Method no_weight_decay

EfficientViT/downstream/efficientvit.py:421–422

(self)

    @torch.jit.ignore
    def no_weight_decay(self):
        return {x for x in self.state_dict().keys() if 'attention_biases' in x}

    def train(self, mode=True):
        """Convert the model into training mode while keep layers freezed."""