当我不在模型中对猫和狗进行分类时,预测值保持正常,即所有图像的值都不相同。
但是,当我将tf.nn.dropout
与keep_prob = 0.8
一起用于我的模型时,为了规范化模型和提高准确性,建议使用tflearn
,它会不断预测相同的值。我该如何解决?那里的每个教程或代码都使用array([[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00]`
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
[ 2.20128131e+00, 1.78127408e+00],
,但这不会发生。
{{1}}