From 7b71bee83005e8476d1cae36af8a0b40e11b1a4d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Dar=C3=ADo=20Here=C3=B1=C3=BA?= Date: Wed, 3 Apr 2019 10:34:27 -0300 Subject: [PATCH] Semantic issue on paragraph #58 * `additional ta to increase` > `additional data to increase` or `additional tasks to increase` (...) --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 5c1ca09..b0d2205 100644 --- a/README.md +++ b/README.md @@ -55,7 +55,7 @@ The following image shows how the training loss changes when we train the model. ### Conclusion -In this project, we investigated how to use a fully convolutional neural network for semantic segmentation. We tested our model against KITTI dataset. The results indicate that our model is quite capable of separating road pixels form the rest. However, we would like to work on following additional ta to increase the accuracy of our model. +In this project, we investigated how to use a fully convolutional neural network for semantic segmentation. We tested our model against KITTI dataset. The results indicate that our model is quite capable of separating road pixels form the rest. However, we would like to work on following additional data to increase the accuracy of our model. 1. Data Augmentation: During our testing, we have found that our mode failed to label road surface when inadequate lighting in the environment. We think data augmentation can be used to generate more training examples with different lighting conditions. So additional data generated using data augmentation will help us to overcome the above-mentioned issue.