BatchFormer
BatchFormer copied to clipboard
zhihou7
CVPR2022, BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning, https://arxiv.org/abs/2203.01522
您好！ 我想问一下： Q1: 在模型训练的时候，模型最终是几个输出？是 **BatchFormer前的classifier** + **BatchFormer后的classifier** 这两个输出呢？然后分别与ground truth计算呢？ Q2: 代码里面，如下所示，这行代码表示的是**BatchFormer后的classifier**的输出呢？还是对模型两个classifier的输出做concat操作后，最后再与ground truth计算呢？ https://github.com/zhihou7/BatchFormer/blob/f6be150ff9fce2ce4bcc3c0f8953dded9d4f273f/moco-v3/moco/builder.py#L23
Sorry to bother, I'm currently working on the long tail, so I'd like to find the general batchformer code for the long-tailed_recognition task. I can understand the batchformer code part...
Could you please share about your improved code for batchformer on detr, I want to learn about the improvement for detr
Hi! Thanks for your sharing. There may be differences between the paper and code. In the paper , it can be seen that "we share the classifier between with or...
I'm sorry to bother you. I found that bf=0 sharebf=1 in the deformable detr batchformerv2 main.py, while bf=1 sharebf=0 in the command line in the readme file. If I want...
Sorry to bother you.The error message is as follows. How can I resolve it？ root@i-r5mjznu9:/workspace/cbn/DINO# /opt/conda/lib/python3.8/site-packages/torch/tensor.py:559: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch....
作者你好，我想将batchformer用于我的人体解析任务，主要对backbone所提取的特征进行batchformer操作，batchformer的输入为（N，C，H，W）的特征请问我这样实现是否有问题？ 
I found some errors when run `bash ./utils/download_data.sh DATA_ROOT` in `czsl/`. The two followed links is unavailable. Could you please update the link? - https://github.com/zhihou7/BatchFormer/blob/6f89e22d089e6efd5b0f84477cc56974dac8dc20/czsl/utils/download_data.sh#L25 - https://github.com/zhihou7/BatchFormer/blob/6f89e22d089e6efd5b0f84477cc56974dac8dc20/czsl/utils/download_data.sh#L25
Sorry to bother, i don't know how you insert batchformer to czsl tasks, could you please tell me more details? Thanks
May I ask the 133-134 lines of code in ./moco-v3/moco/builder.py: loss = self.contrastive_loss(q1[:N], k2[:N]) + self.contrastive_loss(q1[:N], k2[N:]) + self.contrastive_loss(q1[N:], k2[:N]) + self.contrastive_loss(q1[N:], k2[:N]) + \ self.contrastive_loss(q2[:N], k1[:N]) + self.contrastive_loss(q2[:N], k1[N:])...
