From b76ba510125f8ec47d79a8fff11ada2531344da0 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Sat, 1 Sep 2018 13:18:53 +0200 Subject: [PATCH 1/2] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 5d4eec39..e496a2b9 100755 --- a/README.md +++ b/README.md @@ -19,7 +19,7 @@ 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 (coming soon) +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 image augmentation, or ~15 epochs/day with no 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 "training loss") # Inference From d3be281418187e88996ed905327f38cb9fb9481d Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Sat, 1 Sep 2018 13:20:01 +0200 Subject: [PATCH 2/2] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index e496a2b9..d8aa9d7c 100755 --- a/README.md +++ b/README.md @@ -19,7 +19,7 @@ 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 image augmentation, or ~15 epochs/day with no augmentation. Loss plots for the bounding boxes, objectness and class confidence should appear similar to results shown here (coming soon) +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 image augmentation, or ~15 epochs/day with no augmentation. Loss plots for bounding boxes, objectness and classification should appear similar to results shown here (training currently in-progress to 160 epochs). ![Alt](https://github.com/ultralytics/yolov3/blob/master/data/coco_training_loss.png "training loss") # Inference