def test_model():
dataloader = load_dataset(train=False)
model = cnn.Net()
model.load_state_dict(torch.load("./modelo/mnist.pt"))
model.to(cnn.get_device())
model.eval()
dictionary = cnn.test_model(model=model, dataloader=dataloader)
classes = list(dataloader.dataset.class_to_idx.keys())
dictionary['classes'] = classes
dictionary = {**load_stats(), **dictionary}
save_stats(dictionary)
show_stats(dictionary)
model.compile(optimizer='rmsprop',
loss='sparse_categorical_crossentropy',
metrics=["accuracy"])
# callbacks for Save weights, Tensorboard
# creating a new directory for each run using timestamp
# folder = os.path.join(os.getcwd(), datetime.now().strftime("%d-%m-%Y_%H-%M-%S"))
# history_file = folder + "/inception" + ".h5"
# save_callback = ModelCheckpoint(filepath=history_file, verbose=1)
# tb_callback = TensorBoard(log_dir=folder)
# train model with data generator
train_accuracy, train_loss, valid_accuracy, valid_loss = cnn.train_model_datagen(
model, datagen, val_datagen, x_train, y_train, BATCH_SIZE, NUM_EPOCHS,
x_valid, y_valid)
# test model
test_accuracy, test_loss, predictions = cnn.test_model(model, x_test, y_test)
# Visualization and Output
num_epochs_plot = range(1, len(train_accuracy) + 1) # x axis range
# Loss curves
plt.figure()
plt.plot(num_epochs_plot, train_loss, "b", label="Training Loss")
plt.plot(num_epochs_plot, valid_loss, "r", label="Validation Loss")
plt.title("Loss Curves")
plt.xlabel("Number of Epochs")
plt.ylabel("Loss")
plt.legend()
plt.savefig('Figures/loss_inception.png')
plt.close()
#plt.show()
num_classes = 10
################################################################################
# callbacks for Save weights, Tensorboard
# creating a new directory for each run using timestamp
folder = os.path.join(os.getcwd(), datetime.now().strftime("%d-%m-%Y_%H-%M-%S"), str(ACTIV_FN))
history_file = folder + "\cnn_" + str(ACTIV_FN) + ".h5"
save_callback = ModelCheckpoint(filepath=history_file, verbose=1)
tb_callback = TensorBoard(log_dir=folder)
# Build, train, and test model
model = cnn.build_model(input_shape, activation_fn, LEARNING_RATE, DROP_PROB, NUM_NEURONS_IN_DENSE_1, num_classes)
train_accuracy, train_loss, valid_accuracy, valid_loss = cnn.train_model(model, train_images, train_labels, BATCH_SIZE,
NUM_EPOCHS, valid_images, valid_labels,
save_callback, tb_callback)
test_accuracy, test_loss, predictions = cnn.test_model(model, test_images, test_labels)
# save test set results to csv
predictions = np.round(predictions)
predictions = predictions.astype(int)
df = pd.DataFrame(predictions)
df.to_csv("mnist.csv", header=None, index=None)
################################################################################
# Visualization and Output
num_epochs_plot = range(1, len(train_accuracy) + 1)
# Loss curves
plt.figure(1)
plt.plot(num_epochs_plot, train_loss, "b", label="Training Loss")
plt.plot(num_epochs_plot, valid_loss, "r", label="Validation Loss")