老师，按照课上的讲解应该是content的conv1_2组合style的conv4_3的结果图像效果最好是吧，那如果如下：
`style_features = [
vgg_for_style.conv1_2,
vgg_for_style.conv2_2,
vgg_for_style.conv3_3,
vgg_for_style.conv4_3,
vgg_for_style.conv5_3
]
style_gram = [gram_matrix(feature) for feature in style_features]

#结果图像
result_style_features = [
vgg_for_result.conv1_2,
vgg_for_result.conv2_2,
vgg_for_result.conv3_3,
vgg_for_result.conv4_3,
vgg_for_result.conv5_3
]`
结果会怎样呢？
附上结果：
content的conv1_2 + style的conv4_3（正常）

four + four

想问老师，为什么所有卷积层全都参与计算后的结果会这么不好。