This is an automated email from the ASF dual-hosted git repository.
domino 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 5d33cf6 DL: Remove weight passing for multi model evaluate
5d33cf6 is described below
commit 5d33cf645c57fa1c0d5e4fd78b49975c16a4fe09
Author: Orhan Kislal <okis...@apache.org>
AuthorDate: Mon Jun 22 19:55:40 2020 -0400
DL: Remove weight passing for multi model evaluate
Instead of reading the weights from a table and passing to the
evaluate function, we decided to pass the table directly and
let the evaluate function handle reading in the same query.
---
.../modules/deep_learning/madlib_keras.py_in | 34 ++++++++++++++++------
.../madlib_keras_fit_multiple_model.py_in | 8 ++---
.../deep_learning/madlib_keras_helper.py_in | 10 -------
3 files changed, 29 insertions(+), 23 deletions(-)
diff --git a/src/ports/postgres/modules/deep_learning/madlib_keras.py_in
b/src/ports/postgres/modules/deep_learning/madlib_keras.py_in
index ee27554..091fce2 100644
--- a/src/ports/postgres/modules/deep_learning/madlib_keras.py_in
+++ b/src/ports/postgres/modules/deep_learning/madlib_keras.py_in
@@ -33,6 +33,8 @@ from madlib_keras_validator import *
from madlib_keras_wrapper import *
from model_arch_info import *
+from madlib_keras_model_selection import ModelSelectionSchema
+
from utilities.utilities import _assert
from utilities.utilities import add_postfix
from utilities.utilities import is_platform_pg
@@ -396,7 +398,7 @@ def get_metrics_sql_string(metrics_list,
is_metrics_specified):
def compute_loss_and_metrics(schema_madlib, table, compile_params, model_arch,
serialized_weights, use_gpus,
accessible_gpus_for_seg,
dist_key_mapping, images_per_seg_val,
metrics_list, loss_list,
- curr_iter, is_final_iteration):
+ curr_iter, is_final_iteration, model_table=None,
mst_key=None):
"""
Compute the loss and metric using a given model (serialized_weights) on the
given dataset (table.)
@@ -411,7 +413,9 @@ def compute_loss_and_metrics(schema_madlib, table,
compile_params, model_arch,
accessible_gpus_for_seg,
dist_key_mapping,
images_per_seg_val,
- is_final_iteration)
+ is_final_iteration,
+ model_table,
+ mst_key)
end_val = time.time()
if len(evaluate_result) not in [1, 2]:
@@ -670,10 +674,10 @@ def validate_evaluate(module_name, model_table,
model_summary_table, test_table,
def get_loss_metric_from_keras_eval(schema_madlib, table, compile_params,
model_arch, serialized_weights, use_gpus,
accessible_gpus_for_seg, dist_key_mapping,
images_per_seg,
- is_final_iteration=True):
+ is_final_iteration=True, model_table=None,
mst_key=None):
dist_key_col = '0' if is_platform_pg() else DISTRIBUTION_KEY_COLNAME
- gp_segment_id_col = '0' if is_platform_pg() else GP_SEGMENT_ID_COLNAME
+ gp_segment_id_col = '0' if is_platform_pg() else
'__table__.{0}'.format(GP_SEGMENT_ID_COLNAME)
segments_per_host = get_segments_per_host()
mb_dep_var_col = MINIBATCH_OUTPUT_DEPENDENT_COLNAME_DL
@@ -688,14 +692,15 @@ def get_loss_metric_from_keras_eval(schema_madlib, table,
compile_params,
and accuracy of each tuple which then gets averaged to get the final
result.
