我是张量流和语义分割的新手。
我正在设计一个用于语义分割的U-Net。每个图像都有一个我要分类的对象。但是总的来说,我有10个不同对象的图像。我很困惑,我该如何准备口罩输入?是将其视为多标签细分还是仅用于一类?
我应该将输入转换为一种热编码吗?我应该使用to_categorical吗?我发现可以进行多类别细分,但我不知道,如果是这种情况。因为在一张图像中,我只有一个对象要检测/分类。
我尝试使用它作为输入代码。但是我不确定,我在做什么对与错。
#Generation of batches of image and mask
class DataGen(keras.utils.Sequence):
def __init__(self, image_names, path, batch_size, image_size=128):
self.image_names = image_names
self.path = path
self.batch_size = batch_size
self.image_size = image_size
def __load__(self, image_name):
# Path
image_path = os.path.join(self.path, "images/aug_test", image_name) + ".png"
mask_path = os.path.join(self.path, "masks/aug_test",image_name) + ".png"
# Reading Image
image = cv2.imread(image_path, 1)
image = cv2.resize(image, (self.image_size, self.image_size))
# Reading Mask
mask = cv2.imread(mask_path, -1)
mask = cv2.resize(mask, (self.image_size, self.image_size))
## Normalizaing
image = image/255.0
mask = mask/255.0
return image, mask
def __getitem__(self, index):
if(index+1)*self.batch_size > len(self.image_names):
self.batch_size = len(self.image_names) - index*self.batch_size
image_batch = self.image_names[index*self.batch_size : (index+1)*self.batch_size]
image = []
mask = []
for image_name in image_batch:
_img, _mask = self.__load__(image_name)
image.append(_img)
mask.append(_mask)
#This is where I am defining my input
image = np.array(image)
mask = np.array(mask)
mask = tf.keras.utils.to_categorical(mask, num_classes=10, dtype='float32') #Is this true?
return image, mask
def __len__(self):
return int(np.ceil(len(self.image_names)/float(self.batch_size)))
这是真的吗?如果是这样,那么要获得标签/类作为输出,我应该在输入中进行哪些更改?我应该根据班级更改口罩的像素值吗?
这是我的U-Net架构。
# Convolution and deconvolution Blocks
def down_scaling_block(x, filters, kernel_size=(3, 3), padding="same", strides=1):
conv = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(x)
conv = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(conv)
pool = keras.layers.MaxPool2D((2, 2), (2, 2))(conv)
return conv, pool
def up_scaling_block(x, skip, filters, kernel_size=(3, 3), padding="same", strides=1):
conv_t = keras.layers.UpSampling2D((2, 2))(x)
concat = keras.layers.Concatenate()([conv_t, skip])
conv = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(concat)
conv = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(conv)
return conv
def bottleneck(x, filters, kernel_size=(3, 3), padding="same", strides=1):
conv = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(x)
conv = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(conv)
return conv
def UNet():
filters = [16, 32, 64, 128, 256]
inputs = keras.layers.Input((image_size, image_size, 3))
'''inputs2 = keras.layers.Input((image_size, image_size, 1))
conv1_2, pool1_2 = down_scaling_block(inputs2, filters[0])'''
Input = inputs
conv1, pool1 = down_scaling_block(Input, filters[0])
conv2, pool2 = down_scaling_block(pool1, filters[1])
conv3, pool3 = down_scaling_block(pool2, filters[2])
'''conv3 = keras.layers.Conv2D(filters[2], kernel_size=(3,3), padding="same", strides=1, activation="relu")(pool2)
conv3 = keras.layers.Conv2D(filters[2], kernel_size=(3,3), padding="same", strides=1, activation="relu")(conv3)
drop3 = keras.layers.Dropout(0.5)(conv3)
pool3 = keras.layers.MaxPooling2D((2,2), (2,2))(drop3)'''
conv4, pool4 = down_scaling_block(pool3, filters[3])
bn = bottleneck(pool4, filters[4])
deConv1 = up_scaling_block(bn, conv4, filters[3]) #8 -> 16
deConv2 = up_scaling_block(deConv1, conv3, filters[2]) #16 -> 32
deConv3 = up_scaling_block(deConv2, conv2, filters[1]) #32 -> 64
deConv4 = up_scaling_block(deConv3, conv1, filters[0]) #64 -> 128
outputs = keras.layers.Conv2D(10, (1, 1), padding="same", activation="softmax")(deConv4)
model = keras.models.Model(inputs, outputs)
return model
model = UNet()
model.compile(optimizer='adam', loss="categorical_crossentropy", metrics=["acc"])
train_gen = DataGen(train_img, train_path, image_size=image_size, batch_size=batch_size)
valid_gen = DataGen(valid_img, train_path, image_size=image_size, batch_size=batch_size)
test_gen = DataGen(test_img, test_path, image_size=image_size, batch_size=batch_size)
train_steps = len(train_img)//batch_size
valid_steps = len(valid_img)//batch_size
model.fit_generator(train_gen, validation_data=valid_gen, steps_per_epoch=train_steps, validation_steps=valid_steps,
epochs=epochs)
我希望我能正确解释我的问题。任何帮助!
