def main(opt):
dataset = data.Dataset(dataset=opt.dataset, pool_size=opt.pool_size, sample_size=opt.sample_size)
dataset.show_inf()
feature_size, att_size = dataset.feature_size, dataset.att_size
discriminator = model.Discriminator(feature_size, att_size, opt.t1).cuda()
generator = model.Generator(feature_size, att_size, opt.t2).cuda()
train2.train(discriminator, generator, dataset, d_lr=opt.d_lr, g_lr=opt.g_lr,\
batch_size=opt.batch_size, alpha=opt.alpha, epochs=opt.epochs)
def main(_):
# Print FLAGS values
pprint(FLAGS.flag_values_dict())
# Define GPU configuration
os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
os.environ['CUDA_VISIBLE_DEVICES'] = FLAGS.gpu
gpu_config = tf.ConfigProto()
gpu_config.gpu_options.allow_growth = True
# Define model name
if not FLAGS.phase:
setup_list = [
f"ngf_{FLAGS.ngf}", f"ndf_{FLAGS.ndf}", f"nz_{FLAGS.nz}",
f"lrD_{FLAGS.lrD}", f"lrG_{FLAGS.lrG}", f"var_{FLAGS.var}",
f"phase_{FLAGS.phase}", f"da_{FLAGS.da}", f"clip_{FLAGS.clip}"
]
else:
setup_list = [
f"ngf_{FLAGS.ngf}", f"ndf_{FLAGS.ndf}", f"nz_{FLAGS.nz}",
f"lrD_{FLAGS.lrD}", f"lrG_{FLAGS.lrG}", f"var_{FLAGS.var}",
f"phase_{FLAGS.phase}", f"da_{FLAGS.da}", f"clip_{FLAGS.clip}",
f"nhl_{FLAGS.nhl}", f"nhw_{FLAGS.nhw}"
]
model_name = '_'.join(setup_list)
print(f"Model name: {model_name}")
M = model(FLAGS, gpu_config)
M.sess.run(tf.global_variables_initializer())
if FLAGS.phase:
# Previously learned autoencoder model name
setup_list = [
f"ngf_{FLAGS.ngf}", f"ndf_{FLAGS.ndf}", f"nz_{FLAGS.nz}",
f"lrD_{FLAGS.lrD}", f"lrG_{FLAGS.lrG}", f"var_{FLAGS.var}",
f"phase_0", f"da_{FLAGS.da}", f"clip_{FLAGS.clip}"
]
lgan_name = '_'.join(setup_list)
# just for now
# lgan_name = 'ngf_64_ndf_64_nz_64_lrD_5e-05_lrG_0.001_dg_1_aug_0_lw_20.0_ow_0.01_var_3.0_phase_0_nosig'
# lgan_name = 'ngf_64_ndf_64_nz_16_lw_20.0_ow_0.01_var_3.0_phase_0'
var_lgan = tf.get_collection('trainable_variables', 'lgan/gen')
path = tf.train.latest_checkpoint(
os.path.join(FLAGS.ckptdir, lgan_name))
tf.train.Saver(var_lgan).restore(M.sess, path)
print(colored(f"LGAN model is restored from {path}", "blue"))
saver = tf.train.Saver()
# Train the main model
train(M, FLAGS, saver=saver, model_name=model_name)
def run(args):
run_args = AttrDict()
args_dict = {
'dis_learning_rate': 0.0002,
'gen_learning_rate': 0.0002,
'batch_size': 1,
'num_epochs': 10,
'human_root_dir': "../trainHuman/",
'cartoon_root_dir': "../trainCartoon/",
'act_fn_gen': 'relu',
'act_fn_dis': 'lrelu',
'norm_type': 'instance',
'num_res': 3,
'dropout': False,
'lambda_cycle': 10,
'gray': False,
'Conv2T': False
}
if (args.train):
print(
"---Trains 10 images for 10 epochs to indicate that our training loop works---"
)
else:
print("---Will evaluate the specified trained model now---")
folder_path = ""
isVAE = False
if args.Conv2T:
args_dict['Conv2T'] = True
args_dict['norm_type'] = 'batch'
folder_path = "../conv2T"
elif args.RegConv:
args_dict['norm_type'] = 'batch'
folder_path = "../RegConv"
elif args.VAE:
isVAE = True
folder_path = "../VAE"
elif (args.Gray):
pass
run_args.update(args_dict)
if args.train:
train2.train(run_args, device)
else:
evaluate.evaluate(folder_path, run_args, isVAE=isVAE)
HN1, HN2 = 20, 4
EPOCHS = 100
BATCH_SIZE = 50
LR = 0.0007
# Instantiate the network and prepare data
avg_mse = 1
while avg_mse > 0.9:
net = Net(HN1, HN2)
training_inputs = training_data[:, 0:4]
training_labels = training_data[:, 4:]
test_inputs = testing_data[:, 0:4]
test_labels = testing_data[:, 4:]
# Train and test the network
train(net, training_inputs, training_labels, EPOCHS, LR, BATCH_SIZE)
avg_mse, predictions_online, predictions_offline = test(
test_inputs, test_labels, net)
print(avg_mse)
predictions_online_inverse_transform = scaler_test.inverse_transform(
predictions_online)
predictions_offline_inverse_transform = scaler_test.inverse_transform(
predictions_offline)
online = pd.DataFrame(predictions_online_inverse_transform)
offline = pd.DataFrame(predictions_offline_inverse_transform)
avg_mse = pd.DataFrame([avg_mse, 0])
online.to_excel(
'Data3/Optimised_Networks/manual_online3 {x}_{y}-{z}_{a}_{b}_{c}.xlsx'.
