Coin Reconstruction Data

These data are used for training, testing, and evaluating the CycleGAN project related to coin reconstructions. Data are used to train the given CycleGAN model and coins are used to evaluate the model both internally, computationally, and by other users.<br>trainingData.zip: This file provides training data obtained used to train the CycleGAN. There is a training folder which contains two folders (badCoins and goodCoins). The goodCoins folder contains coins that are better preserved and used to train what a coin should look like. The badCoins folder contains damaged coins and attempts to train to reconstruct from these coins. The name of each file corresponds to coins that can be found using the identifier for coins referenced on http://numismatics.org.<br>testCoins.zip: These are image data used to test the developed CycleGAN model. The images folder contains the testing data used to generate model test data. The names of the coins correspond to the identifier on http://numismatics.org.<br>CoinsEvaluation.pdf: This file is used by testers to evaluate if they think given reconstructed coins shows improved quality or not from the real coin. The users are asked to evaluate coins on a 1-5 scale, with 1 indicating no difference and 5 indicating much improved reconstructions.<br>testCoinReconstruction.zip: This folder contains real and fake (i.e., reconstructed coins) coins used to determine if a given coin is real or reconstructed (i.e., fake). It was used for evaluators to determine if they can identify which coins were real or fake. In addition to the real and reconstructed coins, a pdf (Real_or_Fake.pdf) is used to ask judges to determine which given coins are real and which are generated reconstructions.<br>model1MixedLatest.zip: This is the final CycleGAN model used for reconstructions applied in the paper. Notes on parameters for training are included.Model1Mixed.zip: This is a zip file containing real and fake (generated) coins from the model output.Coins_Used_In_Figures.csv: This list helps to correspond the number (in the paper's figures) and identifier used in http://numismatics.org. Figure 2 and 3 are used to show these example in the paper.Coin_Reconstruction_CycleGan: This is the final Google Colab settings used.