def train_val(model, base_model):
train_gen = sample_gen(file_id_mapping_train)
# print gen(train_gen, batch_size).next()
test_gen = sample_gen(file_id_mapping_test)
checkpoint = ModelCheckpoint(file_path,
monitor='val_loss',
verbose=1,
save_best_only=True,
mode='min')
early = EarlyStopping(monitor="val_loss", mode="min", patience=5)
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3)
callbacks_list = [checkpoint, early, reduce_lr] # early
history = model.fit_generator(gen(train_gen, batch_size),
validation_data=gen(test_gen, batch_size),
epochs=60,
verbose=1,
workers=4,
use_multiprocessing=True,
callbacks=callbacks_list,
steps_per_epoch=500,
validation_steps=30)
# model.compile(loss=identity_loss, optimizer=SGD(0.000001))
# history = model.fit_generator(gen(train_gen, batch_size), validation_data=gen(test_gen, batch_size), epochs=60, verbose=1, workers=4, use_multiprocessing=True,
# callbacks=callbacks_list, steps_per_epoch=500, validation_steps=30)
# return
file_name = file_path
for i in xrange(1, 10):
train_file_distance = gen_distance(base_model, file_id_mapping_train,
i)
test_file_distance = gen_distance(base_model, file_id_mapping_test, i)
train_gen = hard_sample_gen(train_file_distance)
test_gen = hard_sample_gen(test_file_distance)
model, base_model = build_model()
model = multi_gpu_model(model, gpus=4)
model.compile(loss=identity_loss, optimizer=Adam(0.000001))
model.load_weights(file_name)
file_name = 'hard_{}.h5'.format(i)
checkpoint = ModelCheckpoint(file_name,
monitor='val_loss',
verbose=1,
save_best_only=True,
mode='min')
early = EarlyStopping(monitor="val_loss", mode="min", patience=15)
history = model.fit_generator(gen(train_gen, batch_size),
validation_data=gen(
test_gen, batch_size),
epochs=60,
verbose=1,
workers=4,
use_multiprocessing=True,
steps_per_epoch=500,
validation_steps=30,
callbacks=[checkpoint, early])
def train_all():
reduce_lr = ReduceLROnPlateau(monitor='loss', factor=0.5, patience=3)
callbacks_list = [reduce_lr] # early
history = model.fit_generator(gen(all_gen, batch_size),
epochs=60,
verbose=1,
workers=4,
use_multiprocessing=True,
callbacks=callbacks_list,
steps_per_epoch=500)
model.compile(loss=identity_loss, optimizer=SGD(0.000001))
history = model.fit_generator(gen(all_gen, batch_size),
epochs=60,
verbose=1,
workers=4,
use_multiprocessing=True,
callbacks=callbacks_list,
steps_per_epoch=500)
model.save('vgg_all.h5')
emb_matrix = data_utils.load_glove_embedding(glove_path, vocab)
K.clear_session()
model = models.build_glove_model(p,
len(vocab),
emb_matrix,
glove_trainable=args.ft,
drop_rate=args.drop)
if last_weight:
print('Loading weight :', last_weight)
model.load_weights(last_weight)
train_gen = data_utils.gen(MODEL_NAME,
p,
train_df,
vocab,
batch_size=BATCH_SIZE)
val_gen = data_utils.gen(MODEL_NAME,
p,
val_df,
vocab,
batch_size=BATCH_SIZE,
shuffle=False)
train_steps = np.ceil(len(train_df) / BATCH_SIZE)
val_steps = np.ceil(len(val_df) / BATCH_SIZE)
print(train_steps, val_steps)
callbacks = [
# reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3)
# callbacks_list = [checkpoint, early, reduce_lr] # early
# history = model.fit_generator(gen(train_gen, batch_size), validation_data=gen(test_gen, batch_size), epochs=60, verbose=1, workers=4, use_multiprocessing=True,
# callbacks=callbacks_list, steps_per_epoch=500, validation_steps=30)
# model.compile(loss=identity_loss, optimizer=SGD(0.000001))
# history = model.fit_generator(gen(train_gen, batch_size), validation_data=gen(test_gen, batch_size), epochs=60, verbose=1, workers=4, use_multiprocessing=True,
# callbacks=callbacks_list, steps_per_epoch=500, validation_steps=30)
reduce_lr = ReduceLROnPlateau(monitor='loss', factor=0.5, patience=3)
callbacks_list = [reduce_lr] # early
history = model.fit_generator(gen(all_gen, batch_size),
epochs=60,
verbose=1,
workers=4,
use_multiprocessing=True,
callbacks=callbacks_list,
steps_per_epoch=500)
model.compile(loss=identity_loss, optimizer=SGD(0.000001))
history = model.fit_generator(gen(all_gen, batch_size),
epochs=60,
verbose=1,
workers=4,
use_multiprocessing=True,
callbacks=callbacks_list,
steps_per_epoch=500)
glove_path = 'glove/glove.6B.50d.txt'
emb_matrix = data_utils.load_glove_embedding(glove_path, vocab)
model = models.build_glove_model(p,
len(vocab),
emb_matrix,
glove_trainable=args.ft,
drop_rate=args.drop,
summary=False)
print('Loading weight :', weight)
model.load_weights(weight)
test_gen = data_utils.gen(MODEL_NAME,
p,
test_df,
vocab,
batch_size=BATCH_SIZE,
test=True,
shuffle=False)
test_steps = np.ceil(len(test_df) / BATCH_SIZE)
print(test_gen, test_steps)
y_true = data_utils.prepare_features(MODEL_NAME,
df=test_df,
prompt=p,
vocab=vocab,
y_only=True,
norm=True)
def on_epoch_end(self, epoch, logs):
y_pred = self.model.predict_generator(
gen(self.model_name, self.prompt, self.val_data, self.vocab, self.batch_size, test=True, shuffle=False), steps=self.steps, verbose=1)
generate_qwk(self.prompt, self.model_name,
self.y_true, y_pred, epoch+1, 'val')