DCNet

DCNet copied to clipboard

请问什么时候上传CFA模块？

1

@hzhupku 请问什么时候上传context-aware feature aggregation (CFA) module 这个部分的代码呢？期待您的回复，谢谢！

cccxiaozhe

请问何时上传CFA模块和coco训练测试的程序？谢谢

1

LiangYang666

I'm sorry, I don't know why I can't reproduce the results in your paper, and we didn't see your Fpn2mlpfeatureextractor_ PCB module of E2E_ voc_ split1_ 2shot_ finetune.yaml in codes....

hejunran

ASDF

2

好多错误，求完善

Zhengfei-0311

当我运行‘bash base_train.sh’时遇到的问题

2

2021-12-19 07:57:32,080 maskrcnn_benchmark.utils.checkpoint INFO: Saving checkpoint to ./model_final.pth /home/hp/anaconda3/envs/dcnet/lib/python3.6/site-packages/apex-0.1-py3.6-linux-x86_64.egg/apex/amp/_initialize.py:25: UserWarning: An input tensor was not cuda. warnings.warn("An input tensor was not cuda.") Traceback (most recent call last): File "../../tools/train_net.py", line...

tangjiaxi98

maybe a bug of freeze_at 2 in backbone?

8

https://github.com/hzhupku/DCNet/blob/58b8b09bf6b242ff09239c6489fb814c33d9a19b/maskrcnn_benchmark/config/defaults.py#L105

Wei-i

pjh4993

ShawnTing6

def forward(self,features,attentions): features = list(features) if isinstance(attentions,dict): for i in range(len(attentions)): if i==0: atten = attentions[i].unsqueeze(0) else: atten = torch.cat((atten,attentions[i].unsqueeze(0)),dim=0) attentions = atten.cuda() output = [] h , w =...

Saralyliu

The/workspace/code/Meta FSOD folder was not found. I want to know how to obtain it? @hzhupku Looking forward to your quick reply!

tutu-star