當我使用 tensorflow 時出現錯誤 Segmentation fault (core dumped)

Question

當我使用 tensorflow 時出現錯誤 Segmentation fault (core dumped)，我的代碼是：

from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import Embedding
from keras.layers import LSTM
from keras.utils import to_categorical

model = Sequential()
max_features = 100
model.add(Embedding(max_features, output_dim=256))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

print("model is ok ")

Answer 1

Segmentation fault意味着您嘗試訪問您無權訪問的內存。 如果選擇正確的Tensorflow組合， CUDA和cuDNN將解決這個問題。 您可以參考經過測試的構建配置。

我能夠毫無問題地執行上面的代碼。 請參考下圖

import tensorflow as tf
print(tf.__version__)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Embedding, LSTM

model = Sequential()
max_features = 100
model.add(Embedding(max_features, output_dim=256))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.summary()

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

print("model is ok ")

輸出：

2.5.0
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        (None, None, 256)         25600     
_________________________________________________________________
lstm (LSTM)                  (None, 128)               197120    
_________________________________________________________________
dropout (Dropout)            (None, 128)               0         
_________________________________________________________________
dense (Dense)                (None, 1)                 129       
=================================================================
Total params: 222,849
Trainable params: 222,849
Non-trainable params: 0
_________________________________________________________________
model is ok