Question

我最近不得不切换到只有英特尔（Idris）GPU的计算机，因此CUDA不再有效。我真的想在GPU上运行Tensorflow，所以我看了Tensorflow-cl。到目前为止

python -c "import tensorflow"

工作正常，以及：

python -c "import keras"

但是运行minst_cnn.py示例：

'''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)
else:
    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),
                 activation='relu',
                 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(x_train, 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])

给出以下错误：

➜  AI python keras_test.py       
Using TensorFlow backend.
x_train shape: (60000, 28, 28, 1)
60000 train samples
10000 test samples
Traceback (most recent call last):
  File "keras_test.py", line 49, in <module>
    input_shape=input_shape))
  File "/usr/lib/python3.6/site-packages/keras/models.py", line 430, in add
    layer(x)
  File "/usr/lib/python3.6/site-packages/keras/engine/topology.py", line 578, in __call__
    output = self.call(inputs, **kwargs)
  File "/usr/lib/python3.6/site-packages/keras/layers/convolutional.py", line 164, in call
    dilation_rate=self.dilation_rate)
  File "/usr/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2893, in conv2d
    data_format='NHWC')
TypeError: convolution() got an unexpected keyword argument 'data_format'

堆栈跟踪并不能让我相信交换到Tensorflow-cl是问题，但我不确定。

正在运行pip show会为keras提供以下信息：

➜  AI pip show keras
Name: Keras
Version: 2.0.3
Summary: Deep Learning for Python
Home-page: https://github.com/fchollet/keras
Author: Francois Chollet
Author-email: francois.chollet@gmail.com
License: MIT
Location: /usr/lib/python3.6/site-packages
Requires: theano, pyyaml, six

tensorflow的以下信息（我使用pip install --upgrade tensorflow-0.11.0rc0-py3-none-any.whl安装）：

➜  AI pip show tensorflow
Name: tensorflow
Version: 0.11.0rc0
Summary: TensorFlow helps the tensors flow
Home-page: http://tensorflow.org/
Author: Google Inc.
Author-email: opensource@google.com
License: Apache 2.0
Location: /usr/lib/python3.6/site-packages
Requires: wheel, numpy, protobuf, six

如何使示例有效？

使用带有Tensorflow-cl的Keras

0 个答案: