class AmazonKerasClassifier:
def __init__(self):
self.losses = []
self.classifier = Sequential()
def add_conv_layer(self, img_size=(32, 32), img_channels=3):
self.classifier.add(BatchNormalization(input_shape=(img_size, img_channels)))
self.classifier.add(Conv2D(32, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(32, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(Conv2D(64, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(64, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(Conv2D(128, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(128, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(Conv2D(256, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(256, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
def add_flatten_layer(self):
self.classifier.add(Flatten())
def add_ann_layer(self, output_size):
self.classifier.add(Dense(512, activation='relu'))
self.classifier.add(BatchNormalization())
self.classifier.add(Dropout(0.5))
self.classifier.add(Dense(output_size, activation='sigmoid'))
def _get_fbeta_score(self, classifier, X_valid, y_valid):
p_valid = classifier.predict(X_valid)
return fbeta_score(y_valid, np.array(p_valid) > 0.2, beta=2, average='samples')
def train_model(self, x_train, y_train, learn_rate=0.001, epoch=5, batch_size=128, validation_split_size=0.2, train_callbacks=()):
history = LossHistory()
X_train, X_valid, y_train, y_valid = train_test_split(x_train, y_train,
test_size=validation_split_size)
opt = Adam(lr=learn_rate)
self.classifier.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
# early stopping will auto-stop training process if model stops learning after 3 epochs
earlyStopping = EarlyStopping(monitor='val_loss', patience=3, verbose=0, mode='auto')
self.classifier.fit(X_train, y_train,
batch_size=batch_size,
epochs=epoch,
verbose=1,
validation_data=(X_valid, y_valid),
callbacks=[history, *train_callbacks, earlyStopping])
fbeta_score = self._get_fbeta_score(self.classifier, X_valid, y_valid)
return [history.train_losses, history.val_losses, fbeta_score]
def save_weights(self, weight_file_path):
self.classifier.save_weights(weight_file_path)
def load_weights(self, weight_file_path):
self.classifier.load_weights(weight_file_path)
def predict(self, x_test):
predictions = self.classifier.predict(x_test)
return predictions
def map_predictions(self, predictions, labels_map, thresholds):
"""
Return the predictions mapped to their labels
:param predictions: the predictions from the predict() method
:param labels_map: the map
:param thresholds: The threshold of each class to be considered as existing or not existing
:return: the predictions list mapped to their labels
"""
predictions_labels = []
for prediction in predictions:
labels = [labels_map[i] for i, value in enumerate(prediction) if value > thresholds[i]]
predictions_labels.append(labels)
return predictions_labels
def close(self):
backend.clear_session()
class AmazonKerasClassifier:
def __init__(self):
self.losses = []
self.classifier = Sequential()
def add_conv_layer(self, img_size=(32, 32), img_channels=3):
self.classifier.add(
BatchNormalization(input_shape=(*img_size, img_channels)))
self.classifier.add(
Conv2D(32, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(32, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(
Conv2D(64, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(64, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(
Conv2D(128, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(128, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(
Conv2D(256, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(256, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
def add_flatten_layer(self):
self.classifier.add(Flatten())
def add_ann_layer(self, output_size):
self.classifier.add(Dense(512, activation='relu'))
