{"message":"Unable to locate open access version of 5 kernel using gated linear units Dauphin et al 2016 The main module of the critic is a convolution with a 5 5 kernel and stride 2 using the concatenated ReLU activation function Shang et al 2016 Notably the generator and critic do not use an activation normalization technique such as batch or layer normalization We train the model using Adam with a learning rate of 3 104 \u03b21 05 \u03b22 0999 We update the generator 3 times for every critic update OTGAN includes two additional hyperparameters for the Sinkhorn algorithm the number of iterations to run the algorithm and"}