INFO:tensorflow:Loading config from /root/seq2seq/example_configs/nmt_small.yml INFO:tensorflow:Loading config from /root/seq2seq/example_configs/train_seq2seq.yml INFO:tensorflow:Loading config from /root/seq2seq/example_configs/text_metrics_bpe.yml INFO:tensorflow:Final Config: buckets: 10,20,30,40 default_params: - {separator: ' '} - {postproc_fn: seq2seq.data.postproc.strip_bpe} hooks: - {class: PrintModelAnalysisHook} - {class: MetadataCaptureHook} - {class: SyncReplicasOptimizerHook} - class: TrainSampleHook params: {every_n_steps: 1000} metrics: - {class: LogPerplexityMetricSpec} - class: BleuMetricSpec params: {postproc_fn: seq2seq.data.postproc.strip_bpe, separator: ' '} - class: RougeMetricSpec params: {postproc_fn: seq2seq.data.postproc.strip_bpe, rouge_type: rouge_1/f_score, separator: ' '} - class: RougeMetricSpec params: {postproc_fn: seq2seq.data.postproc.strip_bpe, rouge_type: rouge_1/r_score, separator: ' '} - class: RougeMetricSpec params: {postproc_fn: seq2seq.data.postproc.strip_bpe, rouge_type: rouge_1/p_score, separator: ' '} - class: RougeMetricSpec params: {postproc_fn: seq2seq.data.postproc.strip_bpe, rouge_type: rouge_2/f_score, separator: ' '} - class: RougeMetricSpec params: {postproc_fn: seq2seq.data.postproc.strip_bpe, rouge_type: rouge_2/r_score, separator: ' '} - class: RougeMetricSpec params: {postproc_fn: seq2seq.data.postproc.strip_bpe, rouge_type: rouge_2/p_score, separator: ' '} - class: RougeMetricSpec params: {postproc_fn: seq2seq.data.postproc.strip_bpe, rouge_type: rouge_l/f_score, separator: ' '} model: AttentionSeq2Seq model_params: attention.class: seq2seq.decoders.attention.AttentionLayerDot attention.params: {num_units: 128} bridge.class: seq2seq.models.bridges.ZeroBridge decoder.class: seq2seq.decoders.AttentionDecoder decoder.params: rnn_cell: cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 embedding.dim: 128 encoder.class: seq2seq.encoders.BidirectionalRNNEncoder encoder.params: rnn_cell: cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 optimizer.learning_rate: 0.0001 optimizer.name: Adam optimizer.params: {epsilon: 8.0e-07} source.max_seq_len: 50 source.reverse: false target.max_seq_len: 50 WARNING:tensorflow:Ignoring config flag: default_params INFO:tensorflow:Setting save_checkpoints_secs to 600 INFO:tensorflow:Creating ParallelTextInputPipeline in mode=train INFO:tensorflow: ParallelTextInputPipeline: !!python/unicode 'num_epochs': null !!python/unicode 'shuffle': true !!python/unicode 'source_delimiter': !!python/unicode ' ' !!python/unicode 'source_files': [/wmt/train.tok.clean.bpe.32000.en] !!python/unicode 'target_delimiter': !!python/unicode ' ' !!python/unicode 'target_files': [/wmt/train.tok.clean.bpe.32000.de] INFO:tensorflow:Creating ParallelTextInputPipeline in mode=eval INFO:tensorflow: ParallelTextInputPipeline: !!python/unicode 'num_epochs': 1 !!python/unicode 'shuffle': false !!python/unicode 'source_delimiter': !!python/unicode ' ' !!python/unicode 'source_files': [/wmt/newstest2013.tok.bpe.32000.en] !!python/unicode 'target_delimiter': !!python/unicode ' ' !!python/unicode 'target_files': [/wmt/newstest2013.tok.bpe.32000.de] INFO:tensorflow:Using config: {'_model_dir': None, '_save_checkpoints_secs': 600, '_num_ps_replicas': 0, '_keep_checkpoint_max': 5, '_tf_random_seed': None, '_task_type': None, '_environment': 'local', '_is_chief': True, '_cluster_spec': , '_tf_config': gpu_options { per_process_gpu_memory_fraction: 1.0 } , '_num_worker_replicas': 0, '_task_id': 0, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_evaluation_master': '', '_keep_checkpoint_every_n_hours': 4, '_master': ''} INFO:tensorflow:Creating PrintModelAnalysisHook in mode=train INFO:tensorflow: PrintModelAnalysisHook: {} INFO:tensorflow:Creating MetadataCaptureHook in mode=train INFO:tensorflow: MetadataCaptureHook: {!!python/unicode 'step': 10} INFO:tensorflow:Creating SyncReplicasOptimizerHook in mode=train INFO:tensorflow: SyncReplicasOptimizerHook: {} INFO:tensorflow:Creating TrainSampleHook in mode=train INFO:tensorflow: TrainSampleHook: {!!python/unicode 'every_n_secs': null, !!python/unicode 'every_n_steps': 1000, !!python/unicode 'source_delimiter': !!python/unicode ' ', !!python/unicode 'target_delimiter': !!python/unicode ' '} INFO:tensorflow:Creating LogPerplexityMetricSpec in mode=eval INFO:tensorflow: LogPerplexityMetricSpec: {} INFO:tensorflow:Creating BleuMetricSpec in mode=eval INFO:tensorflow: BleuMetricSpec: {!!python/unicode 'eos_token': !!python/unicode 'SEQUENCE_END', !!python/unicode 'postproc_fn': !!python/unicode 'seq2seq.data.postproc.strip_bpe', !!python/unicode 'separator': !!python/unicode ' ', !!python/unicode 'sos_token': !!python/unicode 'SEQUENCE_START'} INFO:tensorflow:Creating RougeMetricSpec in mode=eval INFO:tensorflow: RougeMetricSpec: {!!python/unicode 'eos_token': !!python/unicode 'SEQUENCE_END', !!python/unicode 'postproc_fn': !!python/unicode 'seq2seq.data.postproc.strip_bpe', !!python/unicode 'rouge_type': !!python/unicode 'rouge_1/f_score', !!python/unicode 'separator': !!python/unicode ' ', !!python/unicode 'sos_token': !!python/unicode 'SEQUENCE_START'} INFO:tensorflow:Creating RougeMetricSpec in mode=eval INFO:tensorflow: RougeMetricSpec: {!!python/unicode 'eos_token': !!python/unicode 'SEQUENCE_END', !!python/unicode 'postproc_fn': !!python/unicode 'seq2seq.data.postproc.strip_bpe', !!python/unicode 'rouge_type': !!python/unicode 'rouge_1/r_score', !!python/unicode 'separator': !!python/unicode ' ', !!python/unicode 'sos_token': !!python/unicode 'SEQUENCE_START'} INFO:tensorflow:Creating RougeMetricSpec in mode=eval INFO:tensorflow: RougeMetricSpec: {!!python/unicode 'eos_token': !!python/unicode 'SEQUENCE_END', !!python/unicode 'postproc_fn': !!python/unicode 'seq2seq.data.postproc.strip_bpe', !!python/unicode 'rouge_type': !!python/unicode 'rouge_1/p_score', !!python/unicode 'separator': !!python/unicode ' ', !!python/unicode 'sos_token': !!python/unicode 'SEQUENCE_START'} INFO:tensorflow:Creating RougeMetricSpec in mode=eval INFO:tensorflow: RougeMetricSpec: {!!python/unicode 'eos_token': !!python/unicode 'SEQUENCE_END', !!python/unicode 'postproc_fn': !!python/unicode 'seq2seq.data.postproc.strip_bpe', !!python/unicode 'rouge_type': !!python/unicode 'rouge_2/f_score', !!python/unicode 'separator': !!python/unicode ' ', !!python/unicode 'sos_token': !!python/unicode 'SEQUENCE_START'} INFO:tensorflow:Creating RougeMetricSpec in mode=eval INFO:tensorflow: RougeMetricSpec: {!!python/unicode 'eos_token': !!python/unicode 'SEQUENCE_END', !!python/unicode 'postproc_fn': !!python/unicode 'seq2seq.data.postproc.strip_bpe', !!python/unicode 'rouge_type': !!python/unicode 'rouge_2/r_score', !!python/unicode 'separator': !!python/unicode ' ', !!python/unicode 'sos_token': !!python/unicode 'SEQUENCE_START'} INFO:tensorflow:Creating RougeMetricSpec in mode=eval INFO:tensorflow: RougeMetricSpec: {!!python/unicode 'eos_token': !!python/unicode 'SEQUENCE_END', !!python/unicode 'postproc_fn': !!python/unicode 'seq2seq.data.postproc.strip_bpe', !!python/unicode 'rouge_type': !!python/unicode 'rouge_2/p_score', !!python/unicode 'separator': !!python/unicode ' ', !!python/unicode 'sos_token': !!python/unicode 'SEQUENCE_START'} INFO:tensorflow:Creating RougeMetricSpec in mode=eval INFO:tensorflow: RougeMetricSpec: {!!python/unicode 'eos_token': !!python/unicode 'SEQUENCE_END', !!python/unicode 'postproc_fn': !!python/unicode 'seq2seq.data.postproc.strip_bpe', !!python/unicode 'rouge_type': !!python/unicode 'rouge_l/f_score', !!python/unicode 'separator': !!python/unicode ' ', !!python/unicode 'sos_token': !!python/unicode 'SEQUENCE_START'} WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/monitors.py:267: __init__ (from tensorflow.contrib.learn.python.learn.monitors) is deprecated and will be removed after 2016-12-05. Instructions for updating: Monitors are deprecated. Please use tf.train.SessionRunHook. INFO:tensorflow:Creating AttentionSeq2Seq in mode=train INFO:tensorflow: AttentionSeq2Seq: !!python/unicode 