def aug_method():
# 增强方法1: 图片变形
# 1) 水平翻转: 最常用!! 对卷积神经网络而言, 左右互换(水平翻转)差异很大
aug = image.HorizontalFlipAug(0.5)
apply(img, aug)
plt.gcf().suptitle('HorizontialFlipAug')
plt.show()
# 2) 随机裁剪: 卷积神经网络对位置敏感, 虽然Pool池化可以减小位置敏感, 但仍不不够
# 2.1) 裁剪指定(width x height) 的图片
aug = image.RandomCropAug((200, 200))
apply(img, aug)
plt.show()
# 2.2) 裁剪指定'长宽比'范围大小且不小于最小值的随机图片, 并resize为指定(width x height)大小
aug = image.RandomSizedCropAug(size=(100, 100),
min_area=.1,
ratio=(0.5, 2.0))
apply(img, aug)
plt.show()
# 增强方法2: 颜色变化
# 1) 亮度变化:
aug = image.BrightnessJitterAug(
brightness=0.5
) # brightness : The brightness jitter ratio range, [0, 1]
apply(img, aug)
plt.show()
# 2) 色调变化:
aug = image.HueJitterAug(hue=0.5)
apply(img, aug)
plt.show()
def augment_data(imags, label):
datas, labels = [], []
n = imags.shape[0]
for k in range(n):
imag = imags[k].reshape(shape=(1, imags[k].shape[0], imags[k].shape[1],
imags[k].shape[2]))
for i in range(4):
trans_band = transform(
imag, image.HorizontalFlipAug(.5)).astype('float32')
datas.append(img_norm(trans_band))
labels.append(label[k].asscalar())
for i in range(9):
trans_band = transform(
imag, image.RandomSizedCropAug((75, 75), .75,
(.8, 1.2))).astype('float32')
datas.append(img_norm(trans_band))
labels.append(label[k].asscalar())
# brightness augmenter
for i in range(9):
trans_band = transform(
imag, image.BrightnessJitterAug(.1)).astype('float32')
datas.append(img_norm(trans_band))
labels.append(label[k].asscalar())
# random crop augmenter
for i in range(9):
trans_band = resize(transform(imag, image.RandomCropAug((50, 50))),
75).astype('float32')
datas.append(img_norm(trans_band))
labels.append(label[k].asscalar())
# center crop augmenter
trans_band = resize(transform(imag, image.CenterCropAug((50, 50))),
75).astype('float32')
datas.append(img_norm(trans_band))
labels.append(label[k].asscalar())
ds = nd.concat(*datas, dim=0)
return ds, labels
pretrained_net = mobilenet1_0(pretrained=True)
print(pretrained_net)
print("classes: " + str(len(training_map)))
net = mobilenet1_0(classes=len(training_map))
from mxnet import init
net.features = pretrained_net.features
net.output.initialize(init.Xavier())
from mxnet.image import color_normalize
from mxnet import image
train_augs = [
image.HorizontalFlipAug(0.5),
image.BrightnessJitterAug(.3),
image.HueJitterAug(.1)
]
test_augs = [image.ResizeAug(224), image.CenterCropAug((224, 224))]
def transform(data, label, augs):
data = data.astype('float32')
for aug in augs:
data = aug(data)
data = nd.transpose(data, (2, 0, 1))
return data, nd.array([label]).asscalar().astype('float32')
from mxnet.gluon.data.vision import ImageRecordDataset
X = [aug(img.astype('float32')) for _ in range(n * n)]
Y = nd.stack(*X).clip(0, 255) / 255
utils.show_images(Y, n, n, figsize=(256, 256))
# 水平翻转
aug = image.HorizontalFlipAug(.5)
apply(img, aug)
# 随机裁剪一个块, 256 * 256
aug = image.RandomCropAug([256, 256])
apply(img, aug)
# 颜色变化
# 随机将亮度增加或减少一个量
aug = image.BrightnessJitterAug(.5)
apply(img, aug)
# 随机色调变化
aug = image.HueJitterAug(.5)
apply(img, aug)
def apply_aug_list(img, augs):
for aug in augs:
img = aug(img)
return img
train_augs = [image.HorizontalFlipAug(.5), image.RandomCropAug((28, 28))]
from mxnet import image
from mxnet import init
from mxnet import gluon
import time
from mxnet import autograd
from mxnet import nd
from mxnet.gluon.data.vision import ImageRecordDataset
# Global constants ----
ctx = mx.cpu()
train_augs = [
image.ResizeAug(224),
image.HorizontalFlipAug(0.5), # flip the image horizontally
image.BrightnessJitterAug(.3), # randomly change the brightness
image.HueJitterAug(.1) # randomly change hue
]
test_augs = [
image.ResizeAug(224)
]
# Functions ----
def transform(data, label, augs):
# applies augmentations to img data
data = data.astype('float32')
for aug in augs:
data = aug(data)
data = nd.transpose(data, (2,0,1))
return data, nd.array([label]).asscalar().astype('float32')
for i in range(nrows):
for j in range(ncols):
figs[i][j].imshow(imgs[i * ncols + j].asnumpy())
figs[i][j].axes.get_xaxis().set_visible(False)
figs[i][j].axes.get_yaxis().set_visible(False)
plt.show()
self.__X = [
aug(self.__img.astype("float32"))
for _ in range(self.__n * self.__n)
]
self.__Y = nd.stack(*self.__X).clip(0, 255) / 255
show_images(self.__Y, self.__n, self.__n, figsize=(8, 8))
if __name__ == "__main__":
ia = IamgeAugment(input_path="cat.jpg", n=3)
# 变形
# 50% 几率水平翻转图片
ia.apply(aug=image.HorizontalFlipAug(.5))
# 剪裁
# 随机从原图片剪裁出 200×200 的一部分 , 可以图片先变大在剪小
ia.apply(aug=image.RandomCropAug([200, 200]))
# 随机从图片中剪裁一个区域要求是剪裁面积占原图片 >= 0.1 且剪裁的区域长/宽在 0.5~2 之间后将剪裁后的图片放缩到 200×200
ia.apply(aug=image.RandomSizedCropAug((200, 200), .1, (.5, 2)))
# 色调
# 随机将亮度增加或者减小在 0-50% 间的一个量
ia.apply(aug=image.BrightnessJitterAug(.5))
# 随机色调变化
ia.apply(aug=image.HueJitterAug(.5))