"""
use_gpus = use_gpus if use_gpus else False
- evaluate_query = plpy.prepare("""
+
+ eval_sql = """
select ({schema_madlib}.internal_keras_evaluate(
{mb_dep_var_col},
{mb_indep_var_col},
{dep_shape_col},
{ind_shape_col},
$MAD${model_arch}$MAD$,
- $1,
+ {weights},
{compile_params},
{dist_key_col},
ARRAY{dist_key_mapping},
@@ -706,9 +711,20 @@ def get_loss_metric_from_keras_eval(schema_madlib, table,
compile_params,
ARRAY{accessible_gpus_for_seg},
{is_final_iteration}
)) as loss_metric
- from {table}
- """.format(**locals()), ["bytea"])
- res = plpy.execute(evaluate_query, [serialized_weights])
+ from {table} AS __table__ {mult_sql}
+ """
+
+ if mst_key:
+ weights = '__mt__.{0}'.format(MODEL_WEIGHTS_COLNAME)
+ mst_key_col = ModelSelectionSchema.MST_KEY
+ mult_sql = ', {model_table} AS __mt__ WHERE {mst_key_col} =
{mst_key}'.format(**locals())
+ res = plpy.execute(eval_sql.format(**locals()))
+ else:
+ weights = '$1'
+ mult_sql = ''
+ evaluate_query = plpy.prepare(eval_sql.format(**locals()), ["bytea"])
+ res = plpy.execute(evaluate_query, [serialized_weights])
+
loss_metric = res[0]['loss_metric']
return loss_metric
diff --git
a/src/ports/postgres/modules/deep_learning/madlib_keras_fit_multiple_model.py_in
b/src/ports/postgres/modules/deep_learning/madlib_keras_fit_multiple_model.py_in
index 9de9774..c122def 100644
---
a/src/ports/postgres/modules/deep_learning/madlib_keras_fit_multiple_model.py_in
+++
b/src/ports/postgres/modules/deep_learning/madlib_keras_fit_multiple_model.py_in
@@ -261,19 +261,19 @@ class FitMultipleModel():
images_per_seg = self.images_per_seg_valid
self.info_str += "\n\tValidation set after iteration
{0}:".format(epoch)
for mst in self.msts:
- weights = query_weights(self.model_output_table,
self.model_weights_col,
- self.mst_key_col, mst[self.mst_key_col])
model_arch, _ = get_model_arch_weights(self.model_arch_table,
mst[self.model_id_col])
_, metric, loss = compute_loss_and_metrics(
self.schema_madlib, table, "$madlib${0}$madlib$".format(
mst[self.compile_params_col]),
model_arch,
- weights,
+ None,
self.use_gpus,
self.accessible_gpus_for_seg,
seg_ids,
images_per_seg,
- [], [], epoch, True)
+ [], [], epoch, True,
+ self.model_output_table,
+ mst[self.mst_key_col])
mst_metric_eval_time[mst[self.mst_key_col]] \
.append(time.time() - self.metrics_elapsed_start_time)
mst_loss[mst[self.mst_key_col]].append(loss)
diff --git a/src/ports/postgres/modules/deep_learning/madlib_keras_helper.py_in
b/src/ports/postgres/modules/deep_learning/madlib_keras_helper.py_in
index 5be078b..b2b7397 100644
--- a/src/ports/postgres/modules/deep_learning/madlib_keras_helper.py_in
+++ b/src/ports/postgres/modules/deep_learning/madlib_keras_helper.py_in
@@ -235,16 +235,6 @@ def query_dist_keys(source_table, dist_key_col):
res = [x[dist_key_col] for x in res]
return res
-def query_weights(model_output_table, model_weights_col, mst_key_col, mst_key):
- mlp_weights_query = """
- SELECT {model_weights_col}, {mst_key_col}
- FROM {model_output_table}
- WHERE {mst_key_col} = {mst_key}
- """.format(**locals())
-
- res = plpy.execute(mlp_weights_query)
- return res[0][model_weights_col]
-
def create_summary_view(module_name, model_table, mst_key):
tmp_view_summary = unique_string('tmp_view_summary')
model_summary_table = add_postfix(model_table, "_summary")
