如何存儲信息以便能夠在Keras中繪製錯誤和時代？

Question

我想繪製錯誤與keras中的時代數量。爲此，我發現了一個非常有用的帖子here。它在本地就像一個魅力，但如果我想在某些遠程GPU /羣集中運行我的腳本，那麼它就不那麼有用，因爲我需要發送自己的數據以便能夠實際繪製圖形。有沒有辦法運行類似的東西，但將錯誤存儲在某個文件/ csv/json中，然後用rysnc/scp/dropbox等標準工具發送給我自己？

現在我唯一的想法是醃製該文件，然後將其發送給自己，並取消它，但它根本不起作用。我得到的錯誤：

Traceback (most recent call last): 
    File "store_data.py", line 71, in <module> 
    pickle.dump(history, open("history.p", "wb")) 
_pickle.PicklingError: Can't pickle <class 'module'>: attribute lookup module on builtins failed 

是否有不同的方式使用Keras和python？我只需要能夠存儲這種類型的數據，以便我可以以某種方式將它發送到本地計算機。

---

目前我完全重複性誤差可以做如下：

store_data.py

# Visualize training history 
from keras.models import Sequential 
from keras.layers import Dense, Dropout, Activation, Flatten 
from keras.datasets import cifar10 
from keras.utils import np_utils 

import numpy 
import pickle 

print('start visualization example') 

#params 
nb_classes = 10 

data_augmentation = False 

units_single_layer = 10 
actication_func = 'relu' 
actication_func = 'sigmoid' 

nb_epoch = 3 
batch_size = 64 
#optimizer = 'adam' 
optimizer = 'rmsprop' 

# input image dimensions 
img_rows, img_cols = 32, 32 
# The CIFAR10 images are RGB. 
img_channels = 3 

# The data, shuffled and split between train and test sets: 
(X_train, y_train), (X_test, y_test) = cifar10.load_data() 
X_train = X_train.reshape((X_train.shape[0],32*32*3)) 
X_test = X_test.reshape((X_test.shape[0],32*32*3)) 
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) 

# create model 
print('\n ---- Singled Layer Model ----') 
print('units_single_layer: ', units_single_layer) 
print('actication_func: ', actication_func) 
model = Sequential() 

model.add(Dense(units_single_layer, input_shape=(32*32*3,))) 
model.add(Activation(actication_func)) 
model.add(Dense(nb_classes)) 
model.add(Activation('softmax')) 

# Compile model 
print('\n ---- Optimizer ----') 
print('optimizer: ', optimizer) 
print('batch_size: ', optimizer) 

print('') 
model.compile(loss='categorical_crossentropy', 
       optimizer=optimizer, 
       metrics=['accuracy']) 
# Fit the model 
#history = model.fit(X, Y, validation_split=0.33, nb_epoch=150, batch_size=10, verbose=0) 
history = model.fit(X_train, Y_train, 
      batch_size=batch_size, 
      nb_epoch=nb_epoch, 
      validation_data=(X_test, Y_test), 
      shuffle=True) 

pickle.dump(history, open("history.p", "wb")) 

，並繪製它：

plot.py

# Visualize training history 
from keras.models import Sequential 
from keras.layers import Dense, Dropout, Activation, Flatten 
from keras.datasets import cifar10 
from keras.utils import np_utils 

import matplotlib.pyplot as plt 

import numpy 
import pickle 

history = pickle.load(open("history.p", "rb")) 

# list all data in history 
print(history.history.keys()) 
# summarize history for accuracy 
plt.plot(history.history['acc']) 
plt.plot(history.history['val_acc']) 
plt.title('model accuracy') 
plt.ylabel('accuracy') 
plt.xlabel('epoch') 
plt.legend(['train', 'test'], loc='upper left') 
plt.show() 
# summarize history for loss 
plt.plot(history.history['loss']) 
plt.plot(history.history['val_loss']) 
plt.title('model loss') 
plt.ylabel('loss') 
plt.xlabel('epoch') 
plt.legend(['train', 'test'], loc='upper left') 
plt.show() 

另外，如果你有hav與matplot LIB荷蘭國際集團的問題，由於框架構建只使用已經解決了這個問題你與虛擬ENV：

python3 -m venv <my-virtual-env-name> 

http://matplotlib.org/faq/osx_framework.html#virtualenv

http://matplotlib.org/faq/osx_framework.html

http://matplotlib.org/faq/virtualenv_faq.html

的-m venv使用python3的實現的virtualenv，並且該實現使python成爲一個框架。

Answer 1

嘗試酸洗唯一的損失詞典：

pickle.dump(history.history, open("history.p", "wb"))