Youtor
Fruit Classification using GoogleNet Convolutional Neural Network CNN
>> YOUR LINK HERE: ___ http://youtube.com/watch?v=58-1KmsIEcQ
Download Dataset From Here: https://www.nzfaruqui.com/fruit-class... • Copy Code: https://www.scholarshipin.com/fruit-c... • Convolutional neural network (CNN) is a type of deep neural network used for image classification. There are two ways we can use CNNs. One is to design a CNN from scratch and another is to use existing ones using transfer learning. This tutorial shows a simple approach of fruit classification using GoogleNet convolutional neural network through transfer learning. The video explanation, code used in the video and the dataset are available here. You can copy the code and download the dataset and use them wherever you want. • The approach followed in this article is perhaps the simplest possible way to train a convolutional neural network to classify images. It starts with splitting the dataset into training and validation dataset. The training and validation dataset ratio is 70:30. Then they are resized according to the input size of the GoogleNet. After that the feature learner layer and output classifier layer are modified. Finally, the modified feature learner layer is re-trained with the dataset. • Fruit classification using GoogleNet convolutional neural network is a simple and straightforward approach. As a matter of fact, this is the purpose of transfer learning. We prefer transfer learning whenever it is possible for faster implementation with lot less code and complexity. The example demonstrated in this article has been implemented using these 7 simple steps: • 1. Load the dataset, • 2. Split the dataset into training and validation dataset with 70:30 ratio, • 3. Resize the dataset according to the input layer size of the convolutional neural network, • 4. Inspect the network and identify the feature learner and classification layer, • 5. Modify the feature learner layer and classification layer, • 6. Define training options and • 7. Train the network • The dataset created and used in this experiment has been uploaded to a Google Drive folder so that anyone can use it. You can download it from the link below: https://www.scholarshipin.com/fruit-c... • The MATLAB code used in this experiment is divided into two files: • 1. Training and • 2. Test Network • Here the training script trains the network whereas the test network is a function called to test the performance of the network. You can copy the code of both of these files from here: • https://www.scholarshipin.com/fruit-c...
#############################
