choices=[2, 4, 8],
help='upscale factor')
parser.add_argument('--epochs',
default=100,
type=int,
help='train epoch number')
if __name__ == '__main__':
opt = parser.parse_args()
crop_size = opt.crop_size
upscale = opt.upscale_factor
epoch = opt.epochs
train_set = load_training_data('DIV2K_train_HR',
crop_size=crop_size,
upscale=upscale)
val_set = load_val_data('DIV2K_valid_HR', upscale=upscale)
train_loader = DataLoader(dataset=train_set,
num_workers=4,
batch_size=64,
shuffle=True)
val_loader = DataLoader(dataset=val_set,
num_workers=4,
batch_size=1,
shuffle=False)
netG = Generator(upscale)
print('# generator parameters:',
sum(param.numel() for param in netG.parameters()))
netD = Discriminator()
#sys.stdout = f
print("Writing to {}\n".format(out_dir))
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
print("{}={}".format(attr.upper(), value))
print("")
with open(out_dir+'/params', 'w') as f:
for attr, value in sorted(FLAGS.__flags.items()):
f.write("{}={}".format(attr.upper(), value))
f.write("\n")
# hyper-parameters end here
training_path = 'training_set_rel3.tsv'
essay_list, resolved_scores, essay_id = data_utils.load_training_data(training_path, essay_set_id)
max_score = max(resolved_scores)
min_score = min(resolved_scores)
if essay_set_id == 7:
min_score, max_score = 0, 30
elif essay_set_id == 8:
min_score, max_score = 0, 60
print 'max_score is {} \t min_score is {}\n'.format(max_score, min_score)
with open(out_dir+'/params', 'a') as f:
f.write('max_score is {} \t min_score is {} \n'.format(max_score, min_score))
# include max score
score_range = range(min_score, max_score+1)
#word_idx, _ = data_utils.build_vocab(essay_list, vocab_limit)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense
import numpy as np
import data_utils
data_dim = 128
timesteps = 128
train_data = data_utils.load_training_data()
test_data = data_utils.load_test_data()
# loader = data_utils.DataLoader(data=data,batch_size=train_config.batch_size, num_steps=train_config.num_steps)
data_loader = data_utils.DataLoader(train_data, 7352, 1)
# x_test, y_test = data_utils.DataLoader(train_data, 128, 1).next_batch()
# expected input data shape: (batch_size, timesteps, data_dim)
model = Sequential()
model.add(
LSTM(256, return_sequences=True,
input_shape=(1, 1))) # returns a sequence of vectors of dimension 32
model.add(LSTM(
256,
return_sequences=True)) # returns a sequence of vectors of dimension 32
model.add(LSTM(
256, return_sequences=True)) # return a single vector of dimension 32
model.add(Dense(128, activation="sigmoid", name="DENSE1"))
model.add(Dense(72, activation="sigmoid", name="DENSE2"))
model.add(Dense(1, activation='softmax'))