'attention.class': !!python/unicode 'seq2seq.decoders.attention.AttentionLayerDot' !!python/unicode 'attention.params': {num_units: 128} !!python/unicode 'bridge.class': !!python/unicode 'seq2seq.models.bridges.ZeroBridge' !!python/unicode 'bridge.params': {} !!python/unicode 'decoder.class': !!python/unicode 'seq2seq.decoders.AttentionDecoder' !!python/unicode 'decoder.params': rnn_cell: cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 !!python/unicode 'embedding.dim': 128 !!python/unicode 'embedding.init_scale': 0.04 !!python/unicode 'embedding.share': false !!python/unicode 'encoder.class': !!python/unicode 'seq2seq.encoders.BidirectionalRNNEncoder' !!python/unicode 'encoder.params': rnn_cell: cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 !!python/unicode 'inference.beam_search.beam_width': 0 !!python/unicode 'inference.beam_search.choose_successors_fn': !!python/unicode 'choose_top_k' !!python/unicode 'inference.beam_search.length_penalty_weight': 0.0 !!python/unicode 'optimizer.clip_embed_gradients': 0.1 !!python/unicode 'optimizer.clip_gradients': 5.0 !!python/unicode 'optimizer.learning_rate': 0.0001 !!python/unicode 'optimizer.lr_decay_rate': 0.99 !!python/unicode 'optimizer.lr_decay_steps': 100 !!python/unicode 'optimizer.lr_decay_type': !!python/unicode '' !!python/unicode 'optimizer.lr_min_learning_rate': 1.0e-12 !!python/unicode 'optimizer.lr_staircase': false !!python/unicode 'optimizer.lr_start_decay_at': 0 !!python/unicode 'optimizer.lr_stop_decay_at': 2147483647 !!python/unicode 'optimizer.name': !!python/unicode 'Adam' !!python/unicode 'optimizer.params': {epsilon: 8.0e-07} !!python/unicode 'optimizer.sync_replicas': 0 !!python/unicode 'optimizer.sync_replicas_to_aggregate': 0 !!python/unicode 'source.max_seq_len': 50 !!python/unicode 'source.reverse': false !!python/unicode 'target.max_seq_len': 50 !!python/unicode 'vocab_source': !!python/unicode '/wmt/vocab.bpe.32000' !!python/unicode 'vocab_target': !!python/unicode '/wmt/vocab.bpe.32000' INFO:tensorflow:Creating vocabulary lookup table of size 37007 INFO:tensorflow:Creating vocabulary lookup table of size 37007 INFO:tensorflow:Creating BidirectionalRNNEncoder in mode=train INFO:tensorflow: BidirectionalRNNEncoder: init_scale: 0.04 rnn_cell: cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 residual_combiner: add residual_connections: false residual_dense: false INFO:tensorflow:Creating AttentionLayerDot in mode=train INFO:tensorflow: AttentionLayerDot: {!!python/unicode 'num_units': 128} INFO:tensorflow:Creating AttentionDecoder in mode=train INFO:tensorflow: AttentionDecoder: !!python/unicode 'init_scale': 0.04 !!python/unicode 'max_decode_length': 100 !!python/unicode 'rnn_cell': cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 residual_combiner: add residual_connections: false residual_dense: false INFO:tensorflow:Creating ZeroBridge in mode=train INFO:tensorflow: ZeroBridge: {} INFO:tensorflow:Create CheckpointSaverHook. 4 ops no flops stats due to incomplete shapes. Consider passing run_meta to use run_time shapes. Parsing GraphDef... Parsing RunMetadata... Parsing OpLog... Preparing Views... INFO:tensorflow:_TFProfRoot (--/14.74m params) model/att_seq2seq/Variable (1, 1/1 params) model/att_seq2seq/decode/attention/att_keys/biases (128, 128/128 params) model/att_seq2seq/decode/attention/att_keys/weights (256x128, 32.77k/32.77k params) model/att_seq2seq/decode/attention/att_query/biases (128, 128/128 params) model/att_seq2seq/decode/attention/att_query/weights (128x128, 16.38k/16.38k params) model/att_seq2seq/decode/attention_decoder/decoder/attention_mix/biases (128, 128/128 params) model/att_seq2seq/decode/attention_decoder/decoder/attention_mix/weights (384x128, 49.15k/49.15k params) model/att_seq2seq/decode/attention_decoder/decoder/gru_cell/candidate/biases (128, 128/128 params) model/att_seq2seq/decode/attention_decoder/decoder/gru_cell/candidate/weights (512x128, 65.54k/65.54k params) model/att_seq2seq/decode/attention_decoder/decoder/gru_cell/gates/biases (256, 256/256 params) model/att_seq2seq/decode/attention_decoder/decoder/gru_cell/gates/weights (512x256, 131.07k/131.07k params) model/att_seq2seq/decode/attention_decoder/decoder/logits/biases (37007, 37.01k/37.01k params) model/att_seq2seq/decode/attention_decoder/decoder/logits/weights (128x37007, 4.74m/4.74m params) model/att_seq2seq/decode/target_embedding/W (37007x128, 4.74m/4.74m params) model/att_seq2seq/encode/bidi_rnn_encoder/bidirectional_rnn/bw/gru_cell/candidate/biases (128, 128/128 params) model/att_seq2seq/encode/bidi_rnn_encoder/bidirectional_rnn/bw/gru_cell/candidate/weights (256x128, 32.77k/32.77k params) model/att_seq2seq/encode/bidi_rnn_encoder/bidirectional_rnn/bw/gru_cell/gates/biases (256, 256/256 params) model/att_seq2seq/encode/bidi_rnn_encoder/bidirectional_rnn/bw/gru_cell/gates/weights (256x256, 65.54k/65.54k params) model/att_seq2seq/encode/bidi_rnn_encoder/bidirectional_rnn/fw/gru_cell/candidate/biases (128, 128/128 params) model/att_seq2seq/encode/bidi_rnn_encoder/bidirectional_rnn/fw/gru_cell/candidate/weights (256x128, 32.77k/32.77k params) model/att_seq2seq/encode/bidi_rnn_encoder/bidirectional_rnn/fw/gru_cell/gates/biases (256, 256/256 params) model/att_seq2seq/encode/bidi_rnn_encoder/bidirectional_rnn/fw/gru_cell/gates/weights (256x256, 65.54k/65.54k params) model/att_seq2seq/encode/source_embedding/W (37007x128, 4.74m/4.74m params) 2017-04-15 23:24:05.953735: 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. 2017-04-15 23:24:05.953770: 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. 2017-04-15 23:24:05.953788: 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. 2017-04-15 23:24:06.017526: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2017-04-15 23:24:06.017801: I tensorflow/core/common_runtime/gpu/gpu_device.cc:887] Found device 0 with properties: name: GRID K520 major: 3 minor: 0 memoryClockRate (GHz) 0.797 pciBusID 0000:00:03.0 Total memory: 3.94GiB Free memory: 3.91GiB 2017-04-15 23:24:06.017839: I tensorflow/core/common_runtime/gpu/gpu_device.cc:908] DMA: 0 2017-04-15 23:24:06.017856: I tensorflow/core/common_runtime/gpu/gpu_device.cc:918] 0: Y 2017-04-15 23:24:06.017875: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GRID K520, pci bus id: 0000:00:03.0) 2017-04-15 23:24:11.020252: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 6499 get requests, put_count=6464 evicted_count=1000 eviction_rate=0.154703 and unsatisfied allocation rate=0.174642 2017-04-15 23:24:11.020324: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:259] Raising pool_size_limit_ from 100 to 110 INFO:tensorflow:Saving checkpoints for 1 into /tmp/nmt_tutorial/model.ckpt. INFO:tensorflow:loss = 10.5189, step = 1 INFO:tensorflow:Prediction followed by Target @ Step 1 ==================================================================================================== wohnt suffici@@ suffici@@ wohnt übergreifende numbers ungalows lst ｈ@@ Kur@@ zum , ein ern@@ stes Problem . SEQUENCE_END 字@@ map Dom fascinating schäden tested 以 democratic verhindern uz@@ zzle ox Gebäu@@ Es liefert eine gute Diskussions@@ grundlage und ist insofern zu begrüßen . SEQUENCE_END seits Ty@@ Ty@@ ais Ligh@@ OSZE Greens Greens cosmetic überwiegend institutes institutes In den Regionen sind diese Situationen sehr , sehr unterschiedlich . SEQUENCE_END で BER@@ showed 竹@@ IG@@ IG@@ ehol@@ Gewis@@ kette night Allerdings scheint das nicht mach@@ bar zu sein . SEQUENCE_END forschung workshops obstacle Paci@@ ি Zweitens τ@@ embargo Warsaw klus Wir Sozialdemokraten lehnen diese liberale Ver@@ klärung ab . SEQUENCE_END europäisches 碁 lj@@ verab@@ ̇ ę 库@@ pose Säm@@ restruc@@ restruc@@ ser-@@ Darüber hinaus wird auf die Notwendigkeit einer verstärkten Transparenz hingewiesen . SEQUENCE_END compulsory was@@ embra@@ Flotte embra@@ verank@@ verank@@ Bil@@ Lassen Sie mich das begrün@@ den . SEQUENCE_END Galax@@ val@@ 太 exposed zone exposed Indien sierte stecken wines stecken erzielt säm@@ み ್ eh@@ Das , Herr Kommissar , ist das erste Geb@@ ot für den