[英]fastai - plot validation and training accuracy
I have used Keras before, and then I plotted the training and validation accuracy of datasets this way—我之前用过Keras,然后我用这种方式绘制了数据集的训练和验证准确率——
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
I'm currently learning fastai, and have already plotted training and validation losses.我目前正在学习 fastai,并且已经绘制了训练和验证损失。 But I don't know how to plot validation accuracy and training accuracy.
但是我不知道 plot 验证准确率和训练准确率如何。
learn.recorder.plot_losses()
Would anyone please help?有人可以帮忙吗?
Check out: https://forums.fast.ai/t/plotting-metrics-after-learning/69937/3查看: https://forums.fast.ai/t/plotting-metrics-after-learning/69937/3
The function plot_metrics() by Ignacio Oguiza is detailed there.那里详细介绍了 Ignacio Oguiza 的 function plot_metrics()。 Without it, you'll get an error 'Learner' object has no attribute 'plot_metrics'
没有它,你会得到一个错误'Learner' object has no attribute 'plot_metrics'
Once implemented, you can call plot_metrics() as Sirynka has mentioned:实施后,您可以调用 plot_metrics() 正如 Sirynka 提到的:
learn.recorder.plot_metrics()
learn.recorder.plot_metrics()
Post here just for people who are using the latest FastAI version 2.此处仅适用于使用最新 FastAI 版本 2 的人。
The aforementioned methods are out of date and was for Fast AI version 1.上述方法已过时,适用于 Fast AI 版本 1。
For the latest version, you should use a Callback with fit method:对于最新版本,您应该使用带有 fit 方法的回调:
learn.fit_one_cycle(10, slice(5e-3,5e-2),cbs=[ShowGraphCallback()])
The benefit of using this new callback for plot the train validation metrics is it happens directly after each epoch of training and validation, no need for a separated line of code.对 plot 训练验证指标使用这个新回调的好处是它直接在训练和验证的每个 epoch 之后发生,不需要单独的代码行。
learn.recorder.plot_metrics()
will plot all the metrics that you'v specified in将 plot 您指定的所有指标
learn = cnn_learner(data, models.resnet34,
metrics=[accuracy, error_rate])
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.