def __init__(self, input_size, weights):
input_image = Input(shape=(input_size[0], input_size[1], 3))
if weights == 'imagenet':
nasnetmobile = NASNetMobile(input_tensor=input_image,
include_top=False,
weights='imagenet',
pooling=None)
print('Successfully loaded imagenet backend weights')
else:
nasnetmobile = NASNetMobile(input_tensor=input_image,
include_top=False,
weights=None,
pooling=None)
if weights:
nasnetmobile.load_weights(weights)
print('Loaded backend weigths: ' + weights)
self.feature_extractor = nasnetmobile
# 컴파일, 훈련
op = Adadelta(lr=1e-3)
batch_size = 4
es = EarlyStopping(monitor='val_loss', patience=20, restore_best_weights=True, verbose=1)
lr = ReduceLROnPlateau(monitor='val_loss', vactor=0.5, patience=10, verbose=1)
path = 'C:/nmb/nmb_data/h5/5s/Nasnet/nasnet_adadelta_1.h5'
mc = ModelCheckpoint(path, monitor='val_loss', verbose=1, save_best_only=True)
model.compile(optimizer=op, loss="sparse_categorical_crossentropy", metrics=['acc'])
history = model.fit(x_train, y_train, epochs=1000, batch_size=batch_size, validation_split=0.2, callbacks=[es, lr, mc])
# 평가, 예측
# model = load_model('C:/nmb/nmb_data/h5/5s/Nasnet/nasnet_adadelta_1.h5')
model.load_weights('C:/nmb/nmb_data/h5/5s/Nasnet/nasnet_adadelta_1.h5')
result = model.evaluate(x_test, y_test, batch_size=8)
print("loss : {:.5f}".format(result[0]))
print("acc : {:.5f}".format(result[1]))
############################################ PREDICT ####################################
pred = ['C:/nmb/nmb_data/predict_04_26/F', 'C:/nmb/nmb_data/predict_04_26/M']
count_f = 0
count_m = 0
for pred_pathAudio in pred:
files = librosa.util.find_files(pred_pathAudio, ext=['wav'])
files = np.asarray(files)
for file in files:
path = 'C:/nmb/nmb_data/h5/5s/Nasnet/nasnet_rmsprop_1.h5'
mc = ModelCheckpoint(path, monitor='val_loss', verbose=1, save_best_only=True)
model.compile(optimizer=op,
loss="sparse_categorical_crossentropy",
metrics=['acc'])
history = model.fit(x_train,
y_train,
epochs=1000,
batch_size=batch_size,
validation_split=0.2,
callbacks=[es, lr, mc])
# 평가, 예측
# model = load_model('C:/nmb/nmb_data/h5/5s/Nasnet/nasnet_rmsprop_1.h5')
model.load_weights('C:/nmb/nmb_data/h5/5s/Nasnet/nasnet_rmsprop_1.h5')
result = model.evaluate(x_test, y_test, batch_size=8)
print("loss : {:.5f}".format(result[0]))
print("acc : {:.5f}".format(result[1]))
############################################ PREDICT ####################################
pred = ['C:/nmb/nmb_data/predict_04_26/F', 'C:/nmb/nmb_data/predict_04_26/M']
count_f = 0
count_m = 0
for pred_pathAudio in pred:
files = librosa.util.find_files(pred_pathAudio, ext=['wav'])
files = np.asarray(files)
for file in files: