This is an automated email from the ASF dual-hosted git repository.
okislal pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/madlib.git
The following commit(s) were added to refs/heads/master by this push:
new 205bdba updated user docs for madlib-keras with BYOM inference
205bdba is described below
commit 205bdbaf15ef2e2bdd0d48666cbd28346be678ef
Author: Frank McQuillan <fmcquil...@pivotal.io>
AuthorDate: Thu Aug 15 10:31:29 2019 -0700
updated user docs for madlib-keras with BYOM inference
---
.../modules/deep_learning/madlib_keras.sql_in | 182 ++++++++-------------
1 file changed, 68 insertions(+), 114 deletions(-)
diff --git a/src/ports/postgres/modules/deep_learning/madlib_keras.sql_in
b/src/ports/postgres/modules/deep_learning/madlib_keras.sql_in
index c69f158..84c1054 100644
--- a/src/ports/postgres/modules/deep_learning/madlib_keras.sql_in
+++ b/src/ports/postgres/modules/deep_learning/madlib_keras.sql_in
@@ -74,6 +74,9 @@ can perform better than stochastic gradient descent
because it uses more than one training example at a time,
typically resulting faster and smoother convergence [3].
+You can also do inference on models that have not been trained with MADlib,
+but rather imported from an external source.
+
@brief Solves image classification problems by calling
the Keras API
@@ -620,8 +623,10 @@ madlib_keras_predict(
@anchor keras_predict_byom
-@par Predict BYOM (Bring your own model)
-The predict byom function has the following format:
+@par Predict BYOM (bring your own model)
+The predict BYOM function allows you to do inference on models that
+have not been trained on MADlib, but rather imported from elsewhere.
+It has the following format:
<pre class="syntax">
madlib_keras_predict_byom(
model_arch_table,
@@ -645,11 +650,11 @@ madlib_keras_predict_byom(
<DD>TEXT. Name of the architecture table containing the model
to use for prediction. The model weights and architecture can be loaded to
this table by using the
- <a href="group__grp__keras__model__arch.html">load_keras_model</a> function
+ <a href="group__grp__keras__model__arch.html">load_keras_model</a> function.
</DD>
<DT>model_arch_id</DT>
- <DD>INTEGER. This is the id in 'model_arch_table'containing the model
+ <DD>INTEGER. This is the id in 'model_arch_table' containing the model
architecture and model weights to use for prediction.
</DD>
@@ -657,9 +662,7 @@ madlib_keras_predict_byom(
<DD>TEXT. Name of the table containing the dataset to
predict on. Note that test data is not preprocessed (unlike
fit and evaluate) so put one test image per row for prediction.
- Also see the comment below for the 'independent_varname' parameter
- regarding normalization.
-
+ Set the 'normalizing_const' below for the independent variable if necessary.
</DD>
<DT>id_col</DT>
@@ -668,9 +671,7 @@ madlib_keras_predict_byom(
<DT>independent_varname</DT>
<DD>TEXT. Column with independent variables in the test table.
- If a 'normalizing_const' is specified when preprocessing the
- training dataset, this same normalization will be applied to
- the independent variables used in predict.
+ Set the 'normalizing_const' below if necessary.
</DD>
<DT>output_table</DT>
@@ -679,14 +680,14 @@ madlib_keras_predict_byom(
<table class="output">
<tr>
<th>id</th>
- <td>Gives the 'id' for each prediction, corresponding to each row from
the test_table.</td>
+ <td>Gives the 'id' for each prediction, corresponding to each row from
the 'test_table'.</td>
</tr>
<tr>
<th>estimated_dependent_var</th>
<td>
- (For pred_type='response') The estimated class for classification. If
- class_values is passed in as NULL, then we assume that the class
- labels are [0,1,2...,n] where n in the num of classes in the model
+ (For pred_type='response') Estimated class for classification. If
+ the 'class_values' parameter is passed in as NULL, then we assume that
the class
+ labels are [0,1,2...,n-1] where n-1 is the number of classes in the
model
architecture.
</td>
</tr>
@@ -694,11 +695,11 @@ madlib_keras_predict_byom(
<th>prob_CLASS</th>
<td>
(For pred_type='prob' for classification)
- The probability of a given class.
- If class_values is passed in as NULL, we create just one column called
- 'prob' which is an array of probabilities of all the classes.
- Otherwise if class_values is not NULL, then there will be one
- column for each class in the training data.
+ Probability of a given class.
+ If 'class_values' is passed in as NULL, we create one column called
+ 'prob' which is an array of probabilities for each class.
+ If 'class_values' is not NULL, then there will be one
+ column for each class.