self.classifier.add(BatchNormalization())
self.classifier.add(Dropout(0.5))
self.classifier.add(Dense(output_size, activation='sigmoid'))
def _get_fbeta_score(self, classifier, X_valid, y_valid):
p_valid = classifier.predict(X_valid)
return fbeta_score(y_valid,
np.array(p_valid) > 0.2,
beta=2,
average='samples')
def train_model(self,
x_train,
y_train,
learn_rate=0.001,
epoch=5,
batch_size=128,
validation_split_size=0.2,
train_callbacks=()):
history = LossHistory()
X_train, X_valid, y_train, y_valid = train_test_split(
x_train, y_train, test_size=validation_split_size)
opt = Nadam(lr=learn_rate,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08,
schedule_decay=0.004)
self.classifier.compile(loss='binary_crossentropy',
optimizer=opt,
metrics=['accuracy'])
# early stopping will auto-stop training process if model stops learning after 3 epochs
earlyStopping = EarlyStopping(monitor='val_loss',
patience=3,
verbose=0,
mode='auto')
for i in range(epoch):
self.classifier.fit(
X_train,
y_train,
batch_size=batch_size,
epochs=1,
verbose=2,
validation_data=(X_valid, y_valid),
callbacks=[history, *train_callbacks, earlyStopping])
fbeta_score = self._get_fbeta_score(self.classifier, X_valid,
y_valid)
print('fbeta score: %s' % fbeta_score)
return [history.train_losses, history.val_losses, fbeta_score]
def save_weights(self, weight_file_path):
self.classifier.save_weights(weight_file_path)
def load_weights(self, weight_file_path):
self.classifier.load_weights(weight_file_path)
def predict(self, x_test):
predictions = self.classifier.predict(x_test)
return predictions
def map_predictions(self, predictions, labels_map, thresholds):
"""
Return the predictions mapped to their labels
:param predictions: the predictions from the predict() method
:param labels_map: the map
:param thresholds: The threshold of each class to be considered as existing or not existing
:return: the predictions list mapped to their labels
"""
predictions_labels = []
for prediction in predictions:
labels = [
labels_map[i] for i, value in enumerate(prediction)
if value > thresholds[i]
]
predictions_labels.append(labels)
return predictions_labels
def close(self):
backend.clear_session()
class AmazonKerasClassifier:
def __init__(self):
self.losses = []
self.classifier = Sequential()
self.x_vail = []
self.y_vail = []
self.train_filepath = ''
self.train_img_filepath = ''
self.valid_filepath = ''
self.valid_img_filepath = ''
self.test_img_filepath = ''
self.test_addition_img_filepath = ''
self.test_img_name_list = ''
self.y_map = {}
def setTrainFilePath(self, value):
self.train_filepath = value
def getTrainFilePath(self):
return self.train_filepath
def setValidFilePath(self, value):
self.valid_filepath = value
def getValidFilePath(self):
return self.valid_filepath
def setTrainImgFilePath(self, value):
self.train_img_filepath = value
def getTrainImgFilePath(self):
return self.train_img_filepath
def setValidImgFilePath(self, value):
self.valid_img_filepath = value
def getValidImgFilePath(self):
return self.valid_img_filepath
def setTestImgFilePath(self, value):
self.test_img_filepath = value
def getTestImgFilePath(self):
return self.test_img_filepath
def setTestAdditionImgFilePath(self, value):
self.test_addition_img_filepath = value
def getTestAdditionImgFilePath(self):
return self.test_addition_img_filepath
def getTestImgNameList(self):
return self.test_img_name_list
def getYMap(self):
return self.y_map
def vgg(self,
type=16,
bn=False,
img_size=(224, 224),
img_channels=3,
output_size=1000):
if type == 16 and bn == False:
layer_list = vgg.vgg16(num_classes=output_size)
elif type == 16 and bn == True:
layer_list = vgg.vgg16_bn(num_classes=output_size)
elif type == 11 and bn == False:
layer_list = vgg.vgg11(num_classes=output_size)
elif type == 11 and bn == True:
