[Python] Question about implementing Transfer Learning Correctly in Python Keras

I have an assignment where I have to use transfer learning on iris images (the dataset is very small). The task is to build a regularized NN to classify the images into their respective classes.

My entire code is below:

import keras
from keras.preprocessing.image import ImageDataGenerator

#importing images trhrough ImageDataGenerator

train_gen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2, zoom_range = 0.2, horizontal_flip = True)
test_gen = ImageDataGenerator(rescale = 1./255)

#Generating training and test sets

training_set = train_gen.flow_from_directory(r"Iris_Imgs",
target_size = (224, 224), shuffle=True, batch_size = 15, class_mode = 'categorical')
train_imgs, train_labels = next(training_set)
test_set = test_gen.flow_from_directory(r"Iris_Imgs",
target_size = (224, 224), shuffle=True, class_mode = 'categorical')
test_imgs, test_labels = next(test_set)

from keras.applications import VGG16
from keras.models import Model

#Importing VGG16 and getting weights

vgg_conv = VGG16(weights='imagenet', input_shape=(224, 224, 3))

vgg_conv = VGG16(weights='imagenet', include_top=False,
input_shape=(224, 224, 3))
part_model = Model(inputs = vgg_conv.input,
outputs = vgg_conv.get_layer('block4_pool').output)

#These are the features I would like to connect to my NN

block4_pool_features = part_model.predict(training_set)
vgg_conv.layers.pop()


This is the part I'm most confused about - when i built my NN (below) I want to make sure I'm connecting the layers from the vgg_conv.output layer to the NN I've built.

from tensorflow import keras
from tensorflow.keras import layers
from keras.layers.convolutional import Conv2D
from keras.models import Sequential
from keras.layers.convolutional import MaxPooling2D
from keras.layers.normalization import BatchNormalization
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers import Dropout


imageSize=224
classifier=Sequential()

classifier.add(Conv2D(3, (3, 3), input_shape = (imageSize, imageSize, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (1, 1)))

classifier.add(BatchNormalization())


classifier.add(Conv2D(3, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (1, 1)))

classifier.add(BatchNormalization())

classifier.add(Flatten())

classifier.add(Dense(128, activation='relu'))

classifier.add(Dropout(1e-3))

classifier.add(Dense(3, activation='softmax'))

opt = keras.optimizers.Adam(learning_rate=3e-2)

#Connecting last layer - Am I doing this correctly?

last = vgg_conv.output
x = Flatten()(last) ## functional API
x2 = Dense(1024, activation='relu')(x) # Fully Connect
my_preds = Dense(200, activation='softmax')(x2)


for layer in classifier.layers[:10000]:
layer.trainable = False

classifier.compile(loss='categorical_crossentropy', optimizer='adam', metrics = ['acc'])

classifier.fit(train_imgs, train_labels, batch_size = 10, epochs = 30)


I've also noticed that the model I've built is performing very poorly.

Continue reading...