新手提问

[d5d]

需要安装tensorflow？再运行这个程序？还是安装char-rnn？

[hit-computer]

需要安装TensorFlow，char-rnn-tf不需要安装直接运行里面的python文件即可（运行train.py文件训练模型，得到训练好的模型后可运行generate.py进行文本生成）。

[d5d]

求指教 ：-0 ubuntu 已经安装tf. train有如下错误提示： root@27:~/char-rnn-tf# python train.py test.txt data has 9437 characters, 702 unique. W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations. W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations. W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations. W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations. Traceback (most recent call last): File "train.py", line 211, in tf.app.run() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 44, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "train.py", line 194, in main m = Model(is_training=True, config=config) File "train.py", line 77, in init lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(size, forget_bias=0.0, state_is_tuple=False) AttributeError: 'module' object has no attribute 'rnn_cell'

[hit-computer]

这个错误是TensorFlow不同版本间API不一样导致的。我的这个代码是TensorFlow 0.12，你用的应该是1.0吧。你需要把tf.nn.rnn_cell都改成tf.contrib.rnn，还有101行tf.concat(1, outputs)改成tf.concat(outputs, 1)。也不明白为何TensorFlow要改API，导致旧版的程序需要修改才能运行。汗...

[d5d]

已经成功运行。谢谢！

[hscspring]

@hit-computer 不好意思，请问 Python 版本没有要求吗？ Tks：）

[hit-computer]

我用的是python2，如果你使用的是python3，则按照python2和python3的不同之处修改即可，TensorFlow部分的代码应该不需要修改