layer_list = vgg.vgg11_bn(num_classes=output_size)
elif type == 13 and bn == False:
layer_list = vgg.vgg13(num_classes=output_size)
elif type == 13 and bn == True:
layer_list = vgg.vgg13_bn(num_classes=output_size)
elif type == 19 and bn == False:
layer_list = vgg.vgg19(num_classes=output_size)
elif type == 19 and bn == True:
layer_list = vgg.vgg19_bn(num_classes=output_size)
else:
print("请输入11,13,16,19这四个数字中的一个！")
self.classifier.add(
BatchNormalization(input_shape=(*img_size, img_channels)))
for i, value in enumerate(layer_list):
self.classifier.add(eval(value))
def squeezenet(self,
type,
img_size=(64, 64),
img_channels=3,
output_size=1000):
input_shape = Input(shape=(*img_size, img_channels))
if type == 1:
x = squeezenet.squeezenet1_0(input_shape, num_classes=output_size)
elif type == 1.1:
x = squeezenet.squeezenet1_1(input_shape, num_classes=output_size)
else:
print("请输入1,1.0这两个数字中的一个！")
model = Model(inputs=input_shape, outputs=x)
self.classifier = model
def resnet(self,
type,
img_size=(64, 64),
img_channels=3,
output_size=1000):
input_shape = Input(shape=(*img_size, img_channels))
if type == 18:
x = resnet.resnet18(input_shape, num_classes=output_size)
elif type == 34:
x = resnet.resnet34(input_shape, num_classes=output_size)
elif type == 50:
x = resnet.resnet50(input_shape, num_classes=output_size)
elif type == 101:
x = resnet.resnet101(input_shape, num_classes=output_size)
elif type == 152:
x = resnet.resnet152(input_shape, num_classes=output_size)
else:
print("请输入18,34,50,101,152这五个数字中的一个！")
return
model = Model(inputs=input_shape, outputs=x)
self.classifier = model
def inception(self, img_size=(299, 299), img_channels=3, output_size=1000):
input_shape = Input(shape=(*img_size, img_channels))
x = inception.inception_v3(input_shape,
num_classes=output_size,
aux_logits=True,
transform_input=False)
model = Model(inputs=input_shape, outputs=x)
self.classifier = model
def densenet(self,
type,
img_size=(299, 299),
img_channels=3,
output_size=1000):
input_shape = Input(shape=(*img_size, img_channels))
if type == 161:
x = densenet.densenet161(input_shape, num_classes=output_size)
elif type == 121:
x = densenet.densenet121(input_shape, num_classes=output_size)
elif type == 169:
x = densenet.densenet169(input_shape, num_classes=output_size)
elif type == 201:
x = densenet.densenet201(input_shape, num_classes=output_size)
else:
print("请输入161,121,169,201这四个数字中的一个！")
return
model = Model(inputs=input_shape, outputs=x)
self.classifier = model
def alexnet(self, img_size=(299, 299), img_channels=3, output_size=1000):
input_shape = Input(shape=(*img_size, img_channels))
x = alexnet.alexnet(input_shape, num_classes=output_size)
model = Model(inputs=input_shape, outputs=x)
self.classifier = model
def add_conv_layer(self, img_size=(32, 32), img_channels=3):
self.classifier.add(
BatchNormalization(input_shape=(*img_size, img_channels)))
self.classifier.add(
Conv2D(32, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(32, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(
Conv2D(64, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(64, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(
Conv2D(128, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(128, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
self.classifier.add(
Conv2D(256, (3, 3), padding='same', activation='relu'))
self.classifier.add(Conv2D(256, (3, 3), activation='relu'))
self.classifier.add(MaxPooling2D(pool_size=2))
self.classifier.add(Dropout(0.25))
def add_flatten_layer(self):
self.classifier.add(Flatten())
def add_ann_layer(self, output_size):
self.classifier.add(Dense(512, activation='relu'))
self.classifier.add(BatchNormalization())
self.classifier.add(Dropout(0.5))
self.classifier.add(Dense(output_size, activation='sigmoid'))
