关于 ViT Transformer Encoder 中存在硬编码的问题

PaddleViT/image_classification/ViT/transformer.py 的 L300 创建 EncoderLayer 时，参数 qkv_bias, mlp_ratio, dropout, attention_dropout存在硬编码的问题，导致 Encoder 的 __init__ 方法传入的参数形同虚设：

class Encoder(nn.Layer):
    """Transformer encoder
    Encoder encoder contains a list of EncoderLayer, and a LayerNorm.
    Attributes:
        layers: nn.LayerList contains multiple EncoderLayers
        encoder_norm: nn.LayerNorm which is applied after last encoder layer
    """
    def __init__(self,
                 embed_dim,
                 num_heads,
                 depth,
                 qkv_bias=True,
                 mlp_ratio=4.0,
                 dropout=0.,
                 attention_dropout=0.,
                 droppath=0.):
        super(Encoder, self).__init__()
        # stochatic depth decay
        depth_decay = [x.item() for x in paddle.linspace(0, droppath, depth)]
        layer_list = []
        for i in range(depth):
            encoder_layer = EncoderLayer(embed_dim,
                                         num_heads,
                                         qkv_bias=True,
                                         mlp_ratio=4.,
                                         dropout=0.,
                                         attention_dropout=0.,
                                         droppath=depth_decay[i])
            layer_list.append(copy.deepcopy(encoder_layer))
        self.layers = nn.LayerList(layer_list)
……

应该改成：

class Encoder(nn.Layer):
    """Transformer encoder
    Encoder encoder contains a list of EncoderLayer, and a LayerNorm.
    Attributes:
        layers: nn.LayerList contains multiple EncoderLayers
        encoder_norm: nn.LayerNorm which is applied after last encoder layer
    """
    def __init__(self,
                 embed_dim,
                 num_heads,
                 depth,
                 qkv_bias=True,
                 mlp_ratio=4.0,
                 dropout=0.,
                 attention_dropout=0.,
                 droppath=0.):
        super(Encoder, self).__init__()
        # stochatic depth decay
        depth_decay = [x.item() for x in paddle.linspace(0, droppath, depth)]
        layer_list = []
        for i in range(depth):
            encoder_layer = EncoderLayer(embed_dim,
                                         num_heads,
                                         qkv_bias=qkv_bias,
                                         mlp_ratio=mlp_ratio,
                                         dropout=dropout,
                                         attention_dropout=attention_dropout,
                                         droppath=depth_decay[i])
            layer_list.append(copy.deepcopy(encoder_layer))
        self.layers = nn.LayerList(layer_list)
……

以上~

BR-IDL / PaddleViT

关于 ViT Transformer Encoder 中存在硬编码的问题 #76