def main():
# 学習用のimages, labelsのbatchを取得
train, test = inputs.get_data()
train_images, train_labels = inputs.train_batch(train)
# 推論結果、誤差、学習のためのOperationを定義
train_logits = cnn.inference(train_images)
losses = loss(train_labels, train_logits)
train_op = training(losses)
test_images, test_labels = inputs.test_batch(test)
test_logits = cnn.inference(test_images, reuse=True)
correct_prediction = tf.equal(tf.argmax(test_logits, 1), tf.to_int64(test_labels))
accuracy = tf.reduce_mean(tf.to_float(correct_prediction))
with tf.Session() as sess:
# batchからデータを取り出すためのスレッドの準備
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
sess.run(tf.global_variables_initializer())
# 学習を繰り返す
for i in range(300):
_, loss_value, accuracy_value = sess.run([train_op, losses, accuracy])
print("step {:3d} : {:5f} ({:3f})".format(i + 1, loss_value, accuracy_value * 100.0))
coord.request_stop()
coord.join(threads)
def main():
train, valid, test = inputs.get_data()
train_images, train_labels = inputs.make_batch(train)
valid_images, valid_labels = inputs.make_batch(valid)
test_images, test_labels = inputs.make_batch(test)
num_classes = 47
train_y = keras.utils.to_categorical(train_labels, num_classes)
valid_y = keras.utils.to_categorical(valid_labels, num_classes)
test_y = keras.utils.to_categorical(test_labels, num_classes)
model = network(num_classes)
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer='Adam',
metrics=['accuracy'])
# verbose: display mode: 0:no display, 1: progress bar
batch_size = 32
history = model.fit(train_images,train_y,batch_size=32,\
epochs=10,verbose=1,validation_data = (valid_images, valid_y))
score = model.evaluate(test_images, test_y, verbose=0)
# score[0]: loss, score[1]: accuracy
print('Loss:', score[0])
print('Accuracy:', score[1])
backend.clear_session()
def get_all_data(data_path, smell):
print("reading data...")
train_data, train_labels, eval_data, eval_labels, max_input_length = \
inputs.get_data(data_path, OUT_FOLDER, "rq1_rnn_" + smell,
train_validate_ratio=TRAIN_VALIDATE_RATIO, max_training_samples= 5000)
train_data = train_data.reshape((len(train_labels), max_input_length))
eval_data = eval_data.reshape((len(eval_labels), max_input_length))
print("reading data... done.")
return input_data.Input_data(train_data, train_labels, eval_data,
eval_labels, max_input_length)
def get_all_data(data_path):
print("reading data...")
# Load training and eval data
train_data, train_labels, eval_data, eval_labels, max_input_length = \
inputs.get_data(data_path, OUT_FOLDER, "rq1_cnn1d_" + smell,
train_validate_ratio=TRAIN_VALIDATE_RATIO, max_training_samples= 5000)
# train_data = train_data.reshape((len(train_labels), max_input_length))
# eval_data = eval_data.reshape((len(eval_labels), max_input_length))
print("train_data: " + str(len(train_data)))
print("train_labels: " + str(len(train_labels)))
print("eval_data: " + str(len(eval_data)))
print("eval_labels: " + str(len(eval_labels)))
print("reading data... done.")
return input_data.Input_data(train_data, train_labels, eval_data,
eval_labels, max_input_length)
def get_all_data(data_path, smell):
print("reading data...")
if smell in ["ComplexConditional", "ComplexMethod"]:
max_eval_samples = 150000 # for impl smells (methods)
else:
max_eval_samples = 50000 # for design smells (classes)
train_data, train_labels, eval_data, eval_labels, max_input_length = \
inputs.get_data(data_path,
train_validate_ratio=TRAIN_VALIDATE_RATIO, max_training_samples=5000,
max_eval_samples=max_eval_samples, is_c2v=C2V)
train_data = train_data.reshape((len(train_labels), max_input_length))
eval_data = eval_data.reshape((len(eval_labels), max_input_length))
print("reading data... done.")
return input_data.Input_data(train_data, train_labels, eval_data,
eval_labels, max_input_length)
"""
# just deleting variables quickly while I play with file
for name in dir():
if not name.startswith('_'):
del globals()[name]
import numpy as np
import pylab as pl
from model import steps
from likelihood import lnlike, model_outcomes
from inputs import get_data, get_params, get_initial_conditions
from mcmc import mcmc
pops = ['fertile_women', '0-1', '1-6', '6-12', '12-24', '24-72']
D = get_data()
P = get_params()
C0 = get_initial_conditions()
t_steps = 1000 # model run time (months)
# Run the model
y = steps(P, C0, t_steps)
LL = lnlike(C0, P, D, t_steps, pops)
# Parameters to calibrate
meta_prefit = dict()
meta_prefit['mortality, 0-1, non-stunted'] = P['mortality']['0-1'][
'non-stunted']
meta_prefit['mortality, 0-1, stunted'] = P['mortality']['0-1']['stunted']
# just deleting variables quickly while I play with file
for name in dir():
if not name.startswith('_'):
del globals()[name]
import numpy as np
import pylab as pl
from model import steps
from likelihood import lnlike, model_outcomes
from inputs import get_data, get_params, get_initial_conditions
from mcmc import mcmc
pops = ['fertile_women', '0-1', '1-6', '6-12', '12-24', '24-72']
D = get_data()
P = get_params()
C0 = get_initial_conditions()
t_steps = 1000 # model run time (months)
# Run the model
y = steps(P, C0, t_steps)
LL = lnlike(C0, P, D, t_steps, pops)
# Parameters to calibrate
meta_prefit = dict()
meta_prefit['mortality, 0-1, non-stunted'] = P['mortality']['0-1']['non-stunted']
meta_prefit['mortality, 0-1, stunted'] = P['mortality']['0-1']['stunted']
])
if LOAD_OLD:
model = load_model(MODEL_PATH)
checkpoint = ModelCheckpoint(MODEL_PATH,
monitor='val_acc',
verbose=1,
save_best_only=True,
mode='max')
adam = Adam(lr=LR, decay=0.0)
model.compile(loss='mean_squared_error', optimizer=adam, metrics=['accuracy'])
if __name__ == '__main__':
print('Loading data...')
X, Y = get_data()
print('Fitting model...')
history = model.fit(X,
Y,
validation_split=VAL_SPLIT,
epochs=EPOCHS,
batch_size=BATCH_SIZE,
shuffle=True,
callbacks=[checkpoint])
# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('Model Accuracy')
plt.ylabel('accuracy')