From 7672505d458de06acec3e5300003e04cc3e5c2ff Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Sat, 1 Sep 2018 13:43:07 +0200 Subject: [PATCH] updates --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0737f8c2..2079d5c1 100755 --- a/README.md +++ b/README.md @@ -22,7 +22,7 @@ Python 3.6 or later with the following `pip3 install -U -r requirements.txt` pac Run `train.py` to begin training after downloading COCO data with `data/get_coco_dataset.sh`. 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 (coming soon) ![Alt](https://github.com/ultralytics/yolov3/blob/master/data/coco_training_loss.png "coco training loss") -## Augmentation +## Image Augmentation `datasets.py` applies random augmentation to the input images in accordance with the following specifications. Augmentation is applied *only* during training, not during inference. Bounding boxes are automatically tracked and updated with the images. 416 x 416 examples pictured below.