ConvNet_MNIST

A TensorFlow model of Convolutional neural network for digit recognition using MNIST data set.
Accuracy = 97.36% on test set with 1000 epoch on mini batch of 50 using AdamOptimizer.

Structure of Network

1. Input data
   
2. Convolution and max pooling.
   
3. Convolution and max pooling.
   
4. Fully connected layer.
   
5. Processing - DropOut.
   
6. Readout layer - Fully Connected.
   
7. Output - Classified digits.