def _get_fbeta_score2(self, classifier, X_valid, y_valid):
p_valid = classifier.predict(X_valid)
result_threshold_list_final, score_result = self.grid_search_best_threshold(
y_valid, np.array(p_valid))
return result_threshold_list_final, score_result
def _get_fbeta_score(self, classifier, X_valid, y_valid):
p_valid = classifier.predict(X_valid)
return fbeta_score(y_valid,
np.array(p_valid) > 0.2,
beta=2,
average='samples')
def grid_search_best_threshold(self, y_valid, p_valid):
threshold_list = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
result_threshold_list_temp = [
0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2,
0.2, 0.2, 0.2, 0.2
]
result_threshold_list_final = [
0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2,
0.2, 0.2, 0.2, 0.2
]
for i in range(17):
score_result = 0
for j in range(9):
result_threshold_list_temp[i] = threshold_list[j]
score_temp = fbeta_score(y_valid,
p_valid > result_threshold_list_temp,
beta=2,
average='samples')
if score_result < score_temp:
score_result = score_temp
result_threshold_list_final[i] = threshold_list[j]
result_threshold_list_temp[i] = result_threshold_list_final[i]
return result_threshold_list_final, score_result
def train_model(self,
x_train,
y_train,
learn_rate=0.001,
epoch=5,
batch_size=128,
validation_split_size=0.2,
train_callbacks=()):
history = LossHistory()
X_train, X_valid, y_train, y_valid = train_test_split(
x_train, y_train, test_size=validation_split_size)
self.x_vail = X_valid
self.y_vail = y_valid
opt = Adam(lr=learn_rate)
self.classifier.compile(loss='binary_crossentropy',
optimizer=opt,
metrics=['accuracy'])
earlyStopping = EarlyStopping(monitor='val_loss',
patience=3,
verbose=0,
mode='auto')
self.classifier.fit(
X_train,
y_train,
batch_size=batch_size,
epochs=epoch,
verbose=1,
validation_data=(X_valid, y_valid),
callbacks=[history, *train_callbacks, earlyStopping])
fbeta_score = self._get_fbeta_score(self.classifier, X_valid, y_valid)
return [history.train_losses, history.val_losses, fbeta_score]
def train_model_generator(self,
generator_train,
generator_valid,
learn_rate=0.001,
epoch=5,
batchSize=128,
steps=32383,
validation_steps=8096,
train_callbacks=()):
history = LossHistory()
#valid 8096 32383
opt = Adam(lr=learn_rate)
steps = steps / batchSize + 1 - 9
validation_steps = validation_steps / batchSize + 1
if steps % batchSize == 0:
steps = steps / batchSize - 9
if validation_steps % batchSize == 0:
validation_steps = validation_steps / batchSize
print(steps, validation_steps)
self.classifier.compile(loss='binary_crossentropy',
optimizer=opt,
metrics=['accuracy'])
earlyStopping = EarlyStopping(monitor='val_loss',
patience=3,
verbose=0,
mode='auto')
self.classifier.fit_generator(
generator_train,
steps_per_epoch=steps,
epochs=epoch,
verbose=1,
validation_data=generator_valid,
validation_steps=validation_steps,
callbacks=[history, *train_callbacks, earlyStopping])
fbeta_score = self._get_fbeta_score(self.classifier, X_valid, y_valid)
return [history.train_losses, history.val_losses, fbeta_score]
def generate_trainOrValid_img_from_file(self,
train_set_folder,
train_csv_file,
img_resize=(32, 32),
batchSize=128,
process_count=cpu_count()):
labels_df = pd.read_csv(train_csv_file)
labels = sorted(
set(
chain.from_iterable(
[tags.split(" ") for tags in labels_df['tags'].values])))
labels_map = {l: i for i, l in enumerate(labels)}
files_path = []
tags_list = []
for file_name, tags in labels_df.values:
files_path.append('{}/{}.jpg'.format(train_set_folder, file_name))
tags_list.append(tags)
X = []
Y = []
iter_num = 1
self.y_map = {v: k for k, v in labels_map.items()}
with ThreadPoolExecutor(process_count) as pool:
for img_array, targets in tqdm(pool.map(
self._train_transform_to_matrices,
[(file_path, tag, labels_map, img_resize)
for file_path, tag in zip(files_path, tags_list)]),