HN1 = 15
EPOCHS = 30
BATCH_SIZE = 8
LR = [0.0001, 0.0002, 0.0003, 0.0004, 0.0005, 0.0006, 0.0007, 0.0008, 0.0009, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007, 0.008, 0.009, 0.01, 0.02, 0.03, 0.04, 0.05, 0.06, 0.07, 0.08, 0.09, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1]
MODELS = {}
rnn = RNN(3, 5, 12, HN1, HL)
init_state = copy.deepcopy(rnn.state_dict())
for lr in LR:
rnn.load_state_dict(init_state)
training_inputs = training_data[:, 0:5]
training_labels = training_data[:, 5:]
test_inputs = testing_data[:, 0:5]
test_labels = testing_data[:, 5:]
training_inputs = np.split(training_inputs, 606)
training_labels = np.split(training_labels, 606)
test_inputs = np.split(test_inputs, 2)
test_labels = np.split(test_labels, 2)
train(rnn, training_inputs, training_labels, EPOCHS, lr, BATCH_SIZE)
avg_mse = test(test_inputs, test_labels, rnn)
MODELS['{a}_{x}_{z}_{b}'.format(a=HL, x=HN1, z=EPOCHS, b=lr)] = np.array(avg_mse)
with open('Data2/Search/manual_search_results_{x}HL_lr_GLMAX1_1_15_30.csv'.format(x=HL), 'w') as f:
for key in MODELS.keys():
f.write("%s: %s\n"%(key, MODELS[key]))
print(MODELS)
LR = 0.0009
MODELS = {}
rnn = RNN(3, 5, 12, HN1, HL)
init_state = copy.deepcopy(rnn.state_dict())
for bs in BATCH_SIZE:
rnn.load_state_dict(init_state)
training_inputs = training_data[:, 0:5]
training_labels = training_data[:, 5:]
test_inputs = testing_data[:, 0:5]
test_labels = testing_data[:, 5:]
training_inputs = np.split(training_inputs, 606)
training_labels = np.split(training_labels, 606)
test_inputs = np.split(test_inputs, 2)
test_labels = np.split(test_labels, 2)
train(rnn, training_inputs, training_labels, EPOCHS, LR, bs)
avg_mse = test(test_inputs, test_labels, rnn)
MODELS['{a}_{x}_{z}_{b}_{c}'.format(a=HL, x=HN1, z=EPOCHS, b=LR,
c=bs)] = avg_mse
with open(
'Data2/Search/manual_search_results_{x}HL_bs_GLMAX1_1_15_30.csv'.
format(x=HL), 'w') as f:
for key in MODELS.keys():
f.write("%s: %s\n" % (key, MODELS[key]))
print(MODELS)
np.random.shuffle(training_data)
# Manual Search Training Loop
HL = 2
HN1 = 4
HN2 = 8
EPOCHS = 152
BATCH_SIZE = [5, 10, 15, 20, 30, 40, 50, 100, 200, 300, 400, 500]
LR = 0.006
MODELS = {}
net = Net(HN1, HN2)
init_state = copy.deepcopy(net.state_dict())
for bs in BATCH_SIZE:
net.load_state_dict(init_state)
training_inputs = training_data[:, 0:5]
training_labels = training_data[:, 5:]
test_inputs = testing_data[:, 0:5]
test_labels = testing_data[:, 5:]
train(net, training_inputs, training_labels, EPOCHS, LR, bs)
avg_mse = test(test_inputs, test_labels, net)
MODELS['{a}_{x}-{y}_{z}_{b}_{c}'.format(a=HL, x=HN1, y=HN2, z=EPOCHS, b=LR, c=bs)] = avg_mse
with open('Data3/Search/manual_search_results_{x}HL_bsTIMETEST.csv'.format(x=HL), 'w') as f:
for key in MODELS.keys():
f.write("%s: %s\n"%(key, MODELS[key]))
print(MODELS)
train_topic_var = Variable(torch.LongTensor(topic_index))
train_text_var = Variable(torch.LongTensor(text_index))
train_label_var = Variable(torch.LongTensor(label_index))
# dev_topic_var = Variable(torch.LongTensor(dev_topic_index))
# dev_text_var = Variable(torch.LongTensor(dev_text_index))
# dev_label_var = Variable(torch.LongTensor(dev_label_index))
test_topic_var = Variable(torch.LongTensor(test_topic_index))
test_text_var = Variable(torch.LongTensor(test_text_index))
test_label_var = Variable(torch.LongTensor(test_label_index))
# # print("ssss",test_topic_var)
# print(test_text_var)
# print(test_label_var)
# dev_iter = dataProcessing.create_batches(dev_topic_var, dev_text_var, dev_label_var, params.batch_size)
# print(dev_iter)
test_iter = dataProcessing.create_batches(test_topic_var, test_text_var,
test_label_var,
params.batch_size)
# print(test_iter)
# print("train_var",train_topic_var) #2414x6
# print("train_text_var",train_text_var) #2414x35
# print("train_label_var",train_label_var) #2414x1
if params.use_lstm is True:
model = model_BiLSTM.BiLSTM(params)
if params.cuda_use is True:
model = model.cuda()
train2.train(train_topic_var, train_text_var, train_label_var, model,
label2id, id2label, params, test_iter)