From 7f257d30c5063a4ad59a3ebddb6401f631b039c3 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Fri, 28 Dec 2018 19:23:35 +0100 Subject: [PATCH] Update README.md --- README.md | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index e027a368..491e26f1 100755 --- a/README.md +++ b/README.md @@ -24,6 +24,7 @@ Python 3.7 or later with the following `pip3 install -U -r requirements.txt` pac **Resume Training:** Run `train.py --resume` to resume training from the most recently saved checkpoint `weights/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. Default training settings produce loss plots below, with **training speed of 0.6 s/batch on a 1080 Ti (15 epochs/day)** or 0.45 s/batch on a 2080 Ti. + ![Alt](https://user-images.githubusercontent.com/26833433/49822374-3b27bf00-fd7d-11e8-9180-f0ac9fe2fdb4.png "coco training loss") ## Image Augmentation @@ -32,10 +33,10 @@ Each epoch trains on 120,000 images from the train and validate COCO sets, and t Augmentation | Description --- | --- -Translation | +/- 20% (vertical and horizontal) +Translation | +/- 10% (vertical and horizontal) Rotation | +/- 5 degrees -Shear | +/- 3 degrees (vertical and horizontal) -Scale | +/- 20% +Shear | +/- 2 degrees (vertical and horizontal) +Scale | +/- 10% Reflection | 50% probability (horizontal-only) H**S**V Saturation | +/- 50% HS**V** Intensity | +/- 50% @@ -47,7 +48,7 @@ HS**V** Intensity | +/- 50% Run `detect.py` to apply trained weights to an image and visualize results, such as `zidane.jpg` from the `data/samples` folder, shown here. **YOLOv3:** `detect.py --cfg cfg/yolov3.cfg --weights weights/yolov3.pt` - + **YOLOv3-tiny:** `detect.py --cfg cfg/yolov3-tiny.cfg --weights weights/yolov3-tiny.pt`