From af92ac9e63d31f6bee2716174a44aacf3caea026 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Sat, 1 Sep 2018 18:35:28 +0200 Subject: [PATCH] updates --- README.md | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index a4d1469e..217be811 100755 --- a/README.md +++ b/README.md @@ -19,7 +19,11 @@ 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`. 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 (in progress to 160 epochs, will update) +Run `train.py` to begin training after downloading COCO data with `data/get_coco_dataset.sh`. + +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 (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 @@ -40,7 +44,7 @@ HS**V** Intensity | +/- 50% # Inference -Checkpoints will be saved in `/checkpoints` directory. Run `detect.py` to apply trained weights to an image, such as `zidane.jpg` from the `data/samples` folder, shown here. +Checkpoints are saved in `/checkpoints` directory. Run `detect.py` to apply trained weights to an image, such as `zidane.jpg` from the `data/samples` folder, shown here. ![Alt](https://github.com/ultralytics/yolov3/blob/master/data/zidane_result.jpg "inference example") # Testing