self.position_embedding = nn.Parameter(torch.randn(max_len, d_model), requires_grad=True) #add one more for zero-padding ...
Code for CASP: Few-Shot Class-Incremental Learning with CLS Token Attention Steering Prompts - huangshuai0605/CASP ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results