(self, filters, kernel_size, strides)

(data, path="GIFs/", file="data.gif", duration=0.02, min_val=-1., max_val=1.)

(dt = 0.002)

(ground_truths, model_outputs, path="Figures/Differences", frequency=100)

(time_steps=1, h_shape=(16,16,64), c_shape=(16,16,64))

()

()

(ground_truths, model_outputs, path="Figures/Comparison", frequency=100)

(ground_truths, model_outputs, comparison_point=(32,32), path="Figures/", file="poin

(loss_recod_path="../Training/Checkpoints/training_loss.npy", plot_file="Training_Loss.png", fig

(Model, initial_conidtion, time_steps=1000, get_latent=False)

(Model, initial_data, LossFuncs, batch_size=100, dataset_time_steps=1000, epoch=2000, learning_rat

(self, y)

(self, y)

(self, padding=(1,1))

(self, channels, initial_alpha=[-np.pi*2, np.pi*2], **kwargs)

(self, factor)

(self, kernel_lap, kernel_x, kernel_y, kernel_t=np.array([-1,0,1]), dx=1./128, dy=1./128, dt=0.002, viscosity=

(self, kernel_lap, kernel_x, kernel_y, kernel_t=np.array([-1,0,1]), dx=1./16, dy=1./16, dt=0.002, viscosity=1.

(self, x)

(self, x, h, c)

(self, x)

(self, x_old, x_new)