kommenden Zeitraum . SEQUENCE_END 山 obstacle Völker@@ sector Völker@@ Völker@@ Völker@@ Völker@@ Völker@@ Völker@@ Völker@@ sector yl Kli@@ Google Wei@@ Google Google Das , was wir heute machen , ist im Grunde genommen ein Är@@ g@@ ern@@ is . SEQUENCE_END ‟ Karl Dolomiten Car@@ begannen ☑ begannen sta Wor@@ Inclu@@ Ganzes Ganzes grossen 臈@@ 臈@@ possibilities 舩@@ Personen , die mit dieser Gefahr konfrontiert sind , haben deshalb hohen Anforderungen zu genügen . SEQUENCE_END 素@@ 素@@ etus 素@@ big big Früchte Früchte Früchte uma glad glad glad -K@@ Früchte glad rik 莞 Deshalb ist es erforderlich , die strukturelle Finanzierung stärker an die Schaffung von Arbeitsplätzen zu binden . SEQUENCE_END flat@@ night bury Konsum@@ wettbewerbs@@ Kö night Frau Präsidentin , zur Geschäftsordnung . SEQUENCE_END Vermark@@ Stadium Fortschritte tique spak@@ Werk graphy Lösung cafes ナ@@ adop@@ ナ@@ adres@@ Nach den Worten ihres Präsidenten ist sie dazu in der Lage . SEQUENCE_END 题 therapy Under 题 möbli@@ 题 olo@@ Rechts@@ orium 4 Schlu ohlen decentr@@ decentr@@ Bre@@ nutri@@ pts@@ windigkeit verringern Ankün@@ Wir erwarten von der Kommission , daß sie Problemen im Zusammenhang mit der Zusätz@@ lichkeit mehr Aufmerksamkeit widmet . SEQUENCE_END ritz Rain@@ wägen angewiesen Cubase Zerstör@@ 号 ald ald sta Musik@@ Fleisch ̇ Das tut mir leid , Herr Hän@@ sch und Herr Cox . SEQUENCE_END interactive interactive edit Chr@@ etus sicherzustellen etus door 出@@ Berichte Sicherheits@@ ber@@ ater für den Gef@@ ahr@@ gut@@ transport SEQUENCE_END Salon Restaurant INE Nep@@ reagiert reagiert Erhalt Erhalt INE INE INE 飛 approach Unsere Fraktion hält diesen Bericht für sehr gut und befürwortet ihn . SEQUENCE_END で appreci junc@@ never der@@ س@@ deal@@ she personalized ｫ touched matches Die Kommission muß sich also endlich mit dieser Frage befassen . SEQUENCE_END ℔ junc@@ 60 junc@@ mittel@@ Soldaten institute Thematik ɛ@@ Thematik Leitung 喀@@ Die Kluft zwischen Ar@@ m und Reich wird immer tiefer . SEQUENCE_END gefahren gefahren gefahren ʎ@@ ʎ@@ aufenthalt konfiguriert buchen änge absoluten margin margin Dänemark 1.@@ Jahren jek@@ ʎ@@ ʎ@@ ʎ@@ Rahmenbedingungen sind zur Verhinderung von Miß@@ brauch uner@@ läßlich , zum Beispiel durch das Kart@@ ell@@ recht . SEQUENCE_END Schu@@ Physi@@ Mein year-old kaner Mein Mein Mein ser-@@ Deshalb muß die Wettbewerbspolitik modernis@@ iert werden . SEQUENCE_END character character verbringen verbringen verbringen verbringen audiovisu@@ provides EU-Bürger EU-Bürger EU-Bürger provides St. St. gebor@@ lossen Zweitens habe ich Verständnis für die Unternehmen , die einen Verlust an Rechtssicherheit befürchten . SEQUENCE_END gage eim@@ gage gage gage gage news 195@@ ana gage ½ `` 路@@ Chicago valleys news O@@ ffen gesagt , glaube ich , daß diese Modernisierung zufriedenstell@@ end gewesen ist . SEQUENCE_END broke Politik embly rot@@ 式@@ Dienst@@ Championship ג@@ Und deshalb werden wir ihm zustimmen . SEQUENCE_END 1979 Eisenbahn 人@@ Erhol@@ Schengen 36 ved einm@@ BE@@ BE@@ ska olo@@ offering Kapitel geschehen geschehen kennt Nur in wenigen Ländern , zum Beispiel in Deutschland , gibt es eine spezielle Rechtsprechung . SEQUENCE_END Schu@@ Schu@@ ed-@@ Non-Smoking S-@@ Ergebnisse use@@ dairy Ergebnisse windigkeit Der Kollege Hän@@ sch hat Sie dort vertreten . SEQUENCE_END driven driven trieben etus trieben trieben gemeinsamen Having Market Having 350 trieben trieben Gent@@ Er ist ein Schritt in Richtung einer nachhaltigen Beschäftigungs@@ - und Entwicklungspolitik . SEQUENCE_END Ry@@ ungeachtet wort dynam@@ dynam@@ portugi@@ portugi@@ portugi@@ 䟩@@ 路@@ 路@@ Verbündeten fish Verbündeten nec@@ Datei@@ stream wort Jetzt sind wir aber an einen Punkt gekommen , wo wir die Wettbewerbspolitik weiter@@ entwickeln müssen . SEQUENCE_END Viz@@ Ruh@@ gebenen betriebe gebil@@ womit womit klausel Veri@@ Dänemark recorded womit NT fleisch fleisch fleisch fleisch schwer@@ womit gekehrt ratifiziert 气@@ Ich möchte zwei davon kurz zusammen@@ fassen , der Berichterstatter hat sie schon aufgegriffen , eine positive und eine negative . SEQUENCE_END 1979 hat Einstimmigkeit forcing judiciary Einstimmigkeit coupled Einstimmigkeit parameters success@@ &@@ &@@ reas@@ Si@@ eben Änderungs@@ vorschläge werden dieser Plenar@@ sitzung noch einmal vorgelegt . SEQUENCE_END eit raised raised malerweise olo@@ delegations duce unge Sektor Mittwoch radiation ght@@ Ich hoffe , daß dort in Ihrem Sinne entschieden wird . SEQUENCE_END sooner Γ@@ complimentary pursue pursue pursue β ferenzen solange Frankfurter modell bo ž@@ Uns Wies@@ Wies@@ never ト Ra@@ ück@@ zurückzu@@ Deshalb habe ich vorgeschlagen , den Grenz@@ wert für Fro@@ st auf -@@ 40 º@@ C her@@ abzu@@ setzen . SEQUENCE_END ==================================================================================================== 2017-04-15 23:24:17.223973: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 6609 get requests, put_count=5938 evicted_count=1000 eviction_rate=0.168407 and unsatisfied allocation rate=0.255409 2017-04-15 23:24:17.224014: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:259] Raising pool_size_limit_ from 193 to 212 INFO:tensorflow:Performing full trace on next step. 2017-04-15 23:24:18.562167: I tensorflow/stream_executor/dso_loader.cc:139] successfully opened CUDA library libcupti.so.8.0 locally INFO:tensorflow:Captured full trace at step 11 INFO:tensorflow:Saved run_metadata to /tmp/nmt_tutorial/run_meta INFO:tensorflow:Saved timeline to /tmp/nmt_tutorial/timeline.json INFO:tensorflow:Saved op log to /tmp/nmt_tutorial 2017-04-15 23:24:57.699164: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 8244 get requests, put_count=7553 evicted_count=1000 eviction_rate=0.132398 and unsatisfied allocation rate=0.209122 2017-04-15 23:24:57.699217: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:259] Raising pool_size_limit_ from 372 to 409 2017-04-15 23:25:04.325173: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 6803 get requests, put_count=6949 evicted_count=1000 eviction_rate=0.143906 and unsatisfied allocation rate=0.136116 2017-04-15 23:25:04.325223: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:259] Raising pool_size_limit_ from 792 to 871 2017-04-15 23:25:59.218218: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 314957 get requests, put_count=315021 evicted_count=1000 eviction_rate=0.00317439 and unsatisfied allocation rate=0.00356239 2017-04-15 23:25:59.218273: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:259] Raising pool_size_limit_ from 2049 to 2253 INFO:tensorflow:global_step/sec: 0.898519 INFO:tensorflow:loss = 10.2274, step = 101 (111.294 sec) INFO:tensorflow:global_step/sec: 1.30015 INFO:tensorflow:loss = 7.65212, step = 201 (76.914 sec) INFO:tensorflow:global_step/sec: 1.31208 INFO:tensorflow:loss = 7.23198, step = 301 (76.215 sec) INFO:tensorflow:global_step/sec: 1.29937 INFO:tensorflow:loss = 7.25867, step = 401 (76.961 sec) INFO:tensorflow:global_step/sec: 1.32052 INFO:tensorflow:loss = 7.26295, step = 501 (75.728 sec) INFO:tensorflow:global_step/sec: 1.28146 INFO:tensorflow:loss = 7.40051, step = 601 (78.036 sec) INFO:tensorflow:global_step/sec: 1.33482 INFO:tensorflow:loss = 7.07343, step = 701 (74.916 sec) INFO:tensorflow:Saving checkpoints for 740 into /tmp/nmt_tutorial/model.ckpt. INFO:tensorflow:global_step/sec: 1.30173 INFO:tensorflow:loss = 7.35884, step = 801 (76.821 sec) INFO:tensorflow:global_step/sec: 1.32331 INFO:tensorflow:loss = 7.20411, step = 901 (75.568 sec) INFO:tensorflow:Creating AttentionSeq2Seq in mode=eval INFO:tensorflow: AttentionSeq2Seq: !!python/unicode 'attention.class': !!python/unicode 'seq2seq.decoders.attention.AttentionLayerDot' !!python/unicode 'attention.params': {num_units: 128} !!python/unicode 'bridge.class': !!python/unicode 'seq2seq.models.bridges.ZeroBridge' !!python/unicode 'bridge.params': {} !!python/unicode 'decoder.class': !!python/unicode 'seq2seq.decoders.AttentionDecoder' !!python/unicode 'decoder.params': rnn_cell: cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 !!python/unicode 