In this Project, By using the Keras implementation of VGG-16 as a starting point.
-
Using the first 2 blocks of VGG-16 add extra Keras layers to create version a CNN network for the classification of the images according to the number of leaves in the plant images. We have 5 classes. The last layer from VGG-16 will be block2 pool and available to add no more than five fully connected or convolutional layers to the network including the final output layer.
-
Train this simple network on the training set while monitoring convergence on the validation set. As input to the model use images of size no larger than 128×128.
The NootBook contains:
- Plot of loss curve for training and validation data
- Plot an accuracy curve for training and validation data
- Plot of a confusion matrix of the network on the training including validation and testing data sets.