Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
M
mhc_rank
Manage
Activity
Members
Labels
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Model registry
Operate
Environments
Terraform modules
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Patrick Skillman-Lawrence
mhc_rank
Commits
3b35c183
Commit
3b35c183
authored
9 years ago
by
Alex Rubinsteyn
Browse files
Options
Downloads
Patches
Plain Diff
added more options to model search script
parent
e889d8f3
Loading
Loading
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
experiments/nips2015-model-selection.py
+20
-1
20 additions, 1 deletion
experiments/nips2015-model-selection.py
with
20 additions
and
1 deletion
experiments/nips2015-model-selection.py
+
20
−
1
View file @
3b35c183
...
...
@@ -58,6 +58,10 @@ def parse_float_list(string):
substrings
=
[
substring
.
strip
()
for
substring
in
string
.
split
(
"
,
"
)]
return
[
float
(
substring
)
for
substring
in
substrings
if
substring
]
def
parse_string_list
(
string
):
return
[
substring
.
strip
()
for
substring
in
string
.
split
(
"
,
"
)]
parser
.
add_argument
(
"
--binding-data-csv-path
"
,
default
=
PETERS2009_CSV_PATH
,
...
...
@@ -100,7 +104,7 @@ parser.add_argument(
parser
.
add_argument
(
"
--minibatch-size
"
,
default
=
256
,
default
=
[
256
]
,
type
=
parse_int_list
,
help
=
"
How many samples to use in stochastic gradient estimation
"
)
...
...
@@ -122,9 +126,24 @@ parser.add_argument(
type
=
parse_int_list
,
help
=
"
Comma separated list of hidden layer sizes
"
)
parser
.
add_argument
(
"
--init
"
,
default
=
[
"
uniform
"
,
"
glorot_uniform
"
],
type
=
parse_string_list
,
help
=
"
Comma separated list of initialization methods
"
)
parser
.
add_argument
(
"
--activation
"
,
default
=
[
"
tanh
"
,
"
relu
"
,
"
prelu
"
],
type
=
parse_string_list
,
help
=
"
Comma separated list of activation functions
"
)
if
__name__
==
"
__main__
"
:
args
=
parser
.
parse_args
()
configs
=
generate_all_model_configs
(
activations
=
args
.
activation
,
init_methods
=
args
.
init
,
dropout_values
=
args
.
dropout
,
minibatch_sizes
=
args
.
minibatch_size
,
embedding_sizes
=
args
.
embedding_size
,
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment