I want all the output of the pretrained VGG16 model as well as the new classes it is trained on - keras

Question

I have tried transfer learning using VGG16 but only getting a result for those classes which are trained.I want that the output consists of both the VGG16 classes+ my new trained classes. Is it possible?
I have attached my whole code.
import matplotlib.pyplot as plt
import os, PIL
import tensorflow as tf
import numpy as np
import keras
from keras.models import Sequential, Model
from keras.layers.core import Dense, Dropout, Flatten, Reshape, Activation
from keras.layers import Embedding, Input, merge, ELU
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.optimizers import SGD, Adam, RMSprop
from keras.regularizers import l2
from keras.utils.np_utils import to_categorical
import sklearn.metrics as metrics
from PIL import Image, ImageDraw
from keras.applications import VGG16
from keras.applications.vgg16 import preprocess_input, decode_predictions
from keras.preprocessing.image import ImageDataGenerator
def load_images(image_paths):
# Load the images from disk.
images = [plt.imread(path) for path in image_paths]
# Convert to a numpy array and return it.
return np.asarray(images)
def path_join(dirname, filenames):
return [os.path.join(dirname, filename) for filename in filenames]
train_dir = "/home/priyank/Jupyter_notebook/plant_leaves_train_set"
test_dir = "/home/priyank/Jupyter_notebook/val_data_plant"
# # Pre-Trained Model: VGG16
# Downloading the pretrained model of imagenet dataset.
model = VGG16(include_top=True, weights='imagenet')
# # Input Pipeline
# First we need to know the shape of the tensors expected as input by the pre-trained VGG16 model. In this case it is images of shape 224 x 224 x 3.
input_shape = model.layers[0].output_shape[1:3] # the input shape of the vgg16 model
input_shape
# # ImageDataGenerator
# It will pick the image one-by-one and transform all the data each time the image is loaded in the training set.
datagen_train = ImageDataGenerator(
rescale=1./255,
rotation_range=180,
width_shift_range=0.1,
height_shift_range=0.1,
shear_range=0.1,
zoom_range=[0.9, 1.5],
horizontal_flip=True,
vertical_flip=True,
fill_mode='nearest')
datagen_test = ImageDataGenerator(rescale=1./255)
#
# The datagenerator will return the batches of the images. VGG16 model is too large so we can't create the batches too large otherwise we will run out of the RAM and GPU.
# Taking small batch size
batch_size = 20
#
# We can save the randomly transformed images during training, so as to inspect whether they have been overly distorted, so we have to adjust the parameters for the data-generator above.
if True:
save_to_dir = None
else:
save_to_dir='augmented_images/'
generator_train = datagen_train.flow_from_directory(directory=train_dir,
target_size=input_shape,
batch_size=batch_size,
shuffle=True,
save_to_dir=save_to_dir)
generator_test = datagen_test.flow_from_directory(directory=test_dir,
target_size=input_shape,
batch_size=batch_size,
shuffle=False)
steps_test = generator_test.n / batch_size
steps_test
image_paths_train = path_join(train_dir, generator_train.filenames)
image_paths_test = path_join(test_dir, generator_test.filenames)
cls_train = generator_train.classes
cls_test = generator_test.classes
class_names = list(generator_train.class_indices.keys())
class_names
num_classes = generator_train.num_classes
num_classes
# The dataset we have is imbalanced so the gradients for 9.01192 will remain higher adn the gradients of 0.8080 will reamin lower so that model can learn from higher gradient more than the lower gradient.
#
from sklearn.utils.class_weight import compute_class_weight
class_weight = compute_class_weight(class_weight='balanced',
classes=np.unique(cls_train),
y=cls_train)
class_weight
#
# Predicting the our data image with the already trained VGG16 model. Using a helper function which can resize the image so it can be the input to VGG16 model
def predict(image_path):
# Load and resize the image using PIL.
img = PIL.Image.open(image_path)
img_resized = img.resize(input_shape, PIL.Image.LANCZOS)
# Plot the image.
plt.imshow(img_resized)
plt.show()
# Convert the PIL image to a numpy-array with the proper shape.
img_array = np.expand_dims(np.array(img_resized), axis=0)
