add info about new recommendation to train script as well

documentation/resenc_presets.md

@@ -52,7 +52,7 @@ We offer three new presets, each targeted for a different GPU VRAM and compute b
 - **nnU-Net ResEnc L**: requires a GPU with 24GB VRAM. Training time: ~35h on A100
 - **nnU-Net ResEnc XL**: requires a GPU with 40GB VRAM. Training time: ~66h on A100
 
-We recommend **nnU-Net ResEnc L** as the new default nnU-Net configuration to try!
+### **:point_left: We recommend **nnU-Net ResEnc L** as the new default nnU-Net configuration! :point_right:**
 
 The new presets are available as follows ((M/L/XL) = pick one!):
 1. Specify the desired configuration when running experiment planning and preprocessing: 

nnunetv2/run/run_training.py

@@ -148,6 +148,12 @@ def run_training(dataset_name_or_id: Union[str, int],
                  disable_checkpointing: bool = False,
                  val_with_best: bool = False,
                  device: torch.device = torch.device('cuda')):
+    if plans_identifier == 'nnUNetPlans':
+        print("\n############################\n"
+              "INFO: You are using the old nnU-Net default plans. We have updated our recommendations. "
+              "Please consider using those instead! "
+              "Read more here: https://github.com/MIC-DKFZ/nnUNet/blob/master/documentation/resenc_presets.md"
+              "\n############################\n")
     if isinstance(fold, str):
         if fold != 'all':
             try: