def main():
sess = tf.Session()
sda = SDAutoencoder(dims=[784, 500],
activations=["sigmoid"],
sess=sess,
noise=0.40,
loss="cross-entropy")
mnist_train_gen_f = lambda: get_mnist_batch_xs_generator(True, batch_size=100, batch_limit=12000)
sda.pretrain_network_gen(mnist_train_gen_f)
trained_parameters = sda.finetune_parameters_gen(
get_mnist_batch_generator(True, batch_size=100, batch_limit=18000), output_dim=10)
transformed_filepath = "../data/mnist_test_transformed.csv"
test_ys_filepath = "../data/mnist_test_ys.csv"
output_filepath = "../data/mnist_pred_ys.csv"
sda.write_encoded_input_with_ys(transformed_filepath, test_ys_filepath,
get_mnist_batch_generator(False, batch_size=100, batch_limit=100))
sess.close()
test_model(parameters_dict=trained_parameters,
input_dim=sda.output_dim,
output_dim=10,
x_test_filepath=transformed_filepath,
y_test_filepath=test_ys_filepath,
output_filepath=output_filepath)
def sca():
sess = tf.Session()
sca = SCDAutoencoder(dims=[784, 400, 200, 80],
activations=["relu", "relu", "relu"],
sess=sess,
noise=0.20,
loss="cross-entropy",
pretrain_lr=0.0001,
finetune_lr=0.0001)
mnist_train_gen_f = lambda: get_mnist_batch_xs_generator(
True, batch_size=100, batch_limit=12000)
# pretrain locally, layer by layer
sca.pretrain_network_gen(mnist_train_gen_f)
# fine-tune the model by training all the weights
trained_parameters = sca.finetune_parameters_gen(get_mnist_batch_generator(
True, batch_size=100, batch_limit=18000),
output_dim=10)
mainDir = data_storage_path
if not os.path.exists(mainDir):
os.makedirs(mainDir)
transformed_filepath = mainDir + "/mnist_test_transformed.csv"
test_ys_filepath = mainDir + "/mnist_test_ys.csv"
output_filepath = mainDir + "/mnist_pred_ys.csv"
# for testing. write the encoded x value along with y values to csv
sda.write_encoded_input_with_ys(
transformed_filepath, test_ys_filepath,
get_mnist_batch_generator(False, batch_size=100, batch_limit=100))
sess.close()
test_model(parameters_dict=trained_parameters,
input_dim=sda.output_dim,
output_dim=10,
x_test_filepath=transformed_filepath,
y_test_filepath=test_ys_filepath,
output_filepath=output_filepath)
from softmax import test_model, openData
OUTPUT_PATH = "../data/deephand/pred.csv"
TRANSFORMED_PATH = "../data/deephand/transformed.csv"
X_TRAIN_PATH = "../data/trainX.csv"
Y_TRAIN_PATH = "../data/trainY.csv"
X_TEST_PATH = "../data/testX.csv"
Y_TEST_PATH = "../data/testY.csv"
BIASES_PATH = "../data/biases.csv"
WEIGHT_PATH = "../data/weights.csv"
biases = openData(BIASES_PATH)
# print(type(biases[0][0]))
biases = [[float(y.strip('"')) for y in x] for x in biases]
weights = openData(WEIGHT_PATH)
print(type(weights[0][0]))
weights = [[float(y.strip('"')) for y in x] for x in weights]
trained_parameters = {'biases': biases, 'weights': weights}
test_model(parameters_dict=trained_parameters,
input_dim=len(weights),
output_dim=6,
x_test_filepath=TRANSFORMED_PATH,
y_test_filepath=Y_TEST_PATH,
output_filepath=OUTPUT_PATH)