I have a folder called train and in that I have three separate folders for "Covid", "Pneumonia", "Healthy". I have created VGG19 model using transfer learning. I want help with creating confusion matrix for my test data. I have split my train data as 75%,25%. I have tried everything to create confusion matrix and calculate F-1 score. It would be really great if someone provides me the code, since I am new to this.
#import needed packages
import numpy as np
import tensorflow as tf
import keras
from keras import backend as K
from keras.optimizers import Adam
from keras.metrics import categorical_crossentropy
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Model
from keras.layers import Dense,GlobalAveragePooling2D,Dropout,SeparableConv2D,BatchNormalization, Activation, Dense
from keras.applications.vgg19 import VGG19
from keras.applications.resnet import ResNet101
from keras.optimizers import Adam
from keras.layers import Input, Lambda, Dense, Flatten
import matplotlib.pyplot as plt
# dataset has 3 classes
num_class = 3
# Base model without Fully connected Layers
base_model = VGG19(include_top=False, weights='imagenet', input_shape=(224,224,3))
# don't train existing weights
for layer in base_model.layers:
layer.trainable = False
x=base_model.output
x = Flatten()(base_model.output)
##3 classes ,COVID, PNEUNOMIA, NORMAL
preds=Dense(num_class, activation='softmax')(x) #final layer with softmax activation
model=Model(inputs=base_model.input,outputs=preds)
##check the model
model.summary()
# tell the model what cost and optimization method to use
model.compile(
loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy']
)
##Preparing Data
train_datagen=ImageDataGenerator(preprocessing_function=keras.applications.vgg16.preprocess_input,
validation_split=0.25)
train_generator=train_datagen.flow_from_directory('C:/Users/prani/OneDrive/Desktop/Masters project/chest_xray/Train-250/',
target_size=(224,224),
batch_size=64,
class_mode='categorical',
subset='training')
validation_generator = train_datagen.flow_from_directory(
'C:/Users/prani/OneDrive/Desktop/Masters project/chest_xray/Train-250/', # same directory as training data
target_size=(224,224),
batch_size=64,
class_mode='categorical',
subset='validation') # set as validation data
##Training
##SEtting hyper parameter
epochs = 50
learning_rate = 0.0005
decay_rate = learning_rate / epochs
opt = Adam(lr=learning_rate, beta_1=0.9, beta_2=0.999, decay=decay_rate, amsgrad=False)
model.compile(optimizer=opt,loss='categorical_crossentropy',metrics=['accuracy'])
##Train
step_size_train = train_generator.n/train_generator.batch_size
step_size_val = validation_generator.samples // validation_generator.batch_size
r = model.fit_generator(generator=train_generator,
steps_per_epoch=step_size_train,
validation_data = validation_generator,
validation_steps =step_size_val,
epochs=50)
##Confusion Matrix (Sample code for confusion matrix but this is not working, it doesn't produce error neither results)
from sklearn.metrics import classification_report, confusion_matrix
batch_size=64
Y_pred = model.predict_generator(validation_generator,186)
y_pred = np.argmax(Y_pred, axis=1)
print('Confusion Matrix')
print(confusion_matrix(validation_generator.classes, y_pred))
print('Classification Report')
target_names = ['COVID','NORMAL','PNEUMONIA']
print(classification_report(validation_generator.classes, y_pred, target_names=target_names))
You could look at this page for information on how to code a confusion matrix and other metrics: https://www.tensorflow.org/tutorials/structured_data/imbalanced_data