Unet源码+keras2.24+python 3.6.5

2019-09-01 19:41:05 阅读：307 来源： 互联网

标签：python activation same padding keras2.24 源码 import model Conv2D

from keras.models import Model
import keras
from keras.utils import plot_model
from keras.layers import Activation, Dropout, UpSampling2D, concatenate, Input
from keras.layers import Conv2DTranspose, Conv2D, MaxPooling2D
from PIL import Image
import numpy as np
import pickle
import cv2
import os
import tensorflow as tf
from keras import layers
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
from keras.models import load_model

Import necessary items from Keras

from keras.layers.normalization import BatchNormalization
from keras.preprocessing.image import ImageDataGenerator

from keras import regularizers
from keras import optimizers
import matplotlib.pyplot as plt
import keras.backend as K

from keras.optimizers import Adam
from keras.optimizers import SGD
from keras.layers import Dense,AveragePooling2D,ZeroPadding2D
from keras.layers import add,Flatten
from tensorflow.keras.callbacks import TensorBoard
import time
img_rows=80
img_cols=160
########################
def training_vis(hist):
loss = hist.history[‘loss’]
val_loss = hist.history[‘val_loss’]
acc = hist.history[‘acc’]
val_acc = hist.history[‘val_acc’]

# make a figure
fig = plt.figure(figsize=(8,4))
# subplot loss
ax1 = fig.add_subplot(121)
ax1.plot(loss,label='train_loss')
ax1.plot(val_loss,label='val_loss')
ax1.set_xlabel('Epochs')
ax1.set_ylabel('Loss')
ax1.set_title('Loss on Training and Validation Data')
ax1.legend()
# subplot acc
ax2 = fig.add_subplot(122)
ax2.plot(acc,label='train_acc')
ax2.plot(val_acc,label='val_acc')
ax2.set_xlabel('Epochs')
ax2.set_ylabel('Accuracy')
ax2.set_title('Accuracy  on Training and Validation Data')
ax2.legend()
plt.tight_layout()

log_filepath=’’#tensorboard路径文件
model_name = “resunet-cnn-64x2-{}”.format(int(time.time()))
tensorboard = TensorBoard(log_dir=log_filepath.format(model_name))

train_images=[]
labels=[]
#loading data
path=#训练图片路径
for imag in os.listdir(path):
str=path+imag
lab=cv2.imread(str)
y = cv2.cvtColor(lab, cv2.COLOR_RGB2GRAY).reshape(80,160,1)

labels.append(y)

for imag in os.listdir('path):
str=path+imag
img=cv2.imread(str).reshape(80,160,3)

train_images.append(img)

if len(labels)==len(train_images):
print(‘data load success’)
else:
print(‘data load filed’)

Make into arrays as the neural network wants these

train_images = np.array(train_images)
labels = np.array(labels)
print(‘label:’,labels[0].shape)
print(‘image:’,train_images[0].shape)

Normalize labels - training images get normalized to start in the network

labels = labels /50.
#255

Shuffle images along with their labels, then split into training/validation sets

train_images, labels = shuffle(train_images, labels)

Test size may be 10% or 20%

X_train, X_val, y_train, y_val = train_test_split(train_images, labels, test_size=0.2)

Batch size, epochs and pool size below are all paramaters to fiddle with for optimization

batch_size =16# 16
epochs =200

Here is the actual neural network

Normalizes incoming inputs. First layer needs the input shape to work

#BatchNormalization(input_shape=input_shape)
inputs = Input(batch_shape=(None, 80, 160, 3))

#################
def get_unet(inputs):

conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(inputs)
conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
# pool1 = Dropout(0.25)(pool1)
pool1 = BatchNormalization()(pool1)


conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(pool1)
conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
# pool2 = Dropout(0.5)(pool2)
pool2 = BatchNormalization()(pool2)


conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(pool2)
conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
# pool3 = Dropout(0.5)(pool3)
pool3 = BatchNormalization()(pool3)


conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(pool3)
conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
# pool4 = Dropout(0.5)(pool4)
pool4 = BatchNormalization()(pool4)


conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(pool4)
conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(conv5)


up6 = concatenate([Conv2DTranspose(256, (2, 2), strides=(
    2, 2), padding='same')(conv5), conv4], axis=3)
# up6 = Dropout(0.5)(up6)
up6 = BatchNormalization()(up6)
conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(up6)
conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv6)


up7 = concatenate([Conv2DTranspose(128, (2, 2), strides=(
    2, 2), padding='same')(conv6), conv3], axis=3)
# up7 = Dropout(0.5)(up7)
up7 = BatchNormalization()(up7)
conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(up7)
conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv7)

up8 = concatenate([Conv2DTranspose(64, (2, 2), strides=(
    2, 2), padding='same')(conv7), conv2], axis=3)
# up8 = Dropout(0.5)(up8)
up8 = BatchNormalization()(up8)
conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(up8)
conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv8)

up9 = concatenate([Conv2DTranspose(32, (2, 2), strides=(
    2, 2), padding='same')(conv8), conv1], axis=3)
# up9 = Dropout(0.5)(up9)
up9 = BatchNormalization()(up9)
conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(up9)
conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv9)

# conv9 = Dropout(0.5)(conv9)

conv10 = Conv2D(1, (1, 1), activation='sigmoid')(conv9)

model = Model(inputs=[inputs], outputs=[conv10])

#model.compile(optimizer=Adam(lr=1e-5),
#              loss=dice_coef_loss, metrics=[dice_coef])
model.compile(optimizer='Adam', loss='mean_squared_error',metrics=['accuracy'])
model.summary()
#plot_model(model, to_file='unet.png')
return model

inputs = Input(batch_shape=(None, 80, 160, 3))
datagen = ImageDataGenerator(channel_shift_range=0.2)
datagen.fit(X_train)

Freeze layers since training is done

model=get_unet(inputs)
#weight_file = # 保存/加载地址
#model = load_model(weight_file) # 载入已保存的模型文件

hist=model.fit_generator(datagen.flow(X_train, y_train, batch_size=batch_size), steps_per_epoch=len(X_train)/batch_size,
epochs=epochs, verbose=1, validation_data=(X_val, y_val), callbacks=[tensorboard])

#model.compile(loss=‘mean_squared_error’, optimizer=sgd)
model.compile(optimizer=‘Adam’, loss=‘mean_squared_error’, metrics=[‘accuracy’])

Save model architecture and weights

model.save(‘.h5’)#模型保存路径
training_vis(hist)

标签：python,activation,same,padding,keras2.24,源码,import,model,Conv2D
来源： https://blog.csdn.net/u011914647/article/details/100186588

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。

ICode9