In this competition you will analyze images of galaxies to determine the probability that it belongs to particular class.
Your model must have at least the following:

•  At least two Convolutional Layers followed by normalization and pooling layers.

•  Activation function ReLU.

•  Optimizer:  Gradient Descent.

•  At least one fully connected layer followed by softmax transformation.

There are several techniques to improve the performance and generalization of the Convolutional Neural Network.  The objective is to try different methods to tweak the performance of your model and observe how the performance changes. You may use CNN's/ResNet/ODENet, etc.