Flower classification Fully-Connected Image Classifier [AppertincehipProject ]
I will train a fully-connected neural network to image classification of dandelions and grasses. I will be using the TensorFlow Deep Learning Framework to create a neural network and training/validation dataset.
- The Neural Network model using CNN has a higher accuracy rate of 0.6688, while the previous neural network model has a lower accuracy level of 0.611.
- The Neural Network model using CNN has a lower failure rate of 0.5915, while the previous Neural Network model has a higher failure rate of 0.824