class FeatureExtractor:
def __init__(self):
with graph.as_default():
self.model = Xception(
weights="imagenet",
classes=1000,
classifier_activation="softmax",
)
def extract(self, img):
"""
Extract a deep feature from an input image
Args:
img: from PIL.Image.open(path) or tensorflow.keras.preprocessing.image.load_img(path)
Returns:
feature (np.ndarray): deep feature with the shape=(4096, )
"""
img = Image.open(img)
img = img.resize(
(299, 299)) # Xception must take a 299x299 img as an input
img = img.convert('RGB') # Make sure img is color
x = image.img_to_array(
img) # To np.array. Height x Width x Channel. dtype=float32
x = np.expand_dims(
x, axis=0
) # (H, W, C)->(1, H, W, C), where the first elem is the number of img
x = preprocess_input(x) # Subtracting avg values for each pixel
with graph.as_default():
set_session(sess)
feature = self.model.predict(x)[0] # (1, 4096) -> (4096, )
return feature / np.linalg.norm(feature) # Normalize
def predict(img):
model = Xception(weights="imagenet",
include_top=True,
input_tensor=Input(shape=(224, 224, 3)))
img = img_to_array(img)
img = img.reshape((-1, img.shape[0], img.shape[1], 3)) / 255
rez = model.predict(img)
rez = pd.DataFrame(decode_predictions(rez)[0],
columns=['_', 'breed',
'prct']).drop(columns='_').sort_values(
by='prct', ascending=False)
np.array(rez)
return rez
files = librosa.util.find_files(pred_pathAudio, ext=['wav'])
files = np.asarray(files)
for file in files:
name = os.path.basename(file)
length = len(name)
name = name[0]
y, sr = librosa.load(file, sr=22050)
mels = librosa.feature.melspectrogram(y,
sr=sr,
hop_length=128,
n_fft=512)
pred_mels = librosa.amplitude_to_db(mels, ref=np.max)
pred_mels = pred_mels.reshape(1, pred_mels.shape[0],
pred_mels.shape[1])
y_pred = model.predict(pred_mels)
y_pred_label = np.argmax(y_pred)
if y_pred_label == 0: # 여성이라고 예측
print(file, '{:.4f} 의 확률로 여자입니다.', format((y_pred[0][0]) * 100))
if name == 'F':
count_f = count_f + 1
else: # 남성이라고 예측
print(file, '{:.4f} 의 확률로 남자입니다.', format((y_pred[0][1]) * 100))
if name == 'M':
count_m = count_m + 1
print("43개 여성 목소리 중 " + str(count_f) + "개 정답")
print("43개 남성 목소리 중 " + str(count_m) + "개 정답")
end = datetime.now()
time = end - start_now
print("작업 시간 : ", time)
def train_and_test(model_name, compression_type, training_size, test_size):
# train model
if compression_type == "basic" and test_size == 224:
start = time.process_time()
print("training")
model = train(model_name, train_flow, valid_flow)
end = time.process_time()
else:
start = time.process_time()
model = Xception(
weights=None,
include_top=False,
#input_shape=(224,224,3)
)
model = build_model(model)
print("loading weight")
model.load_weights("results/Xception.ckpt")
end = time.process_time()
training_time = end - start
FLOW_MAP = {
"nearest": test_flow_nearest,
"box": test_flow_box,
"lanczos": test_flow_lanczos,
"hamming": test_flow_hamming,
}
test_flow = FLOW_MAP[compression_type]
# save model
# np.savez("model_%s.npz" % model_name, **model)
#Evaluate Model
# get compression specific test flow
# test_flow =
start = time.process_time()
train_pred = model.predict(valid_flow)
train_test = valid_flow.classes
train_accuracy = metrics.accuracy_score(train_test, np.round(train_pred))
# train_accuracy = history.history["accuracy"]
test_pred = model.predict(test_flow)
test_test = test_flow.classes
test_accuracy = metrics.accuracy_score(test_test, np.round(test_pred))
print("Sample predictions: ", np.round(test_pred))
print("Sample actual labels: ", test_test)
test_matrix = metrics.confusion_matrix(test_test,
np.round(test_pred)).ravel()
end = time.process_time()
test_time = end - start
print("Model: %s\n" % model_name)
print("Image Compression: %s\n" % compression)
print("Train Image Size: %d\n" % training_size)
print("Test Image Size: %d\n" % test_size)
print("Train accuracy: %f\n" % train_accuracy)
print("Test accuracy: %f\n" % test_accuracy)
print("True Negatives: %f\n" % test_matrix[0])
print("False Positives: %f\n" % test_matrix[1])
print("False Negatives: %f\n" % test_matrix[2])
print("True Positives: %f\n" % test_matrix[3])
print("Training Time: %s sec\n" % training_time)
print("Testing Time: %s sec\n" % test_time)
# save results
try:
with open("results/%s_results.txt" % model_name, "a") as f:
f.write("Model: %s\n" % model_name)
f.write("Image Compression: %s\n" % compression)
f.write("Train Image Size: %d\n" % training_size)
f.write("Test Image Size: %d\n" % test_size)
f.write("Train accuracy: %f\n" % train_accuracy)
f.write("Test accuracy: %f\n" % test_accuracy)
f.write("True Negatives: %f\n" % test_matrix[0])
f.write("False Positives: %f\n" % test_matrix[1])
f.write("False Negatives: %f\n" % test_matrix[2])
f.write("True Positives: %f\n" % test_matrix[3])
f.write("Training Time: %s sec\n" % training_time)
f.write("Testing Time: %s sec\n" % test_time)
f.write("\n\n")
f.close()
except Exception as e:
print(e)
return {
"Model": model_name,
"Image Compression": compression,
"Train Image Size": training_size,
"Test Image Size": test_size,
"Training Accuracy": train_accuracy,
"Test Accuracy": test_accuracy,
"True Negative": test_matrix[0],
"False Positive": test_matrix[1],
"False Negative": test_matrix[2],
"True Positive": test_matrix[3],
"Train Time": training_time,
"Test Time": test_time
}
# Read until video is completed
while(cap.isOpened()):
# Capture frame-by-frame
c += 1
ret, frame = cap.read()
if ret == True:
# Display the resulting frame
frame = cv2.resize(frame,(299,299))
#cv2.imshow('Frame',frame)
if c <= 200:
frame = img_to_array(frame)
frame = frame.reshape((1, frame.shape[0], frame.shape[1], frame.shape[2]))
frame = preprocess_input(frame)
features = model.predict(frame, verbose=0)
print(features,c)
F.append(features)
#print(np.argmax(features))
else:
break
# Press Q on keyboard to exit
#if cv2.waitKey(25) & 0xFF == ord('q'):
# break
#plt.plot(len(features),features)
#plt.pause(0.05)
# Break the loop
else:
break
