nonvoc_instances_train2014.json processing...

Zyt-wenwne

demo.py

2

Can you provide a demo to test a single image?

tailororrr

Hello, I reproduced the code on 4 2080Ti GPUs, but I got only half mAP of the VOC split1 at phase 1, what may causes this? 按照ReadMe先在VOC数据集上试了一下，一阶段在源域上mAP到不了论文里70+这么高，这可能是什么原因造成的？  [log.txt](https://github.com/Ze-Yang/Context-Transformer/files/7357477/log.txt)

wwwwwbh

src_cls_dim

1

what does "src_cls_dim" mean? when I train my custom dataset, I need to modify it.

loading376

Issue about VOC2007.sh

6

Hello Thanks for contributing this paper/project. I have a question. when I run the VOC2007.sh, the link about Main2007.tar is the same as Main2007.zip? thanks.

sandq

size 512 error.

1

hello, thanks for your nice work, i want to train a model with input size=512, but i got an error ``` list index out of range ``` in the script...

feifeiwei

Comparing with SOTA methods

1

Hello Thanks for contributing this paper/project. I have a question. This paper/project compared the experiment results with some papers/projects researched in 2017 and 2019. We want to know the result...

rose-jinyang