I am using CNN to classify apple type. I achieved high accuracy on train data but really low accuracy on test data. Data is split into 80:20. I am not sure if my data is overfitting or not.
I have 2 folders that contain TraningData and TestData, and each folder has 4 subfolders braeburn, red_apple, red_delicious, rotten (containing corresponding pictures).
TRAIN_DIR = 'apple_fruit'
TEST_DIR = 'apple_fruit'
classes = ['braeburn','red_apples','red_delicious','rotten'] train_datagen = ImageDataGenerator(rescale = 1./255, shear_range=0.2, zoom_range=0.2, horizontal_flip=True, fill_mode='nearest')
test_datagen = ImageDataGenerator(rescale = 1./255)
training_set = train_datagen.flow_from_directory(TRAIN_DIR,
shuffle=True,
target_size = (100,100),
batch_size = 25,
classes =['braeburn','red_apples','red_delicious','rotten'])
test_set= test_datagen.flow_from_directory(TEST_DIR,
target_size = (100, 100),
shuffle=True,
batch_size = 25,classes = classes)
model =Sequential()
model.add(Conv2D(filters=128, kernel_size=(3,3),input_shape=(100,100,3), activation='relu', padding
= 'same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(filters=16, kernel_size=(3,3), activation='relu', padding = 'same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(256))
model.add(Activation('relu'))
model.add(Dropout(0.6))
model.add(Dense(4,activation='softmax'))
model.compile(optimizer ='adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])
history = model.fit(x=training_set,#y=training_set.labels,
steps_per_epoch=len(training_set),
epochs =10)
model.save('Ripe2_model6.h5') # creates a HDF5 file 'my_model.h5'
model_path = "Ripe2_model6.h5"
loaded_model = keras.models.load_model(model_path)
classes = ['braeburn','red_apples','red_delicious','rotten']
predictions = model.predict(x=test_set, steps=len(test_set), verbose=True)
pred = np.round(predictions)
y_true=test_set.classes
y_pred=np.argmax(pred, axis=-1)
> cm = confusion_matrix(y_true=test_set.classes, y_pred=np.argmax(pred, axis=-1))
test_set.classes
np.argmax(pred, axis=-1)
def plot_confusion_matrix(cm, classes,
normalize=False,
title='Confusion matrix',
cmap=plt.cm.Blues):
accuracy = np.trace(cm) / float(np.sum(cm))
misclass = 1 - accuracy
"""
This function prints and plots the confusion matrix.
Normalization can be applied by setting `normalize=True`.
"""
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title,color = 'white')
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45,color = 'white')
plt.yticks(tick_marks, classes,color = 'white')
target_names = ['braeburn','red_apples','red_delicious','rotten']
if target_names is not None:
tick_marks = np.arange(len(target_names))
plt.xticks(tick_marks, target_names, rotation=45)
plt.yticks(tick_marks, target_names)
if normalize:
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
thresh = cm.max() / 1.5 if normalize else cm.max() / 2
for i, j in itertools.product(range(cm.shape[0]),
range(cm.shape[1])):
if normalize:
plt.text(j, i, "{:0.4f}".format(cm[i, j]),
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black")
else:
plt.text(j, i, "{:,}".format(cm[i, j]),
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('True label',color = 'white')
plt.xlabel('Predicted label',color = 'white')
cm_plot_labels = ['braeburn','red_apples','red_delicious','rotten']
plot_confusion_matrix(cm=cm, classes=cm_plot_labels, title='Confusion Matrix')
print(accuracy_score(y_true, y_pred))
print(recall_score(y_true, y_pred, average=None))
print(precision_score(y_true, y_pred, average=None))
The confusion matrix:
I have tried changing many features but still no progress.
It indicates that the data in the test set is quite different from what the model learned. To understand if it is overfitting or a single unfortunate split: