分享(簡易版)的tensorflow win10 + keras安裝步驟

gpu的安裝環節很多有興趣的人安裝如果有問題可以討論喔~

1.anaconda 3.6

安裝網址https://www.continuum.io/downloads
```
  建議下載python 3.6
```

2.加入環境變數path %SystemRoot%\system32

不然後續有些東西無法設定好

3.Tensorflow只支援python 3.5環境，所以要把環境設為3.5

請打開cmd然後請輸入下列指令

 1.conda create --name tensorflow python=3.5

     [建立一個anaconda的python3.5的虛擬環境]

 2.activate tensorflow

   [啟用環境]

 3.conda install jupyter scipy mingw libpython

   [scipy是必要的jupyter是建議安裝的，這樣後續開發比較好用，mingw libpython是安裝keras會用到在這邊先裝]

(4)pip install tensorflow

   Or

   pip install tensorflow-gpu

  [看是要安裝CPU還是GPU版]

4.安裝keras

[1]設定環境變數path\(要依照你安裝的位置更改喔\)

    [C:\Anaconda2;C:\Anaconda2\Scripts;C:\Anaconda2\MinGW\bin;

    C:\Anaconda2\MinGW\x86\_64-w64-mingw32\lib;]

[2] pip install keras

[3]打開`C:\Users\(username)\.keras`,修改文件内的`keras.json`文件如下：

     {

           "image\_dim\_ordering": "tf",

           "epsilon": 1e-07,

           "floatx": "float32",

          "backend": "tensorflow"

      }
[4]keras.backend.backend() 或是直接 import keras 也會show出來

5.下載範例檔

git keras example(https://github.com/fchollet/keras/tree/master/examples)

 如果不能git

 請先安裝git或是直接用網址抓

 conda install -c anaconda git=2.11.1

6.然後執行mnist_cnn.py(python mnist_cnn.py)

成功就會看到下面的畫面

PS1 -- Debug

可以先import tensorflow或是import keras看有沒有錯誤

有的話就看看錯誤訊息來debug

(請先進入python後輸入……)

PS2 : GPU安裝事項

可以參考這個網站http://www.netinstructions.com/how-to-install-and-run-gpu-enabled-tensorflow-on-windows/

----安裝CUDA8.0(driver不要裝，然後設定環境變數)

----安裝CUDNN

沒有問題的話應該可以直接run…….

有問題的話要看問題在哪………太多點了…….

PS :(1) VM 不能使用GPU

   \(2\)Bash on Ubuntu on Windows 也不行

   \(3\)https://developer.nvidia.com/cuda-gpus

showPICs Code

# Plot ad hoc mnist instances
from keras.datasets import mnist
import matplotlib.pyplot as plt
# load (downloaded if needed) the MNIST dataset
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# plot 4 images as gray scale
plt.subplot(221)
plt.imshow(X_train[8], cmap=plt.get_cmap('gray'))
plt.subplot(222)
plt.imshow(X_train[9], cmap=plt.get_cmap('gray'))
plt.subplot(223)
plt.imshow(X_train[20], cmap=plt.get_cmap('gray'))
plt.subplot(224)
plt.imshow(X_train[25], cmap=plt.get_cmap('gray'))
# show the plot
plt.show()

tensorboard Code(最後要在起一個cmd進入virtualEnv後執行註解的那段指令)

'''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 numpy as np
np.random.seed(1337)  # for reproducibility

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
import keras.callbacks
import keras.backend.tensorflow_backend as KTF

batch_size = 128
nb_classes = 10
nb_epoch = 12
log_filepath = '/tmp/keras_log'

# input image dimensions
img_rows, img_cols = 28, 28
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
pool_size = (2, 2)
# convolution kernel size
kernel_size = (3, 3)

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

if K.image_dim_ordering() == 'th':
    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')
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 = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

model = Sequential()

model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
                        border_mode='valid',
                        input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adadelta',
              metrics=['accuracy'])
tb_cb = keras.callbacks.TensorBoard(log_dir=log_filepath, histogram_freq=1)
cbks = [tb_cb]


history = model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
          verbose=1, validation_data=(X_test, Y_test),callbacks=cbks)
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
#tensorboard --logdir=/tmp/keras_log

Install Steps

results matching ""

No results matching ""