From d2b44b3822fc960d959a65852a9e2eec567d1b44 Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Thu, 8 Feb 2018 18:54:25 -0500
Subject: [PATCH] new models_class1_unselected download
---
.../models_class1/generate_hyperparameters.py | 41 ++++++++++---------
.../GENERATE.sh | 4 +-
.../README.md | 0
.../generate_hyperparameters.py | 0
4 files changed, 23 insertions(+), 22 deletions(-)
rename downloads-generation/{models_class1_no_mass_spec => models_class1_unselected}/GENERATE.sh (92%)
rename downloads-generation/{models_class1_no_mass_spec => models_class1_unselected}/README.md (100%)
rename downloads-generation/{models_class1_no_mass_spec => models_class1_unselected}/generate_hyperparameters.py (100%)
diff --git a/downloads-generation/models_class1/generate_hyperparameters.py b/downloads-generation/models_class1/generate_hyperparameters.py
index dcd48aa8..c130471f 100644
--- a/downloads-generation/models_class1/generate_hyperparameters.py
+++ b/downloads-generation/models_class1/generate_hyperparameters.py
@@ -10,7 +10,7 @@ base_hyperparameters = {
##########################################
# ENSEMBLE SIZE
##########################################
- "n_models": 1,
+ "n_models": 8,
##########################################
# OPTIMIZATION
@@ -19,7 +19,7 @@ base_hyperparameters = {
"patience": 20,
"early_stopping": True,
"validation_split": 0.1,
- "minibatch_size": 128,
+ "minibatch_size": None,
"loss": "custom:mse_with_inequalities",
##########################################
@@ -52,28 +52,29 @@ base_hyperparameters = {
"activation": "tanh",
"output_activation": "sigmoid",
"layer_sizes": [16],
- "dense_layer_l1_regularization": 0.001,
+ "dense_layer_l1_regularization": None,
"batch_normalization": False,
"dropout_probability": 0.0,
}
grid = []
-for dense_layer_size in [64, 32, 16]:
- for l1 in [0.001, 0.01, 0.0]:
- for num_lc in [0, 1, 2]:
- for lc_kernel_size in [3, 5]:
- new = deepcopy(base_hyperparameters)
- new["layer_sizes"] = [dense_layer_size]
- new["dense_layer_l1_regularization"] = l1
- (lc_layer,) = new["locally_connected_layers"]
- lc_layer['kernel_size'] = lc_kernel_size
- if num_lc == 0:
- new["locally_connected_layers"] = []
- elif num_lc == 1:
- new["locally_connected_layers"] = [lc_layer]
- elif num_lc == 2:
- new["locally_connected_layers"] = [lc_layer, deepcopy(lc_layer)]
- if not grid or new not in grid:
- grid.append(new)
+for minibatch_size in [32, 128, 512]:
+ for dense_layer_size in [8, 16, 32, 64, 128]:
+ for l1 in [0.0, 0.001, 0.01, 0.1]:
+ for num_lc in [0, 1, 2]:
+ for lc_kernel_size in [3, 5]:
+ new = deepcopy(base_hyperparameters)
+ new["layer_sizes"] = [dense_layer_size]
+ new["dense_layer_l1_regularization"] = l1
+ (lc_layer,) = new["locally_connected_layers"]
+ lc_layer['kernel_size'] = lc_kernel_size
+ if num_lc == 0:
+ new["locally_connected_layers"] = []
+ elif num_lc == 1:
+ new["locally_connected_layers"] = [lc_layer]
+ elif num_lc == 2:
+ new["locally_connected_layers"] = [lc_layer, deepcopy(lc_layer)]
+ if not grid or new not in grid:
+ grid.append(new)
dump(grid, stdout)
diff --git a/downloads-generation/models_class1_no_mass_spec/GENERATE.sh b/downloads-generation/models_class1_unselected/GENERATE.sh
similarity index 92%
rename from downloads-generation/models_class1_no_mass_spec/GENERATE.sh
rename to downloads-generation/models_class1_unselected/GENERATE.sh
index 20b74978..4890da0c 100755
--- a/downloads-generation/models_class1_no_mass_spec/GENERATE.sh
+++ b/downloads-generation/models_class1_unselected/GENERATE.sh
@@ -7,7 +7,7 @@
set -e
set -x
-DOWNLOAD_NAME=models_class1_no_mass_spec
+DOWNLOAD_NAME=models_class1_unselected
SCRATCH_DIR=${TMPDIR-/tmp}/mhcflurry-downloads-generation
SCRIPT_ABSOLUTE_PATH="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/$(basename "${BASH_SOURCE[0]}")"
SCRIPT_DIR=$(dirname "$SCRIPT_ABSOLUTE_PATH")
@@ -35,7 +35,7 @@ time mhcflurry-class1-train-allele-specific-models \
--data "$(mhcflurry-downloads path data_curated)/curated_training_data.no_mass_spec.csv.bz2" \
--hyperparameters hyperparameters.yaml \
--out-models-dir models \
- --percent-rank-calibration-num-peptides-per-length 100000 \
+ --percent-rank-calibration-num-peptides-per-length 0 \
--min-measurements-per-allele 75 \
--num-jobs 32 16
diff --git a/downloads-generation/models_class1_no_mass_spec/README.md b/downloads-generation/models_class1_unselected/README.md
similarity index 100%
rename from downloads-generation/models_class1_no_mass_spec/README.md
rename to downloads-generation/models_class1_unselected/README.md
diff --git a/downloads-generation/models_class1_no_mass_spec/generate_hyperparameters.py b/downloads-generation/models_class1_unselected/generate_hyperparameters.py
similarity index 100%
rename from downloads-generation/models_class1_no_mass_spec/generate_hyperparameters.py
rename to downloads-generation/models_class1_unselected/generate_hyperparameters.py
--
GitLab