KeyError: ‘Transformer/encoderblock_0\\MultiHeadDotProductAttention_1/query\\bias is not a file in t

在运行Window系统中运行GitHub上的VIT时出现如下报错
报错：
KeyError:‘Transformer/encoderblock_0\MultiHeadDotProductAttention_1/query\kernel is not a file in the archive’

出错原因：
pjoin(ROOT, ATTENTION_Q, “kernel”)将多个路径组合为一个路径出错

pjoin（）函数在Windows下，路径分隔符是反斜杠\，而在Unix和Linux下，路径分隔符是正斜杠/

问题描述

KeyError: 'Transformer/encoderblock_0\\MultiHeadDotProductAttention_1/query\\bias is not a file in the archive'

这个错误主要由字符串地址拼接时Windows和Linux等其他系统不太一样，Windows使用 \ 符号，所以找到字符串拼接的地方加上 / 即可

解决方案：

1、modeling.py的相应行加上/

ATTENTION_Q = "MultiHeadDotProductAttention_1/query/"
ATTENTION_K = "MultiHeadDotProductAttention_1/key/"
ATTENTION_V = "MultiHeadDotProductAttention_1/value/"
ATTENTION_OUT = "MultiHeadDotProductAttention_1/out/"
FC_0 = "MlpBlock_3/Dense_0/"
FC_1 = "MlpBlock_3/Dense_1/"
ATTENTION_NORM = "LayerNorm_0/"
MLP_NORM = "LayerNorm_2/"

2、modeling.py的load_from函数加/

def load_from(self, weights, n_block):
    ROOT = f"Transformer/encoderblock_{n_block}/"

3、modeling_resnet.py修改：

self.body = nn.Sequential(OrderedDict([
    ('block1/', nn.Sequential(OrderedDict(
        [('unit1/', PreActBottleneck(cin=width, cout=width*4, cmid=width))] +
        [(f'unit{i:d}/', PreActBottleneck(cin=width*4, cout=width*4, cmid=width)) for i in range(2, block_units[0] + 1)],
        ))),
    ('block2/', nn.Sequential(OrderedDict(
        [('unit1/', PreActBottleneck(cin=width*4, cout=width*8, cmid=width*2, stride=2))] +
        [(f'unit{i:d}/', PreActBottleneck(cin=width*8, cout=width*8, cmid=width*2)) for i in range(2, block_units[1] + 1)],
        ))),    
    ('block3/', nn.Sequential(OrderedDict(
        [('unit1/', PreActBottleneck(cin=width*8, cout=width*16, cmid=width*4, stride=2))] +
        [(f'unit{i:d}/', PreActBottleneck(cin=width*16, cout=width*16, cmid=width*4)) for i in range(2, block_units[2] + 1)],
        ))),
]))

亲测有效！顺利进入到数据集下载部分。