ModelEvaluator

Function Usage

Provides a Python instance based on the input data of the bin type for a model to calibrate and infer the model.

Prototype

class ModelEvaluator(AutoCalibrationEvaluatorBase):

def __init__(self, data_dir, input_shape, data_types):

Command-Line Options

Option	Input/Return	Description	Restriction
data_dir	Input	Sets the path of the .bin dataset that matches the model.	A string Value format: data/input1/;data/input2/ Constraints: 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 (;). The shape of arrays stored in a single .bin file must match that specified by --input_shape. For example, if the shape of arrays stored in a single .bin file is 1 x 224 x 224 x 3, that specified in --input_shape must also be 1 x 224 x 224 x 3. If multiple .bin files are required for quantization, you can adjust the batch number by using --batch_num.
input_shape	Input	Input shape.	A string Format: "input_name1:n1,c1,h1,w1;input_name2:n2,c2,h2,w2". Restrictions: The specified nodes must be enclosed in double quotation marks ("") and separated by semicolons (;).
data_types	Input	Sets the input data type.	A string Format: "float32;float64". Remarks: If a model has multiple inputs of different data types, you need to specify all the involved data types. All the data types must be enclosed in double quotation marks ("") and separated by semicolons (;) in the input node sequence.

Option

Input/Return

Description

Restriction

data_dir

Input

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

A string

Value format: data/input1/;data/input2/

Constraints:

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 (;).
The shape of arrays stored in a single .bin file must match that specified by --input_shape. For example, if the shape of arrays stored in a single .bin file is 1 x 224 x 224 x 3, that specified in --input_shape must also be 1 x 224 x 224 x 3. If multiple .bin files are required for quantization, you can adjust the batch number by using --batch_num.

input_shape

Input

Input shape.

A string

Format: "input_name1:n1,c1,h1,w1;input_name2:n2,c2,h2,w2".

Restrictions: The specified nodes must be enclosed in double quotation marks ("") and separated by semicolons (;).

data_types

Input

Sets the input data type.

A string

Format: "float32;float64".

Remarks: If a model has multiple inputs of different data types, you need to specify all the involved data types. All the data types must be enclosed in double quotation marks ("") and separated by semicolons (;) in the input node sequence.

Returns

A Python instance.

Outputs

None

Example

import amct_pytorch as amct

evaluator = amct.ModelEvaluator(
    data_dir="./data/input_bin/", 
    input_shape="input:32,3,224,224", 
    data_types="float32")

Parent topic: Common API