yuanke

what I found is: at encoder_input, decoder_input = random.choice(data[bucket_id]) the data contains a [], so it cause a call like random.choice([]) which raise the error

maybe you should try --antilm

@liuyuemaicha gang ba de ;) good job

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...

in one computer, it runs on GPU well but in another, it cannot utilize the GPU, just on CPU, any clue on this issue?

that correct, @insikk but how to use it tensor flow 1.2.1?

from tensorflow.python.ops import rnn_cell_impl output = rnn_cell_impl._linear for tf1.2.1

waiting.....

prefer both, thanks ;)

any more example of usage