知识卡片
加权损失和未加权准确率衡量不同
训练目标若按count加权,而准确率只按每行是否相等平均,两者衡量的样本总体不同。下降的损失与变化缓慢的准确率可以同时发生;还应说明阈值、类别基准和测试构成,不能单凭70%宣布现实个人分类可靠。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 神经网络基础
原书出处 · 1 处
- · 查看原书依据
>>> def measure_binary_accuracy(y_pred, y): ... y_pred = make_array(y_pred).round() ... y = make_array(y).round() ... num_correct = (y_pred == y).sum() ... return num_correct / len(y) Now, you can rerun your training using this utility function to see the progress of the model’s loss and accuracy with each epoch: for epoch in range(num_epochs): optimizer.zero_grad() #1 outputs = model(X_train) loss_train = loss_func_train(outputs, y_train) loss_train.backward() epoch_loss_train = loss_train.item() optimizer.step() outputs_test
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第05章《神经网络基础》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-5.html)
- 结论依据:摘录中关于加权损失和未加权准确率衡量不同的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:>>> def measure_binary_accuracy(y_pred, y): ... y_pred = make_array(y_pred).round() ... y = make_array(y).round() ... num_correct = (y_pred == y).sum() ... return num_correct / len(y) Now, you can rerun your training using this utility function to see the progress of the model’s loss and accuracy with each epoch: for epoch in range(num_epochs): optimizer.zero_grad() #1 outputs = model(X_train) loss_train = loss_func_train(outputs, y_train) loss_train.backward() epoch_loss_train = loss_train.item() optimizer.step() outputs_test