BiMPM
BiMPM copied to clipboard
A problem about __init__() got an unexpected keyword argument 'name'
TypeError Traceback (most recent call last)
/notebooks/BiMPM1/src/SentenceMatchModelGraph.pyc in init(self, num_classes, word_vocab, char_vocab, is_training, options, global_step) 8 self.options = options 9 self.create_placeholders() ---> 10 self.create_model_graph(num_classes, word_vocab, char_vocab, is_training, global_step=global_step) 11 12 def create_placeholders(self):
/notebooks/BiMPM1/src/SentenceMatchModelGraph.pyc in create_model_graph(self, num_classes, word_vocab, char_vocab, is_training, global_step) 95 (question_char_outputs_fw, question_char_outputs_bw, _) = layer_utils.my_lstm_layer(in_question_char_repres, options.char_lstm_dim, 96 input_lengths=question_char_lengths,scope_name="char_lstm", reuse=False, ---> 97 is_training=is_training, dropout_rate=options.dropout_rate, use_cudnn=options.use_cudnn) 98 question_char_outputs_fw = layer_utils.collect_final_step_of_lstm(question_char_outputs_fw, question_char_lengths - 1) 99 question_char_outputs_bw = question_char_outputs_bw[:, 0, :]
/notebooks/BiMPM1/src/layer_utils.py in my_lstm_layer(input_reps, lstm_dim, input_lengths, scope_name, reuse, is_training, dropout_rate, use_cudnn) 18 inputs = tf.transpose(input_reps, [1, 0, 2]) 19 lstm = tf.contrib.cudnn_rnn.CudnnLSTM(1, lstm_dim, direction="bidirectional", ---> 20 name="{}_cudnn_bi_lstm".format(scope_name), dropout=dropout_rate if is_training else 0) 21 outputs, _ = lstm(inputs) 22 outputs = tf.transpose(outputs, [1, 0, 2])
TypeError: init() got an unexpected keyword argument 'name'
Thanks very much!
Because my English is particularly poor, so please forgive my rudeness,This sentence is translated by google。
Thanks again!
Looks like we are using different versions of tensorflow. I'm using tensorflow 1.4 nightly. A easier fix for you, is just to remove "name="{}_cudnn_bi_lstm".format(scope_name)" from https://github.com/zhiguowang/BiMPM/blob/master/src/layer_utils.py#L20
I remve the "{}_cudnn_bi_lstm".format(scope_name)" ,and get follow error
TypeError Traceback (most recent call last)
/notebooks/BiMPM1/src/SentenceMatchModelGraph.pyc in init(self, num_classes, word_vocab, char_vocab, is_training, options, global_step) 8 self.options = options 9 self.create_placeholders() ---> 10 self.create_model_graph(num_classes, word_vocab, char_vocab, is_training, global_step=global_step) 11 12 def create_placeholders(self):
/notebooks/BiMPM1/src/SentenceMatchModelGraph.pyc in create_model_graph(self, num_classes, word_vocab, char_vocab, is_training, global_step) 95 (question_char_outputs_fw, question_char_outputs_bw, _) = layer_utils.my_lstm_layer(in_question_char_repres, options.char_lstm_dim, 96 input_lengths=question_char_lengths,scope_name="char_lstm", reuse=False, ---> 97 is_training=is_training, dropout_rate=options.dropout_rate, use_cudnn=options.use_cudnn) 98 question_char_outputs_fw = layer_utils.collect_final_step_of_lstm(question_char_outputs_fw, question_char_lengths - 1) 99 question_char_outputs_bw = question_char_outputs_bw[:, 0, :]
/notebooks/BiMPM1/src/layer_utils.py in my_lstm_layer(input_reps, lstm_dim, input_lengths, scope_name, reuse, is_training, dropout_rate, use_cudnn) 18 inputs = tf.transpose(input_reps, [1, 0, 2]) 19 lstm = tf.contrib.cudnn_rnn.CudnnLSTM(1, lstm_dim, direction="bidirectional", ---> 20 dropout=dropout_rate if is_training else 0) 21 outputs, _ = lstm(inputs) 22 outputs = tf.transpose(outputs, [1, 0, 2])
TypeError: init() takes at least 4 arguments (5 given)
I plan to change tensorflow for the same version as yours,
My current version is also 1.4
I just check my version. Here is the one I'm using tensorflow 1.5.0-dev20171106. Sorry for the inconvenience.
