if __name__ == "__main__":
database = "CR"
if not os.path.exists(database):
os.makedirs(database)
# Load data
(x_train, y_train), (x_dev, y_dev), (x_test, y_test), vocab_size, max_len = load_data(database)
model = CapsNet(input_shape=x_train.shape[1:],
n_class=len(np.unique(np.argmax(y_train, 1))),
num_routing=3,
vocab_size=vocab_size,
embed_dim=20,
max_len=max_len
)
model.summary()
plot_model(model, to_file=database+'/model.png', show_shapes=True)
# Hyperparameters
optimizers = ['adam', 'nadam']
epochs = [10, 20]
batch_sizes = [200, 500]
schedules = [lambda1, lambda2, step_decay, lambda3, step_decay_schedule]
o = 'adam'
e = 10
data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])
return data
# plt.imshow(data); plt.axis('off')
if __name__ == "__main__":
# setting the hyper parameters
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=256, type=int)
args = parser.parse_args()
print(args)
ctx = mx.gpu(0)
capnet = CapsNet(args.batch_size, ctx)
capnet.load_params('capnet.params', ctx)
recnet = ReconNet(args.batch_size, ctx)
recnet.load_params('recnet.params', ctx)
train_data, test_data = utils.load_data_mnist(batch_size=args.batch_size,resize=28)
sum_capout = mx.nd.zeros((16, 10), ctx)
sum_label = mx.nd.zeros((10), ctx)
for i, batch in enumerate(test_data):
data, label = utils._get_batch(batch, ctx)
one_hot_label = nd.one_hot(label, 10)
capout = capnet(data)
# maybe I should not use label to create mask
masked_capoutput = capout * nd.expand_dims(one_hot_label, axis=1)
sum_capout += nd.sum(masked_capoutput, axis=0)
sum_label += nd.sum(one_hot_label, axis=0)
def train():
#
fileName = "..\\data\\train_X.bin"
X_train = read_all_images(fileName)
testFile = "..\\data\\test_X.bin"
X_test = read_all_images(testFile)
test_y_File = "..\\data\\test_y.bin"
targets = read_labels(test_y_File)
# mnist = fetch_openml('mnist_784', version=1, cache=True)
# targets = mnist.target[60000:]
#
# X_train = mnist.data[:60000]
# X_test = mnist.data[60000:]
script_directory = os.path.split(os.path.abspath(__file__))[0]
colons = []
optimizers = []
colons_paths = []
filepath = 'encoders\\encoder_' + str(0) + '.model'
predictor_model = os.path.join(script_directory, filepath)
colons_paths.append(predictor_model)
c = CapsNet()
c = c.cuda()
colons.append(c)
optimizer = torch.optim.Adam(c.parameters(), lr=LEARNING_RATE_DEFAULT)
optimizers.append(optimizer)
max_loss = 10000000
for iteration in range(MAX_STEPS_DEFAULT):
ids = np.random.choice(len(X_train),
size=BATCH_SIZE_DEFAULT,
replace=False)
train = True
products, mim, new_preds = forward_block(X_train, ids, colons,
optimizers, train,
BATCH_SIZE_DEFAULT)
if iteration % EVAL_FREQ_DEFAULT == 0:
# print_dict = {"0": "", "1": "", "2": "", "3": "", "4": "", "5": "", "6": "", "7": "", "8": "", "9": ""}
print_dict = {
1: "",
2: "",
3: "",
4: "",
5: "",
6: "",
7: "",
8: "",
9: "",
0: ""
}
test_ids = np.random.choice(len(X_test),
size=BATCH_SIZE_DEFAULT,
replace=False)
products, mim, new_preds = forward_block(X_test, test_ids, colons,
optimizers, False,
BATCH_SIZE_DEFAULT)
# test_ids = np.random.choice(len(X_test), size=BATCH_SIZE_DEFAULT, replace=False)
# products, mim = forward_block(X_test, test_ids, colons, optimizers, False, BATCH_SIZE_DEFAULT)
# print_dict = gather_data(print_dict, products, targets, test_ids)
#
# test_ids = np.random.choice(len(X_test), size=BATCH_SIZE_DEFAULT, replace=False)
# products, mim = forward_block(X_test, test_ids, colons, optimizers, False, BATCH_SIZE_DEFAULT)
# print_dict = gather_data(print_dict, products, targets, test_ids)
# print("loss 1: ", mim.item())
# products, mim = forward_block(X_test, test_ids, colons, optimizers, False, BATCH_SIZE_DEFAULT)
print()
print("iteration: ", iteration)
print_dict = gather_data(print_dict, new_preds, targets, test_ids)
print_info(print_dict)
test_loss = mim.item()
if max_loss > test_loss:
max_loss = test_loss
print("models saved iter: " + str(iteration))
# for i in range(number_colons):
# torch.save(colons[i], colons_paths[i])
print("test loss " + str(test_loss))
print("")
parser.add_argument('--is_training', default=1, type=int)
parser.add_argument('--weights', default=None)
args = parser.parse_args()
print(args)
if not os.path.exists(args.save_dir):
os.makedirs(args.save_dir)
# load data
(x_train, y_train), (x_test, y_test) = load_imdb()
print(x_train.shape)
print(y_train.shape)
# define model
model = CapsNet(input_shape=x_train.shape[1:], n_class=2, num_routing=args.num_routing)
model.summary()
plot_model(model, to_file=args.save_dir + '/model.png', show_shapes=True)
# train or test
if args.weights is not None: # init the model weights with provided one
model.load_weights(args.weights)
if args.is_training:
train(model=model, data=(x_train, y_train), args=args)
else: # as long as weights are given, will run testing
if args.weights is None:
print('No weights are provided. Will test using random initialized weights.')
evaluation(model=model, data=(x_test, y_test))