High Train and Validation Accuracy, Bad Test Accuracy - machine-learning

Question

I am trying to classify 2 classes of images. Though I am getting high train and validation accuracy (0.97) after 10 epochs, my test results are awful (precision 0.48) and the confusion matrix shows the network is predicting the images for the wrong class (attached results).
There are only 2 classes in the dataset, each class has 10,000 image examples (after augmentation). I am using the VGG16 network. The full dataset is split 20% to test set (this split was performed by taking random images from each class therefore it is shuffled). The remaining images are split to 80% train and 20% valid sets (as indicated in the ImageDataGenerator line of the code). So in the end there are:
12,904 Train images belonging to 2 classes
3,224 Valid images belonging to 2 classes
4,032 Test images belonging to 2 classes
This is my code:
def CNN(CNN='VGG16', choice='predict', prediction='./dataset/Test/image.jpg'):
''' Train images using one of several CNNs '''
Train = './dataset/Train'
Tests = './dataset/Test'
shape = (224, 224)
epochs = 10
batches = 16
classes = []
for c in os.listdir(Train): classes.append(c)
IDG = keras.preprocessing.image.ImageDataGenerator(validation_split=0.2)
train = IDG.flow_from_directory(Train, target_size=shape, color_mode='rgb',
classes=classes, batch_size=batches, shuffle=True, subset='training')
valid = IDG.flow_from_directory(Train, target_size=shape, color_mode='rgb',
classes=classes, batch_size=batches, shuffle=True, subset='validation')
tests = IDG.flow_from_directory(Tests, target_size=shape, color_mode='rgb',
classes=classes, batch_size=batches, shuffle=True)
input_shape = train.image_shape
if CNN == 'VGG16' or 'vgg16':
model = VGG16(weights=None, input_shape=input_shape,
classes=len(classes))
elif CNN == 'VGG19' or 'vgg19':
model = VGG19(weights=None, input_shape=input_shape,
classes=len(classes))
elif CNN == 'ResNet50' or 'resnet50':
model = ResNet50(weights=None, input_shape=input_shape,
classes=len(classes))
elif CNN == 'DenseNet201' or 'densenet201':
model = DenseNet201(weights=None, input_shape=input_shape,
classes=len(classes))
model.compile(optimizer=keras.optimizers.SGD(
lr=1e-3,
decay=1e-6,
momentum=0.9,
nesterov=True),
loss='categorical_crossentropy',
metrics=['accuracy'])
Esteps = int(train.samples/train.next()[0].shape[0])
Vsteps = int(valid.samples/valid.next()[0].shape[0])
if choice == 'train':
history= model.fit_generator(train,
steps_per_epoch=Esteps,
epochs=epochs,
validation_data=valid,
validation_steps=Vsteps,
verbose=1)
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model Loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Validation'], loc='upper left')
plt.show()
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('Model Accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Validation'], loc='upper left')
plt.show()
Y_pred = model.predict_generator(tests, verbose=1)
y_pred = np.argmax(Y_pred, axis=1)
matrix = confusion_matrix(tests.classes, y_pred)
df_cm = pd.DataFrame(matrix, index=classes, columns=classes)
plt.figure(figsize=(10,7))
sn.heatmap(df_cm, annot=True)
print(classification_report(tests.classes,y_pred,target_names=classes))
model.save_weights('weights.h5')
elif choice == 'predict':
model.load_weights('./weights.h5')
img = image.load_img(prediction, target_size=shape)
im = image.img_to_array(img)
im = np.expand_dims(im, axis=0)
if CNN == 'VGG16' or 'vgg16':
im = keras.applications.vgg16.preprocess_input(im)
prediction = model.predict(im)
print(prediction)
elif CNN == 'VGG19' or 'vgg19':
im = keras.applications.vgg19.preprocess_input(im)
prediction = model.predict(im)
print(prediction)
elif CNN == 'ResNet50' or 'resnet50':
im = keras.applications.resnet50.preprocess_input(im)
prediction = model.predict(im)
print(prediction)
print(keras.applications.resnet50.decode_predictions(prediction))
elif CNN == 'DenseNet201' or 'densenet201':
im = keras.applications.densenet201.preprocess_input(im)
prediction = model.predict(im)
print(prediction)
print(keras.applications.densenet201.decode_predictions(prediction))
CNN(CNN='VGG16', choice='train')
Results:
precision recall f1-score support
Predator 0.49 0.49 0.49 2016
Omnivore 0.49 0.49 0.49 2016
accuracy -- -- 0.49 4032
I suspect that the ImageDataGenerator() is not shuffling the images "before" the train/valid split. If this is the case how can i force the ImageDataGenerator here in Keras to shuffle the dataset before the split?
If shuffling is not the case, how can i solve my issue? what am I doing wrong?

Answer 1

So your model is basically overfitting, which means that it is "memorizing" your training set. I have a few suggestions:
check that your 2 prediction classes are balanced in your training set. I.e. 50-50 split of 0 and 1. For example, if 90% of your training data is labeled 0, then your model will simply predict everything to be 0 and get right in the validation 90% of the time.
if your training data is already balanced, it means that your model isn't generalizing. Perhaps you could try using the pre-trained model instead of custom training every layer of VGG? You can load the pre-trained weights of VGG but do not include top and train only the dense layers.
Use cross validation. Reshuffle the data in each validation and see whether results in the test set improve.

Answer 2

Somehow, the image generator of Keras works well when combined with fit() or fit_generator() function, but fails miserably when combined
with predict_generator() or the predict() function.
When using Plaid-ML Keras back-end for AMD processor, I would rather loop through all test images one-by-one and get the prediction for each image in each iteration.
import os
from PIL import Image
import keras
import numpy
# code for creating dan training model is not included
print("Prediction result:")
dir = "/path/to/test/images"
files = os.listdir(dir)
correct = 0
total = 0
#dictionary to label all animal category class.
classes = {
0:'This is Cat',
1:'This is Dog',
}
for file_name in files:
total += 1
image = Image.open(dir + "/" + file_name).convert('RGB')
image = image.resize((100,100))
image = numpy.expand_dims(image, axis=0)
image = numpy.array(image)
image = image/255
pred = model.predict_classes([image])[0]
animals_category = classes[pred]
if ("cat" in file_name) and ("cat" in sign):
print(correct,". ", file_name, animals_category)
correct+=1
elif ("dog" in file_name) and ("dog" in animals_category):
print(correct,". ", file_name, animals_category)
correct+=1
print("accuracy: ", (correct/total))