Apply suggestions from code review

course_UvA-DL/04-inception-resnet-densenet/Inception_ResNet_DenseNet.py

@@ -349,7 +349,7 @@ def train_model(model_name, save_name=None, **kwargs):
     trainer = L.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, save_name),  # Where to save models
         # We run on a single GPU (if possible)
-        accelerator=("cuda" if str(device) == "cuda:0" else "cpu"),
+        accelerator="auto",
         devices=1,
         # How many epochs to train for if no patience is set
         max_epochs=180,

course_UvA-DL/05-transformers-and-MH-attention/Transformers_MHAttention.py

@@ -979,7 +979,7 @@ def train_reverse(**kwargs):
     trainer = L.Trainer(
         default_root_dir=root_dir,
         callbacks=[ModelCheckpoint(save_weights_only=True, mode="max", monitor="val_acc")],
-        accelerator=("cuda" if str(device).startswith("cuda") else "cpu"),
+        accelerator="auto",
         devices=1,
         max_epochs=10,
         gradient_clip_val=5,
@@ -1439,7 +1439,7 @@ def train_anomaly(**kwargs):
     trainer = L.Trainer(
         default_root_dir=root_dir,
         callbacks=[ModelCheckpoint(save_weights_only=True, mode="max", monitor="val_acc")],
-        accelerator=("cuda" if str(device).startswith("cuda") else "cpu"),
+        accelerator="auto",
         devices=1,
         max_epochs=100,
         gradient_clip_val=2,

course_UvA-DL/07-deep-energy-based-generative-models/Deep_Energy_Models.py

@@ -640,7 +640,7 @@ def train_model(**kwargs):
     # Create a PyTorch Lightning trainer with the generation callback
     trainer = L.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, "MNIST"),
-        accelerator=("cuda" if str(device).startswith("cuda") else "cpu"),
+        accelerator="auto",
         devices=1,
         max_epochs=60,
         gradient_clip_val=0.1,

course_UvA-DL/08-deep-autoencoders/Deep_Autoencoders.py

@@ -385,7 +385,7 @@ def train_cifar(latent_dim):
     # Create a PyTorch Lightning trainer with the generation callback
     trainer = L.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, "cifar10_%i" % latent_dim),
-        accelerator=("cuda" if str(device).startswith("cuda") else "cpu"),
+        accelerator="auto",
         devices=1,
         max_epochs=500,
         callbacks=[