--data_dir

Description

Sets the path of the .bin dataset that matches the model.

See Also

Required if --evaluator is not included.

Value

Argument: path of the .bin dataset.

Restrictions:

• The path can contain only letters, digits, underscores (_), hyphens (-), and periods (.).
• If the model has multiple inputs and each input has multiple batches of data, these batches must be stored in different directories and the file in the directories must be arranged in ascending order by name. All input directories must be enclosed in double quotation marks ("") and separated by semicolons (;).

Suggestions and Benefits

None

Examples

--data_dir="data/input1/;data/input2/"

For example, in the input1 and input2 directories, data files are named input1batch1.bin, input1batch2.bin, input2batch1.bin, and input2batch2.bin, which are arranged in ascending order.

Constraints

This option is used only in PTQ scenarios.