On Tue, Jan 30, 2018 at 10:06 PM, lqjsurpass [email protected] wrote:
The version I use now is also tensorflow 1.4
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/zhiguowang/BiMPM/issues/28#issuecomment-361809459, or mute the thread https://github.com/notifications/unsubscribe-auth/AYEV-Sp86Ki9utYhpcaQ9d6ltF1a5WO9ks5tP9i3gaJpZM4Rx1-N .
meet the same problem, I think the "Requirements" chapter in README.md of this project should be modifiled
I have changed my tensorflow version to 1.5.0(tensorflow-1.5.0-cp27-cp27mu-manylinux1_x86_64.whl)
, but encountered another error.
2018-02-05 14:37:26.647844: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
Traceback (most recent call last):
File "src/SentenceMatchTrainer.py", line 253, in <module>
main(FLAGS)
File "src/SentenceMatchTrainer.py", line 191, in main
sess.run(initializer)
File "/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1128, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1344, in _do_run
options, run_metadata)
File "/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1363, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'CudnnRNNCanonicalToParams' with these attrs. Registered devices: [CPU], Registered kernels:
<no registered kernels>
[[Node: Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/CudnnRNNCanonicalToParams = CudnnRNNCanonicalToParams[T=DT_FLOAT, direction="bidirectional", dropout=0, input_mode="linear_input", num_params=16, rnn_mode="lstm", seed=0, seed2=0](Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/CudnnRNNCanonicalToParams/num_layers, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/CudnnRNNCanonicalToParams/num_units, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/CudnnRNNCanonicalToParams/input_size, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_1, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_2, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_3, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_4, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_5, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_6, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_7, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_8, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_9, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_10, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_11, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_12, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_13, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_14, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_15, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_1, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_2, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_3, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_4, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_5, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_6, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_7, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_8, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_9, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_10, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_11, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_12, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_13, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_14, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_15)]]
looks like you are not using GPU, or don't have the cudnn. If you are using cpu, you can change https://github.com/zhiguowang/BiMPM/blob/master/configs/snli.sample.config#L46 to false, and try again.
On Mon, Feb 5, 2018 at 1:45 AM, vacingFang [email protected] wrote:
I have changed the tensor flow version to 1.5.0, but encountered another error.
2018-02-05 14:37:26.647844: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA Traceback (most recent call last): File "src/SentenceMatchTrainer.py", line 253, in
main(FLAGS) File "src/SentenceMatchTrainer.py", line 191, in main sess.run(initializer) File "/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run run_metadata_ptr) File "/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1128, in _run feed_dict_tensor, options, run_metadata) File "/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1344, in _do_run options, run_metadata) File "/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1363, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'CudnnRNNCanonicalToParams' with these attrs. Registered devices: [CPU], Registered kernels: [[Node: Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/CudnnRNNCanonicalToParams = CudnnRNNCanonicalToParams[T=DT_FLOAT, direction="bidirectional", dropout=0, input_mode="linear_input", num_params=16, rnn_mode="lstm", seed=0, seed2=0](Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/CudnnRNNCanonicalToParams/num_layers, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/CudnnRNNCanonicalToParams/num_units, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/CudnnRNNCanonicalToParams/input_size, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_1, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_2, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_3, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_4, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_5, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_6, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_7, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_8, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_9, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_10, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_11, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_12, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_13, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_14, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/random_uniform_15, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_1, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_2, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_3, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_4, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_5, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_6, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_7, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_8, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_9, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_10, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_11, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_12, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_13, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_14, Model_1/aggregation_layer/right_layer-0/right_layer-0_cudnn_bi_lstm/right_layer-0_cudnn_bi_lstm/Const_15)]]
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/zhiguowang/BiMPM/issues/28#issuecomment-362995412, or mute the thread https://github.com/notifications/unsubscribe-auth/AYEV-YtU1nj4WO9H2g2vsSw5DP_yPyDbks5tRqN_gaJpZM4Rx1-N .
looks like you are not using GPU, or don't have the cudnn. If you are using cpu, you can change https://github.com/zhiguowang/BiMPM/blob/master/configs/snli.sample.config#L46 to false, and try again.
it works, many thanks