total=len(files_path)):
if iter_num % batchSize == 0:
X = []
Y = []
iter_num = 0
X.append(img_array)
Y.append(targets)
iter_num += 1
if iter_num == batchSize:
print(iter_num)
yield (np.array(X), np.array(Y))
def _train_transform_to_matrices(self, *args):
file_path, tags, labels_map, img_resize = list(args[0])
img = Image.open(file_path)
img.thumbnail(img_resize)
img_array = np.asarray(img.convert("RGB"), dtype=np.float32) / 255
targets = np.zeros(len(labels_map))
for t in tags.split(' '):
targets[labels_map[t]] = 1
return img_array, targets
def generate_test_img_from_file(self,
test_set_folder,
img_resize=(32, 32),
batchSize=128,
process_count=cpu_count()):
x_test = []
x_test_filename = []
files_name = os.listdir(test_set_folder)
X = []
Y = []
iter_num = 1
with ThreadPoolExecutor(process_count) as pool:
for img_array, file_name in tqdm(pool.map(
_test_transform_to_matrices,
[(test_set_folder, file_name, img_resize)
for file_name in files_name]),
total=len(files_name)):
x_test.append(img_array)
x_test_filename.append(file_name)
self.test_img_name_list = x_test_filename
if iter_num % batchSize == 0:
X = []
Y = []
iter_num = 0
X.append(img_array)
Y.append(targets)
iter_num += 1
if iter_num == batchSize:
print(iter_num)
yield (np.array(X), np.array(Y))
def _test_transform_to_matrices(self, *args):
test_set_folder, file_name, img_resize = list(args[0])
img = Image.open('{}/{}'.format(test_set_folder, file_name))
img.thumbnail(img_resize)
# Convert to RGB and normalize
img_array = np.array(img.convert("RGB"), dtype=np.float32) / 255
return img_array, file_name
def save_weights(self, weight_file_path):
self.classifier.save_weights(weight_file_path)
def load_weights(self, weight_file_path):
self.classifier.load_weights(weight_file_path)
def setBestThreshold(self):
result_threshold_list_final, score_result = self._get_fbeta_score2(
self.classifier, self.x_vail, self.y_vail)
print('最好得分:{}'.format(score_result))
print('最好的阈值:{}'.format(result_threshold_list_final))
return result_threshold_list_final
def predict(self, x_test):
predictions = self.classifier.predict(x_test)
return predictions
def predict_generator(self, generator):
predictions = self.classifier.predcit_generator(generator)
return predictions
def map_predictions(self, predictions, labels_map, thresholds):
predictions_labels = []
for prediction in predictions:
labels = [
labels_map[i] for i, value in enumerate(prediction)
if value > thresholds[i]
]
predictions_labels.append(labels)
return predictions_labels
def close(self):
backend.clear_session()
class KerasModel:
def __init__(self, img_size, img_channels=3, output_size=17):
self.losses = []
self.model = Sequential()
self.model.add(
BatchNormalization(input_shape=(img_size[0], img_size[1],
img_channels)))
self.model.add(Conv2D(32, (3, 3), padding='same', activation='relu'))
self.model.add(Conv2D(32, (3, 3), activation='relu'))
self.model.add(MaxPooling2D(pool_size=2))
self.model.add(Dropout(0.3))
self.model.add(Conv2D(64, (3, 3), padding='same', activation='relu'))
self.model.add(Conv2D(64, (3, 3), activation='relu'))
self.model.add(MaxPooling2D(pool_size=2))
self.model.add(Dropout(0.3))
self.model.add(Conv2D(128, (3, 3), padding='same', activation='relu'))
self.model.add(Conv2D(128, (3, 3), activation='relu'))
self.model.add(MaxPooling2D(pool_size=2))
self.model.add(Dropout(0.3))
self.model.add(Conv2D(256, (3, 3), padding='same', activation='relu'))
self.model.add(Conv2D(256, (3, 3), activation='relu'))
self.model.add(MaxPooling2D(pool_size=2))
self.model.add(Dropout(0.3))
self.model.add(Conv2D(512, (3, 3), padding='same', activation='relu'))
self.model.add(Conv2D(512, (3, 3), activation='relu'))
self.model.add(MaxPooling2D(pool_size=2))
self.model.add(Dropout(0.3))
self.model.add(Flatten())
