使用GPU 訓練Tensorflow/Keras 的CNN模型
關鍵詞：Kaggle 貓狗大賽，MX510 GPU， 聯想潮7000， Win10， NVIDA顯卡python
以前寫了一個貓狗識別的CNN模型，利用筆記本進行訓練，每次都須要很久，基本每一個epoch要5分鐘左右，來來回回改改參數，每次都要等漫長的時間。因而在找怎麼利用GPU進行訓練。json
1. 電腦的顯卡是NVIDA MX510， 能夠支持CUDA，要使用tensorflow-gpu版本，須要安裝CUDA9.0，下載以後直接安裝，可能有2個patch能夠下載，可是patch 1裝不上，patch 2 能夠，不影響。app
2. 下載cuDNN並安裝，須要註冊一下，下載後解壓，將文件複製到CUDA的安裝目錄。dom
這是cuDNN解壓後的文件ide
複製到這裏函數
3. 能夠測試一下CUDA是否安裝成功測試
進入這個文件夾，運行這兩個程序優化
若是結果是pass, 則暗轉成功。debug
4. 安裝tensorflow-gpu， 直接使用pip install tensorflow-gpu3d
5. 安裝keras，pip install keras
6. 在開始訓練模型時，keras會自動檢測是否有可用的GPU
使用以下的腳原本測試一下
import os
#os.environ['CUDA_VISIBLE_DEVICES'] = "0" # 使用第幾個GPU， 0是第一個
import tensorflow as tf
import numpy as np
hello=tf.constant('hhh')
sess=tf.Session()
print (sess.run(hello))結果以下，說明已經能夠正常使用GPU訓練模型了。
7. 利用kaggle的貓狗圖片訓練能夠識別貓狗的CNN模型
# -*- coding: utf-8 -*-
"""
Created on Thu May 3 22:52:05 2018
@author: xiaozhe
"""
import os
from keras.models import Sequential
from keras.optimizers import Adam, SGD
from keras.layers import Dense, Activation, Flatten, Dropout
from keras.layers import Conv2D, MaxPooling2D
import logging
from resize_pic import generate_data, load_data
from sklearn.model_selection import train_test_split
import numpy as np
from keras.models import model_from_yaml, load_model, model_from_json
from matplotlib import pyplot as plt
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s-%(message)s')
path = os.path.join(os.getcwd(), 'train')
# test_data, test_labels = generate_data(path, 100)
test_data, test_labels = load_data('./train', (128, 128), 100)
test_data /= 255
images, labels = load_data(path, (128, 128), 10000)
images /= 255
x_train, x_test, y_train, y_test = train_test_split(
images, labels, test_size=0.2)
model = Sequential()
# the first convolution layer
model.add(Conv2D(filters=32,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu',
input_shape=(128, 128, 3),
padding='same',
data_format="channels_last"))
#model.add(Conv2D(filters=32,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu',
padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# the second convolution layer
model.add(Conv2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu',
padding='same'))
#model.add(Conv2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu',
padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# the third convolution layer
model.add(Conv2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu',
padding='same'))
#model.add(Conv2D(filters=128,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu',
padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# the output layer
model.add(Flatten())
model.add(Dense(100, activation='relu'))
#model.add(Dense(128, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.summary()
sgd = Adam(lr=0.001)
model.compile(loss='binary_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
model.fit(x_train, y_train,
epochs=15, batch_size=100, verbose=1,
validation_data=(x_test, y_test))
predict_value = model.predict(test_data, verbose=1)
animals = np.array(['cat', 'dog'])
accurate = 0
for i in range(len(predict_value)):
predict_temp = 0
if predict_value[i, 0] > 0.5:
predict_temp = 1
if animals[predict_temp] == animals[test_labels[i, 0]]:
accurate += 1
# plt.imshow(test_data[i].astype(int))
print('predict: ', animals[predict_temp],
'actual: ', animals[test_labels[i, 0]], sep=' ')
print('accurate: ', accurate / predict_value.shape[0])
model_json = model.to_json()
with open('./models/model_3.json', 'w') as model_file:
model_file.write(model_json)
model.save_weights('./models/cat_dog_3.h5')
def load_cnnmodel():
with open('models/model_2.json', 'r') as model_js:
model_loaded = model_js.read()
model = model_from_json(model_loaded)
model.load_weights('models/cat_dog_2.h5')
sgd = Adam(lr=0.001)
model.compile(loss='binary_crossentropy',
optimizer=sgd, metrics=['accuracy'])
resize_pic.py 中定義了一些圖像的預處理函數
# -*- coding: utf-8 -*-
"""
Created on Wed May 2 23:03:57 2018
@author: xiaozhe
"""
import cv2
import os
import numpy as np
import _thread as thread
import logging
import random
from matplotlib import pyplot as plt
from keras.preprocessing import image
from keras.utils import np_utils
logging.basicConfig(level=logging.DEBUG, format='%(message)s')
def resize_pic(path, width, height):
# path = '.\\pics_dog'
# width = 300
# height = 200
for num, pic in enumerate(os.listdir(path), 1):
logging.debug(pic) if num % 100 == 0 else None
pic = os.path.join(path, pic)
img = cv2.imread(pic, cv2.IMREAD_UNCHANGED)
try:
img = cv2.resize(img, (width, height))
cv2.imwrite(pic, img)
except Exception as e:
logging.debug(e)
os.remove(pic)
def generate_data(path, samples_num):
logging.debug('Prepare data')
# path = '.\\pics_dog'
# samples_num = 1000
data = np.empty((samples_num, 200, 300, 3))
labels = np.empty((samples_num,))
path_list = os.listdir(path)
random.shuffle(path_list)
# ii, jj = 0, 0
for i, pic in enumerate(path_list):
if i >= samples_num:
break
pic = os.path.join(path, pic)
img = cv2.imread(pic, cv2.IMREAD_UNCHANGED)
if os.path.split(pic)[-1].split('.')[0] == 'dog':
labels[i] = 1
data[i] = img
# print(labels[i])
# ii += 1
elif os.path.split(pic)[-1].split('.')[0] == 'cat':
labels[i] = 0
data[i] = img
# print(labels[i])
# jj += 1
print(i, pic, labels[i])
labels = np_utils.to_categorical(labels, 2)
return data, labels
def load_data(path, image_size, sample_num):
# path = './data/train/'
files = os.listdir(path)
random.shuffle(files)
files = files[:sample_num]
images = []
labels = []
for i, f in enumerate(files, 1):
img_path = os.path.join(path, f)
img = image.load_img(img_path, target_size=image_size)
img_array = image.img_to_array(img)
images.append(img_array)
if 'cat' in f:
labels.append(0)
else:
labels.append(1)
logging.debug(str(i) + ' ' + f + ': ' +
str(labels[-1])) if i % 500 == 0 else None
data = np.array(images)
labels = np.array(labels).reshape(len(labels), 1)
#
# labels = np_utils.to_categorical(labels, 2)
return data, labels
if __name__ == '__main__':
path_dog = os.path.join(os.getcwd(), 'train')
path_cat = os.path.join(os.getcwd(), 'test1')
thread.start_new_thread(resize_pic, (path_cat, 128, 128,))
thread.start_new_thread(resize_pic, (path_dog, 128, 128,))
# resize_pic(path_cat, 224, 224)
# resize_pic(path_dog, 224, 224)
print('Finished')
須要用到opencv庫，直接使用pip install opencv-python 安裝
訓練這個模型，使用CPU的時候一個epoch須要5分鐘左右，使用GPU只須要30多秒左右，速度提升了5倍。實際訓練出來的模型大概有80%左右的精度。
8. 基於上面的模型能夠進一步調參數優化。主要掌握用GPU訓練模型的方法。