</td>
</tr>
@@ -725,8 +726,8 @@ madlib_keras_predict_byom(
<DT>class_values (optional)</DT>
<DD>TEXT[], default: NULL.
- List of class labels that were used while training the model. See the
- output_table column for more details.
+ List of class labels that were used while training the model. See the
'output_table'
+ column for more details.
</DD>
<DT>normalizing_const (optional)</DT>
@@ -1170,84 +1171,67 @@ WHERE q.actual=q.estimated;
(1 row)
</pre>
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-# Predict BYOM.
We will use the validation dataset for prediction
as well, which is not usual but serves to show the
syntax. See <a href="group__grp__keras__model__arch.html">load_keras_model</a>
for details on how to load the model architecture and weights.
-
-
-The prediction is in the 'estimated_dependent_var'
-column:
+In this example we will use weights we already have:
+<pre class="example">
+UPDATE model_arch_library SET model_weights = model_data FROM iris_model WHERE
model_id = 1;
+</pre>
+Now train using a model from the model architecture table directly
+without referencing the model table from the MADlib training:
<pre class="example">
-UPDATE model_arch_library set model_weights = (select model_data from
iris_model) WHERE model_id = 1;
-
DROP TABLE IF EXISTS iris_predict_byom;
-SELECT madlib.madlib_keras_predict_byom('model_arch_library', -- model arch
table
- 1, -- model arch id
- 'iris_test', -- test_table
- 'id', -- id column
- 'attributes', -- independent var
- 'iris_predict_byom', -- output table
- 'response', -- pred_type
- 0, -- gpus_per_host
- ARRAY['Iris-setosa', 'Iris-versicolor',
- 'Iris-virginica'], -- class_values
- 1.0 -- normalizing_const
+SELECT madlib.madlib_keras_predict_byom('model_arch_library', -- model arch
table
+ 1, -- model arch id
+ 'iris_test', -- test_table
+ 'id', -- id column
+ 'attributes', -- independent
var
+ 'iris_predict_byom', -- output table
+ 'response', -- prediction
type
+ 0, -- gpus per host
+ ARRAY['Iris-setosa',
'Iris-versicolor', 'Iris-virginica'], -- class values
+ 1.0 -- normalizing
const
);
SELECT * FROM iris_predict_byom ORDER BY id;
</pre>
+The prediction is in the 'estimated_dependent_var' column:
<pre class="result">
id | estimated_dependent_var
------+-------------------------
- 1 | Iris-setosa
+-----+----------------------
4 | Iris-setosa
- 9 | Iris-setosa
- 27 | Iris-setosa
- 32 | Iris-setosa
- 35 | Iris-setosa
- 40 | Iris-setosa
- 41 | Iris-setosa
- 44 | Iris-setosa
- 46 | Iris-setosa
- 55 | Iris-versicolor
- 56 | Iris-versicolor
- 66 | Iris-versicolor
+ 6 | Iris-setosa
+ 8 | Iris-setosa
+ 12 | Iris-setosa
+ 13 | Iris-setosa
+ 15 | Iris-setosa
+ 24 | Iris-setosa
+ 30 | Iris-setosa
+ 38 | Iris-setosa
+ 49 | Iris-setosa
+ 60 | Iris-virginica
+ 68 | Iris-versicolor
69 | Iris-versicolor
- 75 | Iris-versicolor
76 | Iris-versicolor
- 102 | Iris-virginica
- 105 | Iris-virginica
- 108 | Iris-virginica
- 113 | Iris-virginica
- 115 | Iris-virginica
- 116 | Iris-virginica
- 118 | Iris-virginica
- 119 | Iris-virginica
- 122 | Iris-virginica
- 125 | Iris-virginica
- 133 | Iris-virginica
- 134 | Iris-virginica
- 135 | Iris-virginica
- 138 | Iris-virginica
+ 78 | Iris-versicolor
+ 81 | Iris-versicolor
+ 85 | Iris-virginica
+ 90 | Iris-versicolor
+ 91 | Iris-versicolor
+ 94 | Iris-virginica
+ 104 | Iris-virginica
+ 106 | Iris-versicolor
+ 107 | Iris-virginica
+ 110 | Iris-virginica
+ 119 | Iris-versicolor
+ 127 | Iris-virginica
+ 129 | Iris-virginica
+ 134 | Iris-versicolor
+ 139 | Iris-virginica
+ 144 | Iris-virginica
+(30 rows)
</pre>
Count missclassifications:
<pre class="example">
@@ -1276,36 +1260,6 @@ WHERE q.actual=q.estimated;
</pre>
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
<h4>Classification with Other Parameters</h4>
-# Validation dataset. Now use a validation dataset
