Deep learning training speed with 1080 Ti and M1200

1 min read

I compared the speed of Nvidia’s 1080 Ti on a desktop (Intel i5-3470 CPU, 3.2G Hz, 32G memory) and NVIDIA Quadro M1200 w/4GB GDDR5, 640 CUDA cores on a laptop (CPU: Intel Core i7-7920HQ (Quad Core 3.10GHz, 4.10GHz Turbo, 8MB 45W, Memory: 64G).

The code I used is Keras’ own example ( to classiy MNIST dataset:

MNIST dataset
MNIST dataset
'''Trains a simple convnet on the MNIST dataset.

Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dense(128, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))

              metrics=['accuracy']), y_train, batch_size=batch_size, epochs=epochs,
          verbose=1, validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

The result is that 1080 Ti is 3 times faster than M1200:

M1200 (1 epoch) 1080 Ti (1 epoch)
18s 6s

Receive email notification via email 博客有新内容通知我

Don't want to miss new papers in your field? Check out Stork we developed:

xjview 10.0 released

xjView is a viewing program to visualize fMRI images. It can also be used to visualize fNIRS data if you convert the fNIRS activation...
Xu Cui
14 sec read


作者:北京师范大学 龙宇航,longyuhangwork@163.com代码来源(见本页底部):周思远 在使用wtc计算脑间神经同步后,我们需要在多个频率段、多个通道组合上对神经同步值进行统计检验,因此当进行频段选择时,面临多重比较的问题。为了解决多重比较的问题,可以采取基于参数或非参数检验的多重比较矫正的方法。由于基于非参数检验的多重比较矫正对数据的分布形态没有严格要求,因此具有更广泛的应用场景 (Maris and Oostenveld, 2007)。本文即介绍基于随机置换的非参数检验的方法 (Zheng et al., 2020; Long et al., 2021)。 在寻找感兴趣的效应时,我们采取了基于频率簇(Cluster)的方法,即在频率方向寻找连续显著的Cluster,该方法比基于最强效应点的方法具有更为优秀的抗噪音能力。值得注意的是,我们并没有沿着通道的方向去寻找连续显著的通道簇,这是因为沿着通道方向寻找Cluster容易受到生理噪音的影响。 下面进入具体的实操部分。假设本例招募了22对组1被试及22对组2被试,每对被试分别进行3种条件的任务,因此本例是2(组别,被试间因素)*3(条件,被试内因素)的实验设计。本例对神经同步值进行2*3的混合方差分析,并关注交互作用。 具体来讲,进行置换检验需要进行以下几个步骤:1. 重采样;2. 对随机样本进行计算及统计;3. 计算真实样本的统计量;4. 真实样本与随机样本的对比。下面依次进行介绍。 1. 重采样...
Xu Cui
1 min read

Calculate phase difference between two general signals (e.g. HbO…

In a recent fNIRS journal club (vedio recorded here), Dr. Tong talked about their work on the phase difference between oxy and deoxy Hb,...
Xu Cui
1 min read

4 Replies to “Deep learning training speed with 1080 Ti and M1200”

Leave a Reply

Your email address will not be published. Required fields are marked *