更新:我根据对象类更改了遮罩中每个像素的值。 (如果图像包含要分类为对象2的对象,则将蒙版像素的值更改为2。整个蒙版数组将包含0(bg)和2(object)。因此,对于每个对象,掩码将包含0和3、0和10等)
在这里,我首先将掩码更改为二进制,然后如果pixel的值大于1,则将其更改为1或2或3(根据对象/类号)
然后,如代码所示,将它们转换为具有to_categorical的one_hot。进行培训,但网络没有学到任何东西。精度和损耗会在两个值之间波动。我这是什么错我在生成蒙版(更改像素值?)时出错吗?还是在函数to_categorical上出错了?
发现的问题: 我在创建蒙版时出错。.我正在用cv2读取图像,将图像读取为heightxwidth ..在考虑将我的图像尺寸为widthxheight之后,我正在根据类创建具有像素值的蒙版。网络什么也没学。.它现在正在工作..
答案 0 :(得分:1)
每个图像都有一个我要分类的对象。但是总的来说,我有10个不同对象的图像。我很困惑,我该如何准备口罩输入?是将其视为多标签细分还是仅用于一类?
如果您的数据集具有N个不同的标签(即:0-背景,1-狗,2-猫...),即使您的图像仅包含一种对象,也会遇到多类问题。
我应该将输入转换为一种热编码吗?我应该使用to_categorical吗?
是的,您应该对标签进行一次热编码。使用to_categorical可以归结为标签的源格式。假设您有N个类别,且标签为(高度,宽度,1),其中每个像素的值在[0,N]范围内。在这种情况下, keras.utils.to_categorical(label,N)将提供一个float(height,width,N)标签,其中每个像素为0或1。您不必除以255。
如果您的源格式不同,则可能必须使用自定义函数来获取相同的输出格式。
查看此仓库(不是我的工作):keras-unet。 Notebooks文件夹包含两个示例,可以在小型数据集上训练u-net。它们不是多类的,但是很容易逐步使用您自己的数据集。通过将标签加载为:来加注星标
im = Image.open(mask).resize((512,512))
im = to_categorical(im,NCLASSES)
像这样重塑和标准化:
x = np.asarray(imgs_np, dtype=np.float32)/255
y = np.asarray(masks_np, dtype=np.float32)
y = y.reshape(y.shape[0], y.shape[1], y.shape[2], NCLASSES)
x = x.reshape(x.shape[0], x.shape[1], x.shape[2], 3)
使模型适应NCLASSES
model = custom_unet(
input_shape,
use_batch_norm=False,
num_classes=NCLASSES,
filters=64,
dropout=0.2,
output_activation='softmax')
选择正确的损失:
from keras.losses import categorical_crossentropy
model.compile(
optimizer=SGD(lr=0.01, momentum=0.99),
loss='categorical_crossentropy',
metrics=[iou, iou_thresholded])
希望有帮助