self.model.add(Dense(512, activation='relu'))
self.model.add(BatchNormalization())
self.model.add(Dropout(0.5))
self.model.add(Dense(output_size, activation='sigmoid'))
def get_fbeta_score(self, validation_data, verbose=True):
p_valid = self.model.predict(validation_data[0])
thresholds = optimise_f2_thresholds(validation_data[1],
p_valid,
verbose=verbose)
return fbeta_score(validation_data[1],
np.array(p_valid) > thresholds,
beta=2,
average='samples'), thresholds
def fit(self,
flow,
epochs,
lr,
validation_data,
train_callbacks=[],
batches=300):
history = LossHistory()
fbeta = Fbeta(validation_data)
opt = Adam(lr=lr)
self.model.compile(loss='binary_crossentropy',
optimizer=opt,
metrics=['accuracy'])
earlyStopping = EarlyStopping(monitor='val_loss',
patience=3,
verbose=0,
mode='auto')
self.model.fit_generator(flow,
steps_per_epoch=batches,
epochs=epochs,
callbacks=[history, earlyStopping, fbeta] +
train_callbacks,
validation_data=validation_data)
fb_score, thresholds = self.get_fbeta_score(validation_data,
verbose=False)
return [
fbeta.fbeta, history.train_losses, history.val_losses, fb_score,
thresholds
]
def save_weights(self, weight_file_path):
self.model.save_weights(weight_file_path)
def load_weights(self, weight_file_path):
self.model.load_weights(weight_file_path)
def predict_image(self, image):
img = Image.fromarray(np.uint8(image * 255))
images = [img.copy().rotate(i) for i in [-90, 90, 180]]
images.append(img)
images = np.asarray([
np.asarray(image.convert("RGB"), dtype=np.float32) / 255
for image in images
])
return sum(self.model.predict(images)) / 4
def predict(self, x_test):
return [self.predict_image(img) for img in tqdm(x_test)]
def map_predictions(self, predictions, labels_map, thresholds):
predictions_labels = []
for prediction in predictions:
labels = [
labels_map[i] for i, value in enumerate(prediction)
if value > thresholds[i]
]
predictions_labels.append(labels)
return predictions_labels
def close(self):
backend.clear_session()
"""Predict if the customer with the following informations will leave the bank:
Geography: France
Credit Score: 600
Gender: Male
Age: 40
Tenure: 3
Balance: 60000
Number of Products: 2
Has Credit Card: Yes
Is Active Member: Yes
Estimated Salary: 50000"""
new_prediction = classifier.predict(
sc.transform(np.array([[0.0, 0, 600, 1, 40, 3, 60000, 2, 1, 1, 50000]])))
new_prediction = (new_prediction > 0.5)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
#confusion matric which consists of diagonal of elements of right and wrong predictions
cm = confusion_matrix(y_test, y_pred)
print(cm)
backend.clear_session()
#Saving the weights
fname = "weights-ann.hdf5"
classifier.save_weights(fname, overwrite=True)
#loading the weights
fname = "weights-ann.hdf5"
classifier.load_weights(fname)
class_mode='binary')
# Create a loss history
history = LossHistory()
classifier.fit_generator(training_set,
steps_per_epoch=8000 / batch_size,
epochs=90,
validation_data=test_set,
validation_steps=2000 / batch_size,
workers=12,
max_q_size=100,
callbacks=[history])
# serialize model to JSON
model_json = classifier.to_json()
with open("catordog.json", "w") as json_file:
json_file.write(model_json)
# serialize weights to HDF5
classifier.save_weights("catordog.h5")
print("Saved model to disk")
# Save loss history to file
loss_history_path = os.path.join(script_dir, 'loss_history.log')
myFile = open(loss_history_path, 'w+')
myFile.write(history.losses)
myFile.close()
backend.clear_session()
print("The model class indices are:", training_set.class_indices)
class Model(object):
def __init__(self):
self.model = Sequential()
self.model.add(
Conv2D(32, (3, 3), input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)))
self.model.add(Activation('relu'))
self.model.add(MaxPooling2D(pool_size=(2, 2)))
self.model.add(Conv2D(32, (3, 3)))
