How to plot epoch vs. val_acc and epoch vs. val_loss graph in CNN?

0
votes

I used a convolutional neural network (CNN) for training a dataset. Here I get epoch, val_loss, val_acc, total loss, training time, etc. as a history. If I want to calculate the average of accuracy, then how to access val_acc, and how to plot epoch vs. val_acc and epoch vs. val_loss graph?

convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 3], name='input')
convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = conv_2d(convnet, 128, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)

convnet = fully_connected(convnet, 4, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')

model = tflearn.DNN(convnet, tensorboard_dir='log')

if os.path.exists('{}.meta'.format(MODEL_NAME)):
   model.load(MODEL_NAME)
   print('model loaded!')

train = train_data[:-150]
test = train_data[-50:]

X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,3)
Y = [i[1] for i in train]

test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,3)
test_y = [i[1] for i in test]

hist=model.fit({'input': X}, {'targets': Y}, n_epoch=8, validation_set=({'input': test_x}, {'targets': test_y}),
snapshot_step=40, show_metric=True, run_id=MODEL_NAME)
model.save(MODEL_NAME)
2
pythonpython-3.xtensorflowimage-processingconv-neural-network

2 Answers

1
votes

try the following: 

history = model.fit(X_train, Y_train, validation_data=(X_test, Y_test), batch_size=32, epochs=10, verbose=1)

# Get training and test loss histories
training_loss = history.history['loss']
test_loss = history.history['val_loss']

# Create count of the number of epochs
epoch_count = range(1, len(training_loss) + 1)

# Visualize loss history
plt.plot(epoch_count, training_loss, 'r--')
plt.plot(epoch_count, test_loss, 'b-')
plt.legend(['Training Loss', 'Test Loss'])
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.show();

credit to https://chrisalbon.com/deep_learning/keras/visualize_loss_history/

0
votes

You can use callbacks in Tensorflow. In particular, you can use Keras callbacks like CSVLogger which will stream your epoch results to a CSV. From there you can do all sorts of analysis.

Example based on your code:

csv_logger = CSVLogger('training.log')
model.fit({'input': X}, {'targets': Y}, ..., callbacks=[csv_logger]