Mastering Computer Vision with TensorFlow 2.x

Setting up model parameters

For our analysis, we set the model parameters as shown in the following block of code:

NUM_EPOCHS = 5batchsize = 10num_train_images = 900num_val_images = 100

The base model is then constructed similar to our example in the last section, except we do not include the top model by setting include_top=False:

base_model = ResNet50(weights='imagenet',include_top=False,input_shape=(img_height, img_width, 3))

In this code, we used the base model to generate the feature vector by using only convolutional layers.