self.model.add(Activation('relu'))
self.model.add(MaxPooling2D(pool_size=(2, 2)))
self.model.add(Conv2D(64, (3, 3)))
self.model.add(Activation('relu'))
self.model.add(MaxPooling2D(pool_size=(2, 2)))
self.model.add(Flatten())
self.model.add(Dense(64))
self.model.add(Activation('relu'))
self.model.add(Dropout(0.5))
self.model.add(Dense(1))
self.model.add(Activation('sigmoid'))
def train(self, dataset, batch_size=batch_size, nb_epoch=epochs):
self.model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
self.model.fit_generator(
dataset.train,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=dataset.valid,
validation_steps=nb_validation_samples // batch_size)
def save(self, file_path=FILE_PATH):
print('Model Saved.')
self.model.save_weights(file_path)
def load(self, file_path=FILE_PATH):
print('Model Loaded.')
self.model.load_weights(file_path)
def predict(self, image):
# 预测样本分类
img = image.resize((1, IMAGE_SIZE, IMAGE_SIZE, 3))
img = image.astype('float32')
img /= 255
#归一化
result = self.model.predict(img)
print(result)
# 概率
result = self.model.predict_classes(img)
print(result)
# 0/1
return result[0]
def evaluate(self, dataset):
# 测试样本准确率
score = self.model.evaluate_generator(dataset.valid, steps=2)
print("样本准确率%s: %.2f%%" %
(self.model.metrics_names[1], score[1] * 100))
class TinyYoloV2:
"""
This class handles the building and the loss of the
tiny yolo v2 network.
"""
def __init__(self, config):
"""
Initializes class variables.
:param config: Contains the networks hyperparameters
"""
#super.__init__(self)
self.config = config
self.network = None
self.loss = None
self.input_shape = config.input_shape
def build(self):
"""
Builds the tiny yolo v2 network.
:param input: input image batch to the network
:return: logits output from network
"""
self.model = Sequential()
self.model.add(Convolution2D(16, (3, 3), input_shape=(416, 416, 3), padding='same'))
self.model.add(LeakyReLU())
self.model.add(BatchNormalization())
self.model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='valid'))
self.model.add(Convolution2D(32, (3, 3), padding='same'))
self.model.add(LeakyReLU())
self.model.add(BatchNormalization())
self.model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='valid'))
self.model.add(Convolution2D(64, (3, 3), padding='same'))
self.model.add(LeakyReLU())
self.model.add(BatchNormalization())
self.model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='valid'))
self.model.add(Convolution2D(128, (3, 3), padding='same'))
self.model.add(LeakyReLU())
self.model.add(BatchNormalization())
self.model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='valid'))
self.model.add(Convolution2D(256, (3, 3), padding='same'))
self.model.add(LeakyReLU())
self.model.add(BatchNormalization())
self.model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='valid'))
self.model.add(Convolution2D(512, (3, 3), padding='same'))
self.model.add(LeakyReLU())
self.model.add(BatchNormalization())
self.model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 1), padding='valid'))
self.model.add(Convolution2D(1024, (3, 3), padding='same'))
self.model.add(LeakyReLU())
self.model.add(BatchNormalization())
self.model.add(Convolution2D(1024, (3, 3), padding='same'))
self.model.add(LeakyReLU())
self.model.add(BatchNormalization())
self.model.add(Convolution2D(125, (1, 1), activation=None))
if self.config.optimizer == 'adam':
opt = Adam()
elif self.config.optimizer == 'sgd':
opt = SGD()
if self.config.loss == 'categorical_crossentropy':
loss = 'categorical_crossentropy'
elif self.config.loss == 'yolov2_loss':
raise NotImplemented
self.model.compile(loss=loss, optimizer=opt, metrics=['accuracy'])
self.model.summary()
return self.model
def convertToBoxParams(self, out):
"""
Convert the final layer features to bounding box parameters.