'embedding.dim': 128 !!python/unicode 'embedding.init_scale': 0.04 !!python/unicode 'embedding.share': false !!python/unicode 'encoder.class': !!python/unicode 'seq2seq.encoders.BidirectionalRNNEncoder' !!python/unicode 'encoder.params': rnn_cell: cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 !!python/unicode 'inference.beam_search.beam_width': 0 !!python/unicode 'inference.beam_search.choose_successors_fn': !!python/unicode 'choose_top_k' !!python/unicode 'inference.beam_search.length_penalty_weight': 0.0 !!python/unicode 'optimizer.clip_embed_gradients': 0.1 !!python/unicode 'optimizer.clip_gradients': 5.0 !!python/unicode 'optimizer.learning_rate': 0.0001 !!python/unicode 'optimizer.lr_decay_rate': 0.99 !!python/unicode 'optimizer.lr_decay_steps': 100 !!python/unicode 'optimizer.lr_decay_type': !!python/unicode '' !!python/unicode 'optimizer.lr_min_learning_rate': 1.0e-12 !!python/unicode 'optimizer.lr_staircase': false !!python/unicode 'optimizer.lr_start_decay_at': 0 !!python/unicode 'optimizer.lr_stop_decay_at': 2147483647 !!python/unicode 'optimizer.name': !!python/unicode 'Adam' !!python/unicode 'optimizer.params': {epsilon: 8.0e-07} !!python/unicode 'optimizer.sync_replicas': 0 !!python/unicode 'optimizer.sync_replicas_to_aggregate': 0 !!python/unicode 'source.max_seq_len': 50 !!python/unicode 'source.reverse': false !!python/unicode 'target.max_seq_len': 50 !!python/unicode 'vocab_source': !!python/unicode '/wmt/vocab.bpe.32000' !!python/unicode 'vocab_target': !!python/unicode '/wmt/vocab.bpe.32000' INFO:tensorflow:Creating vocabulary lookup table of size 37007 INFO:tensorflow:Creating vocabulary lookup table of size 37007 INFO:tensorflow:Creating BidirectionalRNNEncoder in mode=eval INFO:tensorflow: BidirectionalRNNEncoder: init_scale: 0.04 rnn_cell: cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 residual_combiner: add residual_connections: false residual_dense: false INFO:tensorflow:Creating AttentionLayerDot in mode=eval INFO:tensorflow: AttentionLayerDot: {!!python/unicode 'num_units': 128} INFO:tensorflow:Creating AttentionDecoder in mode=eval INFO:tensorflow: AttentionDecoder: !!python/unicode 'init_scale': 0.04 !!python/unicode 'max_decode_length': 100 !!python/unicode 'rnn_cell': cell_class: GRUCell cell_params: {num_units: 128} dropout_input_keep_prob: 0.8 dropout_output_keep_prob: 1.0 num_layers: 1 residual_combiner: add residual_connections: false residual_dense: false INFO:tensorflow:Creating ZeroBridge in mode=eval INFO:tensorflow: ZeroBridge: {} INFO:tensorflow:Starting evaluation at 2017-04-15-23:37:32 2017-04-15 23:37:33.285718: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GRID K520, pci bus id: 0000:00:03.0) INFO:tensorflow:Restoring parameters from /tmp/nmt_tutorial/model.ckpt-740 2017-04-15 23:37:36.968914: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:36.968989: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:36.969826: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:36.970315: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:36.970364: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:36.970572: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:36.970654: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:36.970804: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:37.477510: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:37.500012: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:37.502192: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:37.508629: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:37.509288: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:37.510966: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] 2017-04-15 23:37:37.511661: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] Traceback (most recent call last): File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main "__main__", fname, loader, pkg_name) File "/usr/lib/python2.7/runpy.py", line 72, in _run_code exec code in run_globals File "/root/seq2seq/bin/train.py", line 