# Use the VGG16 model to make a prediction.
# This outputs an array with 1000 numbers corresponding to
# the classes of the ImageNet-dataset.
print(img_array.shape)
pred = model.predict(img_array)
# Decode the output of the VGG16 model.
print(pred)
print(pred.shape)
pred_decoded = decode_predictions(pred)[0]
# Print the predictions.
for code, name, score in pred_decoded:
print("{0:>6.2%} : {1}".format(score, name))
predict(image_path='/home/priyank/Pictures/people.jpg')
predict(image_path=image_paths_train[0])
# The pre-trained VGG16 model was unable to classify images from the plant disease dataset. The reason is perhaps that the VGG16 model was trained on the so-called ImageNet dataset which may not have contained many images of plant diseases.
#
# The lower layers of a Convolutional Neural Network can recognize many different shapes or features in an image. It is the last few fully-connected layers that combine these featuers into classification of a whole image. So we can try and re-route the output of the last convolutional layer of the VGG16 model to a new fully-connected neural network that we create for doing classification
# summary of VGG16 model.
model.summary()
# We can see that the last convolutional layer is called 'block5_pool' so we use Keras to get a reference to that layer.
transfer_layer = model.get_layer('block5_pool')
#
#
# We refer to this layer as the Transfer Layer because its output will be re-routed to our new fully-connected neural network which will do the classification for the Knifey-Spoony dataset.
#
# The output of the transfer layer has the following shape:
#
transfer_layer.output
# we take the part of the VGG16 model from its input-layer to the output of the transfer-layer. We may call this the convolutional model, because it consists of all the convolutional layers from the VGG16 model.
conv_model = Model(inputs=model.input,
outputs=transfer_layer.output)
# Start a new Keras Sequential model.
new_model = Sequential()
# Add the convolutional part of the VGG16 model from above.
new_model.add(conv_model)
# Flatten the output of the VGG16 model because it is from a
# convolutional layer.
new_model.add(Flatten())
# Add a dense (aka. fully-connected) layer.
# This is for combining features that the VGG16 model has
# recognized in the image.
new_model.add(Dense(1024, activation='relu'))
# Add a dropout-layer which may prevent overfitting and
# improve generalization ability to unseen data e.g. the test-set.
new_model.add(Dropout(0.5))
# Add the final layer for the actual classification.
new_model.add(Dense(num_classes, activation='softmax'))
optimizer = Adam(lr=1e-5)
loss = 'categorical_crossentropy'
metrics = ['categorical_accuracy']
# Helper-function for printing whether a layer in the VGG16 model should be trained.
def print_layer_trainable():
for layer in conv_model.layers:
print("{0}:\t{1}".format(layer.trainable, layer.name))
print_layer_trainable()
#
#
# In Transfer Learning we are initially only interested in reusing the pre-trained VGG16 model as it is, so we will disable training for all its layers.
#
conv_model.trainable = False
for layer in conv_model.layers:
layer.trainable = False
print_layer_trainable()
new_model.compile(optimizer=optimizer, loss=loss, metrics=metrics)
epochs = 15
steps_per_epoch = 100
# Steps per epochs are multiplied with the epoch here 100*20 = 2000 means 2000 random images will be selected.
history = new_model.fit_generator(generator=generator_train,
epochs=epochs,
steps_per_epoch=steps_per_epoch,
class_weight=class_weight,
validation_data=generator_test,
validation_steps=steps_test)
new_model.save("trained_new.h5")
predict(image_path = "/home/priyank/Jupyter_notebook/pp.jpg")
**IT is only predicting the 38 classes it is trained on I want, if the new image is not belongs to these 38 classes then the model should return the VGG16 class or no match found. please help **
Thanks in advance.

Answer 1

use functional api instead of Sequential,
offical guide is here: https://keras.io/getting-started/functional-api-guide/
You can find a multi input & multi output model example there. What you want is very similar but uses only one input instead of multiple.