From 954b11bc17b56fac7bd0d864e84f0a8f6e465a6a Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Fri, 21 Jun 2019 09:46:58 -0400
Subject: [PATCH] update
---
.../models_class1_pan/GENERATE.sh | 22 +++++++++++++++++--
.../generate_hyperparameters.py | 2 +-
2 files changed, 21 insertions(+), 3 deletions(-)
diff --git a/downloads-generation/models_class1_pan/GENERATE.sh b/downloads-generation/models_class1_pan/GENERATE.sh
index ca880004..5bf20841 100755
--- a/downloads-generation/models_class1_pan/GENERATE.sh
+++ b/downloads-generation/models_class1_pan/GENERATE.sh
@@ -35,6 +35,9 @@ echo "Detected GPUS: $GPUS"
PROCESSORS=$(getconf _NPROCESSORS_ONLN)
echo "Detected processors: $PROCESSORS"
+export PYTHONUNBUFFERED=1
+VERBOSITY=1
+
mhcflurry-class1-train-pan-allele-models \
--data "$(mhcflurry-downloads path data_curated)/curated_training_data.with_mass_spec.csv.bz2" \
--allele-sequences "$(mhcflurry-downloads path allele_sequences)/allele_sequences.csv" \
@@ -42,11 +45,26 @@ mhcflurry-class1-train-pan-allele-models \
--held-out-measurements-per-allele-fraction-and-max 0.25 100 \
--ensemble-size 4 \
--hyperparameters hyperparameters.yaml \
- --out-models-dir models-unselected \
- --num-jobs 4 --gpus $GPUS --max-workers-per-gpu 1 --max-tasks-per-worker 1
+ --out-models-dir models-unselected.with_mass_spec \
+ --worker-log-dir "$SCRATCH_DIR/$DOWNLOAD_NAME" \
+ --verbosity $VERBOSITY \
+ --num-jobs $GPUS --max-tasks-per-worker 1 --gpus $GPUS --max-workers-per-gpu 1
+
+mhcflurry-class1-train-pan-allele-models \
+ --data "$(mhcflurry-downloads path data_curated)/curated_training_data.no_mass_spec.csv.bz2" \
+ --allele-sequences "$(mhcflurry-downloads path allele_sequences)/allele_sequences.csv" \
+ --pretrain-data "$(mhcflurry-downloads path random_peptide_predictions)/predictions.csv.bz2" \
+ --held-out-measurements-per-allele-fraction-and-max 0.25 100 \
+ --ensemble-size 4 \
+ --hyperparameters hyperparameters.yaml \
+ --out-models-dir models-unselected.no_mass_spec \
+ --worker-log-dir "$SCRATCH_DIR/$DOWNLOAD_NAME" \
+ --verbosity $VERBOSITY \
+ --num-jobs $GPUS --max-tasks-per-worker 1 --gpus $GPUS --max-workers-per-gpu 1
cp $SCRIPT_ABSOLUTE_PATH .
bzip2 LOG.txt
+for i in $(ls LOG-worker.*.txt) ; do bzip2 $i ; done
tar -cjf "../${DOWNLOAD_NAME}.with_unselected.tar.bz2" *
echo "Created archive: $SCRATCH_DIR/${DOWNLOAD_NAME}.with_unselected.tar.bz2"
diff --git a/downloads-generation/models_class1_pan/generate_hyperparameters.py b/downloads-generation/models_class1_pan/generate_hyperparameters.py
index 72be989f..f07639ca 100644
--- a/downloads-generation/models_class1_pan/generate_hyperparameters.py
+++ b/downloads-generation/models_class1_pan/generate_hyperparameters.py
@@ -50,7 +50,7 @@ base_hyperparameters = {
grid = []
for layer_sizes in [[512, 256], [512, 512],]:
for pretrain in [True, False]:
- for l1 in [0.0, 0.0001, 0.001, 0.01]:
+ for l1 in [0.0, 0.00001, 0.0001, 0.001]:
new = deepcopy(base_hyperparameters)
new["layer_sizes"] = layer_sizes
new["dense_layer_l1_regularization"] = l1
--
GitLab