diff --git a/research/mi_lira_2021/README.md b/research/mi_lira_2021/README.md
index 72cd48f..ae68154 100644
--- a/research/mi_lira_2021/README.md
+++ b/research/mi_lira_2021/README.md
@@ -8,14 +8,15 @@ by Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, and F
 
 ### INSTALLING
 
-You will need to install fairly standard dependencies
+You will need to install fairly standard dependencies and python 3.11 minimum.
 
-`pip install scipy, sklearn, numpy, matplotlib`
-
-and also some machine learning framework to train models. We train our models
-with JAX + ObJAX so you will need to follow build instructions for that
-https://github.com/google/objax
-https://objax.readthedocs.io/en/latest/installation_setup.html
+```
+pip install scipy scikit-learn numpy matplotlib tensorflow tensorflow_datasets objax
+RELEASE_URL="https://storage.googleapis.com/jax-releases/jax_cuda_releases.html"
+JAX_VERSION=`python3 -c 'import jax; print(jax.__version__)'`
+pip uninstall -y jaxlib
+pip install -f $RELEASE_URL jax[cuda]==$JAX_VERSION
+```
 
 ### RUNNING THE CODE
 
diff --git a/research/mi_lira_2021/scripts/train_demo.sh b/research/mi_lira_2021/scripts/train_demo.sh
index 20e5e91..3732a1e 100644
--- a/research/mi_lira_2021/scripts/train_demo.sh
+++ b/research/mi_lira_2021/scripts/train_demo.sh
@@ -11,7 +11,7 @@
 # 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
+mkdir -p logs
 
 SECONDS=0
 
diff --git a/research/mi_lira_2021/scripts/train_demo_multigpu.sh b/research/mi_lira_2021/scripts/train_demo_multigpu.sh
index f20334b..1fbd86c 100644
--- a/research/mi_lira_2021/scripts/train_demo_multigpu.sh
+++ b/research/mi_lira_2021/scripts/train_demo_multigpu.sh
@@ -11,6 +11,7 @@
 # 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 -p 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='1' 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 &