[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f67XbbG37eSczT6KlO4l3FiG_s-960Pe5Upz7t4TlHG0":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2026-04-14 10:49:43",340255408,[8,9,10,11],"DataLoader","Dataset","TensorDataset","BatchSampler",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},11,"53e1d2ef4961cca8eea3e23969ad2cb9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F03a579384a6dc297c89809b582fcc767.png","默认课程","work_51694495","第3章习题","PyTorch中实现数据分批的类是",[21,32,35,44,53,62,71,80,89,98],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],340255407,[25,26,27,28],"手写数字分类(0-9)","时间序列预测","图像回归任务","二分类情感分析","输入784节点,输出10节点的网络最可能用于","v1",0,{"answer":33,"createTime":5,"id":6,"options":34,"question":19,"source":30,"type":31},[],[8,9,10,11],{"answer":36,"createTime":5,"id":37,"options":38,"question":43,"source":30,"type":31},[],340255409,[39,40,41,42],"784×512 + 512×10","784 + 512 + 10","×512 + (512+1)×10","784×512×10","某全连接网络输入层784节点,隐藏层512节点,输出层10节点,总参数量为",{"answer":45,"createTime":5,"id":46,"options":47,"question":52,"source":30,"type":31},[],340255410,[48,49,50,51],"减少测试集误差","统一数据分布,加速收敛","增加数据多样性","降低模型复杂度","对输入数据归一化的核心目的是",{"answer":54,"createTime":5,"id":55,"options":56,"question":61,"source":30,"type":31},[],340255411,[57,58,59,60],"每个神经元与相邻层的所有神经元连接","同一层的神经元之间互相连接","每个神经元仅与下一层的部分神经元连接","网络层数必须大于3层","以下关于全连接神经网络(FCNN)的描述,正确的是",{"answer":63,"createTime":5,"id":64,"options":65,"question":70,"source":30,"type":31},[],340255412,[66,67,68,69],"更新参数→前向计算损失→反向传播梯度","反向传播梯度→前向计算损失→更新参数","随机初始化→更新参数→反向传播","前向计算损失→反向传播梯度→更新参数","反向传播的正确流程是",{"answer":72,"createTime":5,"id":73,"options":74,"question":79,"source":30,"type":31},[],340255413,[75,76,77,78],"BCELoss","MSELoss","BCEWithLogitsLoss","CrossEntropyLoss","当网络输出层未使用激活函数(如直接输出logits),且任务是三分类问题时,应选择哪个损失函数",{"answer":81,"createTime":5,"id":82,"options":83,"question":88,"source":30,"type":31},[],340255414,[84,85,86,87],"动态调整学习率","减少显存占用","提高测试精度","加速反向传播","梯度累加的主要作用是",{"answer":90,"createTime":5,"id":91,"options":92,"question":97,"source":30,"type":31},[],340255415,[93,94,95,96],"缓解后期过拟合","防止训练初期震荡","加速前向传播","提高模型容量","学习率衰减的主要目的是",{"answer":99,"createTime":5,"id":100,"options":101,"question":106,"source":30,"type":31},[],340255416,[102,103,104,105],"手动累加梯度并跳过optimizer.step()","每次loss.backward()后立即调用optimizer.step()","累积损失值后再调用一次backward()","多次loss.backward()后调用一次optimizer.step()","在PyTorch中实现梯度累积的正确代码逻辑是"]