SimCLR

Notation Conventions

• Parentheses () indicate literal parentheses.
• Braces {} are used to bind combinations of options.
• The bracket [] indicates an optional clause.
• An ellipsis following a comma in brackets [,...] means that the preceding item can be repeated as a comma-separated list
• The vertical bar | represents the logic OR.
• VALUE represents a regular value.

• literal: a fixed or unchangeable value, also known as a Constant.

  Each literal has a special data type such as column, in the table.

BUILD MODEL Syntax

Use the "BUILD MODEL" statement to develop an AI model. The "BUILD MODEL" statement allows you to train a model using datasets defined with the query_expr that comes after the "AS" clause.

query_statement:
    query_expr

BUILD MODEL (model_name_expression)
USING SimCLR
OPTIONS (
    expression [ , ...]
    )
AS
(query_expr)

OPTIONS Clause ​

OPTIONS (
    (image_col=VALUE),
    [batch_size=VALUE],
    [max_epochs=VALUE],
    [pretrained={True|False}],
    [overwrite={True|False}]
    )

The "OPTIONS" clause allows you to change the value of a parameter. The definition of each parameter is as follows.

• "image_col": the name of the column containing the image path to be used for the training (str, default: 'image_path')
• "batch_size": the size of dataset bundle utilized in a single cycle of training (int, optional, default: 256)
• "max_epochs": number of times to train with the training dataset (int, optional, default: 5)
• "pretrained": Sets whether or not to use pre-trained ImageNet weights (bool, optional, True|False, default: False)
• "overwrite": determines whether to overwrite a model if it already exists. If set as True, the old model is replaced with the new model (bool, optional, True|False, default: False)

BUILD MODEL Example

An example "BUILD MODEL" query can be found in Search Image by Image. ​

%%thanosql
BUILD MODEL my_image_search_model
USING SimCLR
OPTIONS (
    image_col='image_path',
    max_epochs=1,
    overwrite=True
    )
AS
SELECT *
FROM mnist_train

CONVERT Syntax

Use the "CONVERT" statement to convert data into the vectors and add it to the table.

query_statement:
    query_expr

CONVERT USING (model_name_expression)
OPTIONS (
    expression [ , ...]
    )
AS
(query_expr)

OPTIONS Clause

OPTIONS (
    (image_col=column_name),
    [result_col=column_name],
    [batch_size=VALUE]
    )

The "OPTIONS" clause allows you to change the value of a parameter. The definition of each parameter is as follows.

• "image_col": the name of the column containing the image path (str, default: 'image_path')
• "result_col": defines the column name that contains the vectorized results (str, optional, default: 'convert_result')
• "batch_size": the size of dataset bundle utilized in a single cycle of training (int, optional, default: 256)

CONVERT Example

An example "CONVERT" query can be found in Search Image by Image. ​

%%thanosql
CONVERT USING my_image_search_model
OPTIONS (
    image_col='image_path',
    result_col='convert_result'
    )
AS
SELECT *
FROM mnist_test

SEARCH IMAGE Syntax

Use the "SEARCH IMAGE" statement to retrieve the desired image data.

query_statement:
    query_expr

SEARCH IMAGE 
USING (model_name_expression)
OPTIONS (
    expression [ , ...]
    )
AS
(query_expr)

OPTIONS Clause

OPTIONS (
    (search_by={image|text|audio|video}),
    (search_input=expression),
    (emb_col=column_name),
    [result_col=column_name],
    [top_k=VALUE]
    )

The "OPTIONS" clause allows you to change the value of a parameter. The definition of each parameter is as follows.

• "search_by": defines the image|text|audio|video type to be used for the search (str)
• "search_input": defines the input to be used for the search (str)
• "emb_col": the column that contains the vectorized results (str)
• "result_col": defines the name of the column that contains the search results (str, optional, default: 'search_result')
• "top_k": number of rows to return. If set as None, returns the entire data table (int, optional, default: 1000)

SEARCH IMAGE Example

An example "SEARCH IMAGE" query can be found in Search Image by Image.

%%thanosql
SEARCH IMAGE 
USING my_image_search_model
OPTIONS (
    search_by='image',
    search_input='tutorial_data/mnist_data/test/923.jpg',
    emb_col='convert_result',
    result_col='search_result'
    )
AS
SELECT *
FROM mnist_test

---

Last update: 2023-08-09