Explore. Share. Code.

What types of network architectures can be trained using the annTrain action?

You can specify the network architecture using the 'arch' parameter. The available options are 'MLP' for a multilayer perceptron, 'GLIM' for a generalized linear model architecture (a two-layer perceptron with no hidden layers), and 'DIRECT' which is an extension of MLP with direct connections from the input to the output layer. The default architecture is 'GLIM'.

See answer

On: annTrain

MAXTABLEMEM

specifies the maximum amount of memory, in bytes, that each thread should allocate for in-memory blocks before converting to a memory-mapped file. Files are written in the directories that are specified in the CAS_DISK_CACHE environment variable. When you create a large output table, such as 5G or more for each worker, you can set this value to 256M or more to improve performance.

See answer

On: getServOpt

Can I incorporate observation frequencies into the analysis?

Yes, you can use the 'freq' parameter to specify a numeric variable that represents the frequency of each observation in the input table.

See answer

On: analyzeMissingPatterns

What does the logisticCode action do?

The logisticCode action writes SAS DATA step code to compute predicted values of a fitted logistic regression model.

See answer

On: logisticCode

How does the outputFormat parameter affect the structure of the output table?

The 'outputFormat' parameter determines how cropped detections are saved. 'MULTIPLE_ROWS' (default) saves them in one column across multiple rows, while 'MULTIPLE_COLUMNS' saves them in multiple columns within a single row.

See answer

On: extractDetectedObjects