[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fXj0lGRp1kXcQRR-oc43E6crmWXg5YekyB1JoKODrHBI":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2025-01-12 15:43:02",177216463,[8,9,10,11],"\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F65d2cf9c73d6b19a9674bf3974a4642d.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Fb57164c7702b8852e97117e47a9357a5.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F10de4de2c7158c7f4d9f3108e7fc8624.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F9d5ae708c375ff61dbb3e51169024ab7.png\">",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},224,"4f17b2bde91d0c947d3228ee0c8b1307","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F1bdc1a3b0f438a24892a274da88eeb74.png","深度学习应用","exam_148860406","期末","在进行反卷积计算时,假设输入尺寸为\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F65d2cf9c73d6b19a9674bf3974a4642d.png\">,卷积核大小(kernel_size)为\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Fb57164c7702b8852e97117e47a9357a5.png\">,步长(strides)为1,边界扩充(padding的值)为"valid",那么反卷积的输出尺寸:( )",[21,32,41,50,59,68,77,80,89,98],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],177216457,[25,26,27,28],"提高模型的泛化能力","增加模型的复杂度","关注输入序列中与当前输出相关的部分","减少模型的计算成本","在神经机器翻译中,注意力机制(Attention Mechanism)的主要作用是什么","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":30,"type":31},[],177216458,[36,37,38,39],"先大后小","先小后大","一直变大","保持不变","如果模型设置指数衰减学习率,那么学习率的变小的幅度是( )",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":30,"type":31},[],177216459,[45,46,47,48],"assets","keras_metadata.pb","saved_model.pb","variables","使用model.save()保存整个模型时,以下哪个目录用于保存模型权重值.( )",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":30,"type":31},[],177216460,[54,55,56,57],"stddev","inputs","training","std","tf.keras.layers.GaussianNoise可用于加性高斯噪声,其中以下哪个参数用于设置噪声分布的标准差.( )",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":30,"type":31},[],177216461,[63,64,65,66],"relu","softmax","sigmoid","tanh","在模型调参中,常用的激活函数有relu、leaky-relu、softmax、sigmoid、tanh等.对于中间隐层,一般优先选择( )激活函数",{"answer":69,"createTime":5,"id":70,"options":71,"question":76,"source":30,"type":31},[],177216462,[72,73,74,75],"定义模型结构","编译模型","部署模型","训练模型","使用Keras开发深度学习模型时,以下哪个步骤是不必要的",{"answer":78,"createTime":5,"id":6,"options":79,"question":19,"source":30,"type":31},[],[8,9,10,11],{"answer":81,"createTime":5,"id":82,"options":83,"question":88,"source":30,"type":31},[],177216464,[84,85,86,87],"max_error","mean_absolute_error","mean_squared_error","median_absolute_error","Scikit-Learn中的metrics子模块中用于计算均方误差函数是以下哪个.( )",{"answer":90,"createTime":5,"id":91,"options":92,"question":97,"source":30,"type":31},[],177216465,[93,94,95,96],"准确率","图像尺寸","特征数量","损失函数","在模型评估中,常用的指标包括",{"answer":99,"createTime":5,"id":100,"options":101,"question":106,"source":30,"type":31},[],177216466,[102,103,104,105],"生成器生成新数据,判别器评估生成数据的真实性","生成器评估生成数据的真实性,判别器生成新数据","生成器生成真实数据,判别器评估生成数据的真实性","生成器评估生成数据的真实性,判别器评估真实数据的真实性","生成式对抗网络(GAN)中的生成器(Generator)和判别器(Discriminator)的作用分别是什么"]