Open zhouzhengbo2022 opened 1 year ago
Thanks author for this great project. I have a question about how absolute position embedding is applied as shown in the code
self.pos_embed = nn.Parameter(torch.zeros(1, channels, 14, 14))
https://github.com/huawei-noah/Efficient-AI-Backbones/blob/master/vig_pytorch/vig.py#L110
since it is initialized as zero and have not updated during the training.
It is used in https://github.com/huawei-noah/Efficient-AI-Backbones/blob/9172762a38e9bcafab9907c93ca7141797386f4c/vig_pytorch/vig.py#L140
It will be updated during training.
Thanks author for this great project. I have a question about how absolute position embedding is applied as shown in the code
https://github.com/huawei-noah/Efficient-AI-Backbones/blob/master/vig_pytorch/vig.py#L110
since it is initialized as zero and have not updated during the training.