metrics=["accuracy"])
model.build()
model.summary()
history = model.fit_generator(
train_generator,
epochs=1,
validation_data=validation_generator,
class_weight={
0: 0.5, # false
1: 0.5 # true
},
callbacks=[EarlyStopping(monitor="val_loss", patience=5)])
def plot_history(history):
loss = history.history["loss"]
val_loss = history.history["val_loss"]
epochs = range(1, len(loss) + 1)
plt.figure()
plt.plot(epochs, loss, "bo", label="Training loss")
plt.plot(epochs, val_loss, "b", label="Validation loss")
plt.title("Training and validation loss")
plt.legend()
# plt.show()
plot_history(history)
predictions_pos = model.predict_generator(test_generator_positive)
predictions_neg = model.predict_generator(test_generator_negative)
pdb.set_trace()
shuffle=False
)
val_steps = test_generator.n//test_generator.batch_size
loss, acc = model.evaluate_generator( test_generator, verbose=1, steps = val_steps)
print('Test loss: %f' %loss)
print('Test accuracy: %f' %acc)
"""Precision, recall, F-score"""
import sklearn.metrics
from sklearn.metrics import classification_report, confusion_matrix
print('Loaded %d test samples from %d classes.' %(test_generator.n, test_generator.num_classes))
preds = model.predict_generator(test_generator, verbose=1, steps=val_steps)
Ypred = np.argmax(preds, axis=1)
Ytest = test_generator.classes # shuffle=False in test_generator
print(classification_report(Ytest, Ypred, labels=None, target_names=classnames, digits=3))
"""Graphs"""
import matplotlib.pyplot as plt
# summarize history for accuracy
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('model accuracy')
plt.ylabel('accuracy')
# print model
model.summary()
# Same compile as in original model
model.compile(optimizer=Adam(learning_rate=.0001), loss='categorical_crossentropy', metrics=['accuracy'])
# Learning on 40 images -> 4 steps and 10 images per step
model.fit_generator(generator=train_batches, steps_per_epoch=4,
validation_data=valid_batches, validation_steps=4, epochs=5, verbose=2)
test_imgs, test_labels = next(test_batches)
test_labels = test_labels[:,0]
# Taking one batch so will be 10 images
predictions = model.predict_generator(generator=test_batches, steps=1, verbose=0)
print(np.round(predictions[:,0]))
cm = confusion_matrix(y_true=test_labels, y_pred=np.round(predictions[:,0]))
print('Configuration matrix')
print(cm)
"""
Epoch 5/5
4/4 - 39s - loss: 0.4781 - accuracy: 0.8250 - val_loss: 0.5529 - val_accuracy: 0.7750
Configuration matrix
[[5 1]
[0 4]]
