哪种精度称为深度学习模型的精度？

Question

This question was migrated from Stack Overflow because it can be answered on Cross Validated. Migrated 5 days ago .

I have developed a deep learning model, to predict whether an image is affected by a certain disease or not. Accuracies of 99.8%, 88.8%, and 89% have been achieved on the training set, testing set, and validation set respectfully. I'm going to publish my research work in a journal, therefore, whichever accuracy will be the accuracy of my deep model? If I say the accuracy of 99.8% is the accuracy of my model, is it justified?

Answer 1

Let's borrow some definitions from MachineLearningMastery/Jason Brownlee

• Your training set is the sample of data used to fit the model.
• Your validation set is the sample of data used to provide an unbiased evaluation of a model fit on the training dataset while tuning model hyperparameters.
• Your test set is the sample of data used to provide an *unbiased evaluation of a final parameter-tuned model's performance on new data.

In other words, the result of your experiment is the outcome of applying your model to new data, ie your test data. In your case, that means that your can report an accuracy of 89%.

Answer 2

You must always report the metrics of the test set; ie the data set that has been used only once to assess the performance of the final network. Anything else might be biased due to fitting or hyperparameter tuning. Then, you should also report other classification metrics alongside accuracy, such as recall or F1 score (again evaluated on the test set). For imbalanced data sets (ie one class label dominates), it's also important to balance the data set, or to take this into account when computing classification scores.

Answer 3

No, AFAIK there is no designer support for hotspots - I use a piece of paper.

Concerning the code, you'll have to set HotSpotMode="PostBack" PostBackValue="HS1" for each hotspot and use a switch statement in ImageMap1_Click to react to the different Postback values.

Answer 4

You can capture mouse clicks on the imagemap using jQuery, then pass the x, y coordinates of mouseposition to textbox. At the end you can add captured areas to your imagemap.