diff --git a/README.md b/README.md
index 4dc3fa8e..04348198 100755
--- a/README.md
+++ b/README.md
@@ -19,11 +19,12 @@ Python 3.6 or later with the following `pip3 install -U -r requirements.txt` pac
 
 # Training
 
-Run `train.py` to begin training after downloading COCO data with `data/get_coco_dataset.sh` and specifying COCO path on line 37 (local) or line 39 (cloud).
+***Start Training:*** Run `train.py` to begin training after downloading COCO data with `data/get_coco_dataset.sh` and specifying COCO path on line 37 (local) or line 39 (cloud).
 
-Run `train.py -resume 1` to resume training from the most recently saved checkpoint `checkpoints/latest.pt`.
+***Resume Training:*** Run `train.py -resume 1` to resume training from the most recently saved checkpoint `checkpoints/latest.pt`.
 
 Each epoch trains on 120,000 images from the train and validate COCO sets, and tests on 5000 images from the COCO validate set. An Nvidia GTX 1080 Ti will process ~10 epochs/day with full augmentation, or ~15 epochs/day without input image augmentation. Loss plots for the bounding boxes, objectness and class confidence should appear similar to results shown here (results in progress to 160 epochs, will update).
+
 ![Alt](https://github.com/ultralytics/yolov3/blob/master/data/coco_training_loss.png "coco training loss")
 
 ## Image Augmentation
diff --git a/train.py b/train.py
index c70b5af7..cdfd3428 100644
--- a/train.py
+++ b/train.py
@@ -93,6 +93,7 @@ def main(opt):
     for epoch in range(opt.epochs):
         epoch += start_epoch
 
+        # Random input
         # img_size = random.choice(range(10, 20)) * 32
         # dataloader = ListDataset(train_path, batch_size=opt.batch_size, img_size=img_size)
         # print('Running image size %g' % img_size)