From 1ebadd9c6cfba4d9a2d8e716d57a9859cb64d5fa Mon Sep 17 00:00:00 2001 From: KatHellg Date: Tue, 24 Sep 2024 14:21:44 +0200 Subject: [PATCH] fixed image sizes in readme --- examples/welding-defect-detection/README.md | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/examples/welding-defect-detection/README.md b/examples/welding-defect-detection/README.md index 5e1983ad..b22697c5 100644 --- a/examples/welding-defect-detection/README.md +++ b/examples/welding-defect-detection/README.md @@ -5,11 +5,11 @@ This is an example FEDn project that trains a YOLOv8n model on images of welds to classify them as "good", "bad", or "defected". The dataset is pre-labeled and can be accessed for free from Kaggle https://www.kaggle.com/datasets/sukmaadhiwijaya/welding-defect-object-detection. See a few examples below, -![example data point 1](figs/fig1.jpg) + -![example data point 2](figs/fig2.jpg) + -![example data point 3](figs/fig3.jpg) + This example is generalizable to many manufacturing and operations use cases, such as automatic optical inspection. The federated setup enables the organization to make use of available data in different factories and in different parts of the manufacturing process, without having to centralize the data. @@ -106,14 +106,14 @@ Approach: The number of epochs and rounds in each experiment are divided such th Centralized: -![example output 0](figs/CentralizedmAP50.png) + Federated: -![example output 1](figs/2clients_5epochs_50rounds.png) + -![example output 2](figs/2clients_10epochs_25rounds.png) + -![example output 3](figs/2clients_25epochs_10rounds.png) +