From f3af0a3a5caa7e44dfdd76d54c083dcf5cd59e7b Mon Sep 17 00:00:00 2001
From: Akemi Izuko <akemi@noway.moe>
Date: Mon, 14 Oct 2024 14:14:45 -0600
Subject: [PATCH] Lira2021: fix training for cuda 12

---
 research/mi_lira_2021/scripts/train_demo.sh | 33 +++++++++++----------
 research/mi_lira_2021/train.py              |  4 ++-
 2 files changed, 20 insertions(+), 17 deletions(-)

diff --git a/research/mi_lira_2021/scripts/train_demo.sh b/research/mi_lira_2021/scripts/train_demo.sh
index 2ab43e3..8f7d04d 100644
--- a/research/mi_lira_2021/scripts/train_demo.sh
+++ b/research/mi_lira_2021/scripts/train_demo.sh
@@ -11,20 +11,21 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+mkdir logs
 
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 0 --logdir exp/cifar10 &> logs/log_0
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 1 --logdir exp/cifar10 &> logs/log_1
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 2 --logdir exp/cifar10 &> logs/log_2
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 3 --logdir exp/cifar10 &> logs/log_3
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 4 --logdir exp/cifar10 &> logs/log_4
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 5 --logdir exp/cifar10 &> logs/log_5
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 6 --logdir exp/cifar10 &> logs/log_6
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 7 --logdir exp/cifar10 &> logs/log_7
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 8 --logdir exp/cifar10 &> logs/log_8
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 9 --logdir exp/cifar10 &> logs/log_9
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 10 --logdir exp/cifar10 &> logs/log_10
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 11 --logdir exp/cifar10 &> logs/log_11
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 12 --logdir exp/cifar10 &> logs/log_12
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 13 --logdir exp/cifar10 &> logs/log_13
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 14 --logdir exp/cifar10 &> logs/log_14
-CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 15 --logdir exp/cifar10 &> logs/log_15
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 0 --logdir exp/cifar10 2>&1 | tee logs/log_0
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 1 --logdir exp/cifar10 2>&1 | tee logs/log_1
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 2 --logdir exp/cifar10 2>&1 | tee logs/log_2
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 3 --logdir exp/cifar10 2>&1 | tee logs/log_3
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 4 --logdir exp/cifar10 2>&1 | tee logs/log_4
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 5 --logdir exp/cifar10 2>&1 | tee logs/log_5
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 6 --logdir exp/cifar10 2>&1 | tee logs/log_6
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 7 --logdir exp/cifar10 2>&1 | tee logs/log_7
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 8 --logdir exp/cifar10 2>&1 | tee logs/log_8
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 9 --logdir exp/cifar10 2>&1 | tee logs/log_9
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 10 --logdir exp/cifar10 2>&1 | tee logs/log_10
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 11 --logdir exp/cifar10 2>&1 | tee logs/log_11
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 12 --logdir exp/cifar10 2>&1 | tee logs/log_12
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 13 --logdir exp/cifar10 2>&1 | tee logs/log_13
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 14 --logdir exp/cifar10 2>&1 | tee logs/log_14
+CUDA_VISIBLE_DEVICES='0' python3 -u train.py --dataset=cifar10 --epochs=100 --save_steps=20 --arch wrn28-2 --num_experiments 16 --expid 15 --logdir exp/cifar10 2>&1 | tee logs/log_15
diff --git a/research/mi_lira_2021/train.py b/research/mi_lira_2021/train.py
index fa658ac..94ac685 100644
--- a/research/mi_lira_2021/train.py
+++ b/research/mi_lira_2021/train.py
@@ -66,7 +66,9 @@ class TrainLoop(objax.Module):
         for k, v in kv.items():
             if jn.isnan(v):
                 raise ValueError('NaN, try reducing learning rate', k)
-            if summary is not None:
+            if summary is not None and v.ndim == 1:
+                summary.scalar(k, float(v[0]))
+            elif summary is not None:
                 summary.scalar(k, float(v))
 
     def train(self, num_train_epochs: int, train_size: int, train: DataSet, test: DataSet, logdir: str, save_steps=100, patience=None):