diff --git a/brats/algorithms.py b/brats/algorithms.py
index 14defac..ad54cd9 100644
--- a/brats/algorithms.py
+++ b/brats/algorithms.py
@@ -151,12 +151,13 @@ def infer_batch(
 
         data_folder = Path(data_folder)
         output_folder = Path(output_folder)
+        output_folder.mkdir(parents=True, exist_ok=True)
 
         temp_data_folder = Path(tempfile.mkdtemp())
         temp_output_folder = Path(tempfile.mkdtemp())
         if log_file:
             inference_log_file = logger.add(log_file, level="INFO", catch=True)
-            logger.info(f"Logging to: {log_file.absolute()}")
+            logger.info(f"Logging to: {Path(log_file).absolute()}")
         try:
             self._log_algorithm_info()
             # find subjects
diff --git a/brats/docker.py b/brats/docker.py
index 5d36af5..6e9f809 100644
--- a/brats/docker.py
+++ b/brats/docker.py
@@ -239,19 +239,21 @@ def run_docker(
         additional_files_path=additional_files_path,
         output_path=output_path,
     )
-
-    logger.info(f"{'Starting inference'}")
+    logger.debug(f"Volume mappings: {volume_mappings}")
 
     command_args, extra_args = _build_args(
         algorithm=algorithm, additional_files_path=additional_files_path
     )
+    logger.debug(f"Command args: {command_args}, Extra args: {extra_args}")
 
     # device setup
     device_requests = _handle_device_requests(
         algorithm=algorithm, cuda_devices=cuda_devices, force_cpu=force_cpu
     )
+    logger.debug(f"Device requests: {device_requests}")
 
     # Run the container
+    logger.info(f"{'Starting inference'}")
     container = client.containers.run(
         image=algorithm.run_args.docker_image,
         volumes=volume_mappings,