- Practical Convolutional Neural Networks
- Mohit Sewak Md. Rezaul Karim Pradeep Pujari
- 106字
- 2021-06-24 18:58:52
Testing
After you're satisfied with the training output and accuracy, you can run the network on the test dataset to measure its performance!
Keep in mind to perform this only after you've completed the training and are satisfied with the results.
A good result will obtain an accuracy higher than 95%. Some simple models have been known to achieve even up to 99.7% accuracy! We can test the model, as shown here:
# Comparing the labels predicted by our model with the actual labels score = model.evaluate(X_test, y_test, batch_size=32, verbose=1,sample_weight=None) # Printing the result print('Test score:', score[0]) print('Test accuracy:', score[1])
推薦閱讀
- 數據庫基礎與應用:Access 2010
- 劍破冰山:Oracle開發藝術
- Spark核心技術與高級應用
- 智能數據時代:企業大數據戰略與實戰
- Oracle 12c云數據庫備份與恢復技術
- AI時代的數據價值創造:從數據底座到大模型應用落地
- 數據庫應用系統開發實例
- Mastering LOB Development for Silverlight 5:A Case Study in Action
- Oracle高性能SQL引擎剖析:SQL優化與調優機制詳解
- Access 2010數據庫程序設計實踐教程
- Hands-On System Programming with C++
- 大數據技術體系詳解:原理、架構與實踐
- Trino權威指南(原書第2版)
- Hive性能調優實戰
- 大數據原理與技術