:return: box_xy: tensor
x, y box predictions adjusted by spatial location in conv layer
box_wh: tensor
w, h box predictions adjusted by anchors and conv spatial resolution
box_conf: tensor
Probability estimate for whether each box contains any object
box_class_pred : tensor
Probability distribution estimate for each box over class labels
"""
feats = out
num_anchors = len(self.config.anchors)
# Reshape to batch, height, width, num_anchors, box_params
anchors_tensor = K.reshape(K.variable(self.config.anchors), [1, 1, 1, num_anchors, 2])
conv_dims = K.shape(feats)[1:3] # assuming channels last
# In YOLO the height index is the inner most iteration
conv_height_index = K.arange(0, stop=conv_dims[0])
conv_width_index = K.arange(0, stop=conv_dims[1])
conv_height_index = K.tile(conv_height_index, [conv_dims[1]])
conv_width_index = K.tile(
K.expand_dims(conv_width_index, 0), [conv_dims[0], 1])
conv_width_index = K.flatten(K.transpose(conv_width_index))
conv_index = K.transpose(K.stack([conv_height_index, conv_width_index]))
conv_index = K.reshape(conv_index, [1, conv_dims[0], conv_dims[1], 1, 2])
conv_index = K.cast(conv_index, K.dtype(feats))
feats = K.reshape(
feats, [-1, conv_dims[0], conv_dims[1], num_anchors, self.config.classes + 5])
conv_dims = K.cast(K.reshape(conv_dims, [1, 1, 1, 1, 2]), K.dtype(feats))
# Static generation of conv_index:
# conv_index = np.array([_ for _ in np.ndindex(conv_width, conv_height)])
# conv_index = conv_index[:, [1, 0]] # swap columns for YOLO ordering.
# conv_index = K.variable(
# conv_index.reshape(1, conv_height, conv_width, 1, 2))
# feats = Reshape(
# (conv_dims[0], conv_dims[1], num_anchors, num_classes + 5))(feats)
box_xy = K.sigmoid(feats[..., :2])
box_wh = K.exp(feats[..., 2:4])
box_confidence = K.sigmoid(feats[..., 4:5])
box_class_probs = K.softmax(feats[..., 5:])
# Adjust preditions to each spatial grid point and anchor size.
# Note: YOLO iterates over height index before width index.
box_xy = (box_xy + conv_index) / conv_dims
box_wh = box_wh * anchors_tensor / conv_dims
return box_xy, box_wh, box_confidence, box_class_probs
def save_model(self, name):
"""
Saves model to path.
:return:
"""
path = "C:\ObjectDetection\Data\ModelCheckpoints" + name + ".h5"
self.model.save(path)
def save_weights(self, name):
"""
Saves the model weights to path.
:param name:
:return:
"""
path = "C:\ObjectDetection\Data\ModelCheckpoints" + name + ".h5"
self.model.save_weights(path)
def load_weights(self):
print("About to load weights.")
utils.load_weights(self.model, 'C:\\ObjectDetection\\Data\\ModelCheckpoints\\tiny-yolo-voc.weights')
print("Loaded weights.")
def _load_pretrained_network(self):
"""
Loads the pretrained network's weights
into the new network.
:return:
"""
raise NotImplemented
