Nsryjdtyk

i run the coed with rtx2080 ,using docker.
Once i call sess.run(train_step,feed_dick={}),i get "the Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)" .But if i run it with cpu ,it works well.
i have no idea what happened .

Using TensorFlow backend.

2018-11-18 13:19:12.025412: I
tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports
instructions that this TensorFlow binary was not compiled to use: AVX2
FMA 2018-11-18 13:19:12.132999: I
tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:964] successful
NUMA node read from SysFS had negative value (-1), but there must be
at least one NUMA node, so returning NUMA node zero 2018-11-18
13:19:12.133566: I
tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0
with properties: name: GeForce RTX 2080 major: 7 minor: 5
memoryClockRate(GHz): 1.8 pciBusID: 0000:06:00.0 totalMemory: 7.76GiB
freeMemory: 7.46GiB 2018-11-18 13:19:12.133584: I
tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible
gpu devices: 0 2018-11-18 13:19:12.394726: I
tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device
interconnect StreamExecutor with strength 1 edge matrix: 2018-11-18
13:19:12.394763: I
tensorflow/core/common_runtime/gpu/gpu_device.cc:988] 0
2018-11-18 13:19:12.394770: I
tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0: N
2018-11-18 13:19:12.394963: I
tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created
TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with
7172 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2080,
pci bus id: 0000:06:00.0, compute capability: 7.5)

import tensorflow as tf

import numpy as np

import pandas as pd

from tensorflow.contrib.framework import arg_scope

from keras.layers import Dense, Activation

import pickle

from tensorflow.contrib.layers import batch_norm, flatten



train_data = {b'data': , b'labels': }

# 加载训练数据

for i in range(5):

    with open("data/cifar-10/data_batch_" + str(i + 1), mode='rb') as file:

        data = pickle.load(file, encoding='bytes')

        train_data[b'data'] += list(data[b'data'])

        train_data[b'labels'] += data[b'labels']

# 加载测试数据

with open("data/cifar-10/test_batch", mode='rb') as file:

    test_data = pickle.load(file, encoding='bytes')

# 定义一些变量

NUM_LABLES = 10  # 分类结果为10类

BATCH_SIZE = 64  # 每次训练batch数



sess = tf.InteractiveSession()





# 权重初始化

def weight_variable(shape):

    initial = tf.truncated_normal(shape, stddev=2 / shape[0] / shape[1] / shape[2])

    #   initial = tf.truncated_normal(shape, stddev=0.01)

    return tf.Variable(initial)





# 卷积层偏置初始化为常数0.1

def bias_variable(shape):

    initial = tf.constant(0.1, shape=shape)

    return tf.Variable(initial)





# 定义卷积操作，卷积步长为1. padding = 'SAME' 表示全0填充

def conv2d(x, W):

    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')





# 定义最大池化操作，尺寸为2，步长为2，全0填充

def max_pool_2x2(x):

    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')



# 对输入进行占位操作，输入为BATCH*3072向量，输出为BATCH*10向量

x = tf.placeholder(tf.float32, [None, 3072])

y_ = tf.placeholder(tf.float32, [None, NUM_LABLES])

# 对输入进行reshape，转换成3*32*32格式

x_image = tf.reshape(x, [-1, 3, 32, 32])

# 转置操作，转换成滤波器做卷积所需格式：32*32*3,32*32为其二维卷积操作维度

x_image = tf.transpose(x_image, [0, 2, 3, 1])



# 第一层卷积，滤波器参数3*3*3, 32个

#bn_layer1 = Batch_Normalization(x_image, istraining, "bn1")

W_conv1 = weight_variable([3, 3, 3, 32])

b_conv1 = bias_variable([32])

h_conv1 = conv2d(x_image, W_conv1) + b_conv1

#h_conv1 = tf.layers.dropout(inputs=h_conv1, rate=droprate, training=istraining)

h_relu1 = tf.nn.relu(h_conv1)  # 卷积

h_pool1 = max_pool_2x2(h_relu1)  # 池化



h_pool4 = tf.reshape(h_pool1,[-1,16*16*32])

bn_layer5_flat = tf.layers.dense(inputs=h_pool4, units=10, name='linear')



cross_entropy = tf.losses.softmax_cross_entropy(onehot_labels=y_, logits=bn_layer5_flat,

                                                reduction=tf.losses.Reduction.MEAN)

train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(bn_layer5_flat, 1), tf.argmax(y_, 1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))



sess.run(tf.global_variables_initializer())

x_train = np.array(train_data[b'data']) / 255

y_train = np.array(pd.get_dummies(train_data[b'labels']))

x_test = test_data[b'data'] / 255

y_test = np.array(pd.get_dummies(test_data[b'labels']))

eplr = 1e-4;

for i in range(20000):

    if i == 20000 * 0.5 or i == 20000 * 0.75:

        eplr = eplr / 10

    start = i * BATCH_SIZE % (50000 - BATCH_SIZE)

    sess.run(train_step,feed_dict={x: x_train[start: start + BATCH_SIZE],

                              y_: y_train[start: start + BATCH_SIZE],

                              })

    if i % 100 == 0:

        train_accuracy = accuracy.eval(feed_dict={x: x_test[0: 200],

                                                  y_: y_test[0: 200]

                                                  })

        loss_value = cross_entropy.eval(feed_dict={x: x_train[start: start + BATCH_SIZE],

                                                   y_: y_train[start: start + BATCH_SIZE]

                                                   })

        print("step %d, trainning accuracy， %g loss %g" % (i, train_accuracy, loss_value))



test_accuracy = accuracy.eval(feed_dict={x: x_test, y_: y_test})

print("test accuracy %g" % test_accuracy)