TensorBoard is a tool which allows visualizing training metrics (e.g. loss and accuracy), model graph, activation histograms, profiling results, etc.
This tutorial demonstrates how to visualize training metrics using TensorBoard...
TensorFlow 2
TensorFlow 2 provides the RemoteMonitor callback which allows to send epochs results during training to a server. A server can save results to a file, database table or perform other...
Model training can take a long time. TensorFlow 2 provides the TimeStopping callback which allows stopping training after a certain amount of time has passed.
The TimeStopping callback is provided...
TensorFlow 2 provides the CSVLogger callback which allows to write epochs results during training to a CSV file. After that file can be opened and results can be interpretated by...
TensorFlow 2 allows to count the number of trainable and non-trainable parameters of the model. It can be useful if we want to improve the model structure, reduce the size...
Mean absolute percentage error (MAPE) is a loss function that is used to solve regression problems. MAPE is calculated as the average of the absolute percentage differences between the actual...
Kaggle Dogs vs. Cats is a dataset that contains 25000 images of cats and dogs. Images are different sizes, so need them to reprocess. There are 12500 images of dogs...
Mean squared logarithmic error (MSLE) is a loss function that is used to solve regression problems. MSLE is calculated as the average of the squared differences between the log-transformed actual...
Binary classification is the process that is used to classify data points into one of two classes. For example, whether a customer will buy a product or not, emails are...
Mean absolute error (MAE) is a loss function that is used to solve regression problems. MAE is calculated as the average of the absolute differences between the actual and predicted...