Keras VGG16 with different input shape

Featured image is from analyticsvidhya.com Update (June 19, 2019): Recently, I revisit this case and found out the latest version of Keras==2.2.4 and tensorflow-gpu==1.13.1 make customizing VGG16 easier. For example, we can use pre-trained VGG16 to fit CIFAR-10 (32×32) dataset just like this: X, y = load_cfar10_batch(dir_path, 1) base_model = VGG16(include_top=False, weights=vgg16_weights, input_shape=(32, 32, 3))…

Keras VGG16 flat-features extractor

Using pre-trained deep learning model as feature extractor is a proven way to improve classification accuracy. One of the famous model is Oxford’s VGG16, which is trained using million images to recognize 1,000 classes ranging from animals, vehicles and other stuffs. Now, to use VGG16 as part of another neural network is relatively easy, especially…