Your training dataset must meet the following criteria to be compatible with Edge AI Lab and suitable for building accurate machine learning models. For the exact requirements, see the relevant option depending on your use case:
- It must be a CSV file using UTF-8 or ISO-8859-1 encoding.
- The file name must not contain the following special characters:
!/[+!@#$%^&*,. ?":{}\\/|<>()[]]. - All feature values in the dataset must be numeric.
For the classification task type, values of the target variable should start with
0. - A dataset must not have any empty values or values which represent empty values, such as
NA,NAN, and others. - A comma, semicolon, pipe, care, or tab must be used as a separator.
- You should use CRLF or LF as the end-of-line character and ensure it is consistent.
- All column names (values in the CSV file header) must be unique and must contain only letters (a-z, A-Z), numbers (0-9), hyphens (-), or underscores (_).
- For the classification task type, a training dataset must have a minimum of 2 classes of target variable with at least 20 samples provided for each class.
-
Currently, the Edge AI Lab supports only the EN-US locale for numbers. This means the following:
- You must use a dot as a decimal separator, and delete spaces and commas typically used to separate every third digit in your numeric fields.
For example,
20,000.00should be replaced with20000.00. - If any numeric column is represented as a combination of a number and its corresponding unit, then only the number should be placed in the column.
For example,
$20,000.00should be replaced with20000.00. - Date and time columns must be in epoch time representation or relative date format.
For example,
10/18/2017should be represented as1508284800. - In test datasets, the same timestamp format should be used in a manner consistent with the training dataset.
- End-of-line symbols must be excluded from the field values.
-
In the case of sensor data from gyroscopes, accelerometers, magnetometers, electromyography (EMG), and other similar devices for creating models using Signal Preprocessing, every row of a dataset should be device readings per unit of time with a label as a target. You should not shuffle signal labels or encode your signal for model creation. For example, if the window is 8, then the dataset can be organized as follows:
- You must use a dot as a decimal separator, and delete spaces and commas typically used to separate every third digit in your numeric fields.
For example,
-
The number of lines must be excluded from the training dataset.
- Data can be represented in the following types: INT8, INT16, FLOAT 32.
- When transferring data for inference on the device, the values must always be in the same order as in the training dataset.
- Datatype should match the train data type.
- A dataset must be a CSV file using UTF-8 or ISO-8859-1 encoding.
- The first row in the dataset must contain the column names, and a comma, semicolon, pipe, caret, or tab must be used as a separator. CRLF or LF should be used as the end of a line character.
- The test (holdout) dataset must have the same file structure with the same requirements for the feature values as the training dataset. The order of fields must be the same as in the training dataset.
-
End-of-line symbols must be excluded from the field values.