From ff68352bb11e413fbc67effd04067b7345b88829 Mon Sep 17 00:00:00 2001 From: Edmond Yoo <hj3yoo@uwaterloo.ca> Date: Sat, 08 Sep 2018 03:07:51 +0000 Subject: [PATCH] Trained second general model --- README.md | 21 ++++++++++++++++++++- 1 files changed, 20 insertions(+), 1 deletions(-) diff --git a/README.md b/README.md index d7344a5..9de35e6 100644 --- a/README.md +++ b/README.md @@ -26,4 +26,23 @@ <img src="https://github.com/hj3yoo/darknet/blob/master/figures/0_detection_result_5.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/0_detection_result_6.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/0_detection_result_7.jpg" width="360"> -The second and third problems should easily be solved by further augmenting the dataset with random lighting and image skew. I'll have to think more about the first problem, though. \ No newline at end of file +The second and third problems should easily be solved by further augmenting the dataset with random lighting and image skew. I'll have to think more about the first problem, though. + +## Day 1 +----------------------- + +Added several image augmentation techniques to apply to the training set: noise, dropout, light variation, and glaring: + +<img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_augmented_set_example_1.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_augmented_set_example_2.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_augmented_set_example_3.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_augmented_set_example_4.jpg" width="360"> + +Currently trying to generate enough images to start model training. Hopefully this helps. + +Recompiled darknet with OpenCV and CUDNN installed, and recalculated anchors. + +----------------------- + +I've ran a quick training with tiny_yolo configuration with new training data, and Voila! The model performs significantly better than the last iteration, even against some hard images with glaring & skew! The first prediction model can't detect anything from these new test images, so this is a huge improvement to the model :) + +<img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_detection_result_1.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_detection_result_2.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_detection_result_3.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_detection_result_4.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_detection_result_5.jpg" width="360"> <img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_detection_result_6.jpg" width="360"> + +<img src="https://github.com/hj3yoo/darknet/blob/master/figures/1_learning_curve.jpg" width="360"> \ No newline at end of file -- Gitblit v1.10.0