JZTXT

炼丹记录

发布时间 2023-12-28 11:47:32作者: FrostyForest

8层transformer

    self.transformer = TransformerModel(
        d_model=32,
        nhead=4,
        num_encoder_layers=8,
        dim_feedforward=128,
        max_len=512
    )
    self.transformer2 = TransformerModel(
        d_model=32,
        nhead=4,
        num_encoder_layers=8,
        dim_feedforward=128,
        max_len=512
    )
    self.BigConv1 = unireplknet.UniRepLKNet(
        in_chans=2,
        num_classes=128,
        depths=(3, 3, 27, 3),
        dims=(48, 48 * 2, 48 * 4, 48 * 4),
        drop_path_rate=0.15,
        layer_scale_init_value=1e-6,
        head_init_scale=1.,
        kernel_sizes=None,
        deploy=False,
        with_cp=False,
        init_cfg=None,
        attempt_use_lk_impl=False,
        use_sync_bn=False,
    )