def Scaling(path, image_save_dir, aug_number):
datagen = ImageDataGenerator(zoom_range=0.3, fill_mode='constant') # 0.3
img = load_img(path, grayscale=True) # 这是一个PIL图像
x = img_to_array(img) # 把PIL图像转换成一个numpy数组
x = x.reshape((1, ) + x.shape) # 这是一个numpy数组
image_dir = os.path.dirname(path)
image_name = os.path.basename(path)
prefix = image_name.split(".")[0]
i = 1
for batch in datagen.flow(x,
batch_size=1,
save_to_dir=image_save_dir,
save_prefix=prefix + "_aug_" + 'Scal',
save_format='jpg'):
i += 1
if i > aug_number:
break # 否则生成器会退出循环
def Random_translation(path, image_save_dir, aug_number):
datagen = ImageDataGenerator(width_shift_range=0.05,
height_shift_range=0.05) # 0.2
img = load_img(path, grayscale=True) # 这是一个PIL图像
x = img_to_array(img) # 把PIL图像转换成一个numpy数组
x = x.reshape((1, ) + x.shape) # 这是一个numpy数组
image_dir = os.path.dirname(path)
image_name = os.path.basename(path)
prefix = image_name.split(".")[0]
i = 1
for batch in datagen.flow(x,
batch_size=1,
save_to_dir=image_save_dir,
save_prefix=prefix + "_aug_" + 'trans',
save_format='jpg'):
i += 1
if i > aug_number:
break # 否则生成器会退出循环
def Random_affine_transform(path, image_save_dir, aug_number):
datagen = ImageDataGenerator(
shear_range=3) # 水平或垂直投影变换,shear_range是角度范围 #5
img = load_img(path, grayscale=True) # 这是一个PIL图像
x = img_to_array(img) # 把PIL图像转换成一个numpy数组
x = x.reshape((1, ) + x.shape) # 这是一个numpy数组
image_dir = os.path.dirname(path)
image_name = os.path.basename(path)
prefix = image_name.split(".")[0]
i = 1
for batch in datagen.flow(x,
batch_size=1,
save_to_dir=image_save_dir,
save_prefix=prefix + "_aug_" + 'aff',
save_format='jpg'):
i += 1
if i > aug_number:
break # 否则生成器会退出循环
height_shift_range=
0.1, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=False,
zerosquare=True,
zerosquareh=noises,
zerosquarew=noises,
zerosquareintern=0.0) # randomly flip images
# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(X_train)
# fit the model on the batches generated by datagen.flow()
if weighted:
model.fit_generator(datagen.flow(X_train,
Y_train,
batch_size=batch_size),
samples_per_epoch=X_train.shape[0],
nb_epoch=nb_epoch,
validation_data=(X_test, Y_test),
callbacks=callbacks_list,
class_weight=[weights[0], weights[1]])
else:
print(Y_train.shape)
model.fit_generator(datagen.flow(X_train,
Y_train,
batch_size=batch_size),
samples_per_epoch=X_train.shape[0],
nb_epoch=nb_epoch,
validation_data=(X_test, Y_test),
callbacks=callbacks_list)
reduce_lr = ReduceLROnPlateau(monitor='val_f1_score',
factor=np.sqrt(0.1),
patience=reduce_lr_patience,
verbose=2,
mode='max',
cooldown=1)
model.compile(loss=losses[loss_name],
optimizer=opt,
metrics=[f1_score, precision, recall])
# Start fitting model
fold = 50
epoch = 1e4
print(" Fine tune " + model_name + ": \n")
model.fit_generator(datagen.flow(x_train,
'../data/train_data',
width,
y_train,
batch_size=batch_size),
steps_per_epoch=len(x_train) / batch_size / fold,
validation_data=val_datagen.flow(
x_val,
'../data/val_data',
width,
y_val,
batch_size=batch_size),
validation_steps=len(x_val) / batch_size,
epochs=epoch,
callbacks=[early_stopping, reduce_lr, checkpointer],
workers=4)
patience = 5 # reduce_lr_patience+1 + 1
early_stopping = EarlyStopping(
monitor='val_f1_score', patience=patience, verbose=2, mode='max')
checkpointer = ModelCheckpoint(
filepath=f'../models/{model_name}_{loss_name}.h5',
monitor='val_f1_score', verbose=0, mode='max', save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_f1_score',
factor=np.sqrt(0.1),
patience=reduce_lr_patience,
verbose=2, mode='max', cooldown=1)
model.compile(
loss=losses[loss_name],
optimizer=opt,
metrics=[f1_score, precision, recall])
# Start fitting model
batch_size = 16
fold = 50
epoch = 1e4
print(" Fine tune " + model_name + ": \n")
model.fit_generator(
datagen.flow(x_train, '../data/train_data', width,
y_train, batch_size=batch_size),
steps_per_epoch=len(x_train) / batch_size / fold,
validation_data=val_datagen.flow(
x_val, '../data/val_data', width, y_val, batch_size=batch_size),
validation_steps=len(x_val) / batch_size,
epochs=epoch,
callbacks=[early_stopping, reduce_lr, checkpointer],
workers=4)
batch_y = y_val
for i, j in enumerate(tqdm(index_array)):
s_img = cv2.imread(f'../data/val_data/{j+1}.jpg')
b, g, r = cv2.split(s_img) # get b,g,r
rgb_img = cv2.merge([r, g, b]) # switch it to rgb
x = resizeAndPad(rgb_img, (width, width))
batch_x[i] = x
model_names = ['Xception_f1_59', 'Xception_f1_5945']
for model_name in model_names:
with CustomObjectScope({
'f1_loss': f1_loss,
'f1_score': f1_score,
'precision': precision,
'recall': recall
}):
model = load_model(f'../models/{model_name}.h5')
# y_pred_val = model.predict(batch_x, verbose=1)
# print(model_name, f1_score(y_val, y_pred_val))
val_datagen = ImageDataGenerator(preprocessing_function=preprocess_input)
y_pred_val = model.predict_generator(val_datagen.flow(x_val,
'../data/val_data',
width,
y_val,
batch_size=3,
shuffle=False),
verbose=1)
print(model_name, f1_score_np(y_val, y_pred_val))
data['imageId'] = data['imageId'].astype(np.uint32)
mlb = MultiLabelBinarizer()
train_label = mlb.fit_transform(train['labelId'])
y_test = np.zeros((39706, 228))
x_test = np.arange(y_test.shape[0]) + 1
width = 224
model_name = 'Xception'
# with CustomObjectScope({'f1_loss': f1_loss, 'f1_score': f1_score, 'precision': precision, 'recall': recall}):
# model = load_model(f'../models/{model_name}_f1.h5')
test_datagen = ImageDataGenerator(preprocessing_function=preprocess_input)
y_pred_test = model.predict_generator(test_datagen.flow(x_test,
'../data/test_data',
width,
y_test,
batch_size=1,
shuffle=False),
verbose=1)
np.save(f'../data/json/y_pred_{model_name}', y_pred_test)
# y_pred_test_xe = y_pred_test.copy()
# y_pred_test = (y_pred_test_xe + y_pred_test_in) / 2
y_pred_test1 = np.round(y_pred_test)
where_1 = mlb.inverse_transform(y_pred_test1)
file = open('../data/json/test.csv', 'w')
file.write('image_id,label_id\n')
for i in x_test:
where_one = where_1[i - 1]