You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I find the code "setattr(self,"pos_embed_{}".format(i),nn.Parameter(torch.randn(kv_size**2, hidden_dim)),)" in VisionCrossAttentionLayer, is the variable pos_embed_i learnable?
The text was updated successfully, but these errors were encountered:
I find the code "setattr(self,"pos_embed_{}".format(i),nn.Parameter(torch.randn(kv_size**2, hidden_dim)),)" in VisionCrossAttentionLayer, is the variable pos_embed_i learnable?
The text was updated successfully, but these errors were encountered: