1. Model

MODEL 1 : 3 Layers with 1 Convolution layer

---

        model_1 = keras.models.Sequential([
                    keras.layers.Conv2D(32, (3,3), activation = 'relu', input_shape = (28, 28,1)),  # layer 1 
                    keras.layers.MaxPool2D((2,2)),                                                  # layer 2 
                    keras.layers.Flatten(),
                    keras.layers.Dense(10, activation = 'softmax')])                                # layer 3

2. Training with Training loss

Training Step

Training for 5 epochs.

model_1.fit(train_images, train_labels, epochs = 5)

3. Test Accuracy

Perform Test with Test data

4. Images and corresponding probability that predicted Right

5. Images and corresponding probability that predicted Wrong

1. Model

MODEL 2 : 5 Layers with 2 Convolution layer

---

         model_2 = keras.models.Sequential([
                    keras.layers.Conv2D(32, (3,3), activation = 'relu', input_shape=(28,28,1)),     # layer 1 
                    keras.layers.MaxPool2D((2,2)),                                                  # layer 2
                    keras.layers.Conv2D(64, (3,3), activation = 'relu'),                            # layer 3 
                    keras.layers.MaxPool2D((2,2)),                                                  # layer 4
                    keras.layers.Flatten(),
                    keras.layers.Dense(10, activation = 'softmax')])                                # layer 5

2. Training with Training loss

Training Step

Training for 5 epochs.

model_2.fit(train_images, train_labels, epochs = 5)

3. Test Accuracy

Perform Test with Test data

4. Images and corresponding probability that predicted Right

5. Images and corresponding probability that predicted Wrong

1. Model

MODEL 3 : 7 Layers with 4 Convolution layer

---

     model_3 = keras.models.Sequential([
                    keras.layers.Conv2D(32, (3,3), activation = 'relu', input_shape = (28, 28,1)),  # layer 1
                    keras.layers.MaxPool2D((2,2)),                                                  # layer 2
                    keras.layers.Conv2D(64, (3,3), activation = 'relu'),                            # layer 3
                    keras.layers.Conv2D(64, (3,3), activation = 'relu'),                            # layer 4
                    keras.layers.MaxPool2D((2,2)),                                                  # layer 5
                    keras.layers.Conv2D(128, (3,3), activation = 'relu'),                           # layer 6
                    keras.layers.Flatten(),
                    keras.layers.Dense(10, activation = 'softmax')])   

2. Training with Training loss

Training Step

Training for 5 epochs.

model_3.fit(train_images, train_labels, epochs = 5)

3. Test Accuracy

Perform Test with Test data

4. Images and corresponding probability that predicted Right

5. Images and corresponding probability that predicted Wrong