276, in tf.app.run() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/root/seq2seq/bin/train.py", line 271, in main schedule=FLAGS.schedule) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 111, in run return _execute_schedule(experiment, schedule) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 46, in _execute_schedule return task() File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 431, in train_and_evaluate self.train(delay_secs=0) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 230, in train monitors=self._train_monitors + extra_hooks) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 281, in new_func return func(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 430, in fit loss = self._train_model(input_fn=input_fn, hooks=hooks) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 978, in _train_model _, loss = mon_sess.run([model_fn_ops.train_op, model_fn_ops.loss]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 484, in run run_metadata=run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 820, in run run_metadata=run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 776, in run return self._sess.run(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 938, in run run_metadata=run_metadata)) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 1155, in after_run induce_stop = m.step_end(self._last_step, result) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 356, in step_end return self.every_n_step_end(step, output) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 662, in every_n_step_end name=self.name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 281, in new_func return func(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 518, in evaluate log_progress=log_progress) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 828, in _evaluate_model config=config_pb2.ConfigProto(allow_soft_placement=True)) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/evaluation.py", line 182, in _evaluate_once session.run(eval_ops, feed_dict) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 484, in run run_metadata=run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 820, in run run_metadata=run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 776, in run return self._sess.run(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 930, in run run_metadata=run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 776, in run return self._sess.run(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 778, in run run_metadata_ptr) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 982, in _run feed_dict_string, options, run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1032, in _do_run target_list, options, run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1052, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]] Caused by op u'model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape', defined at: File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main "__main__", fname, loader, pkg_name) File "/usr/lib/python2.7/runpy.py", line 72, in _run_code exec code in run_globals File "/root/seq2seq/bin/train.py", line 276, in tf.app.run() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/root/seq2seq/bin/train.py", line 271, in main schedule=FLAGS.schedule) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 111, in run return _execute_schedule(experiment, schedule) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 46, in _execute_schedule return task() File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 431, in train_and_evaluate self.train(delay_secs=0) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 230, in train monitors=self._train_monitors + extra_hooks) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 281, in new_func return func(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 430, in fit loss = self._train_model(input_fn=input_fn, hooks=hooks) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 978, in _train_model _, loss = mon_sess.run([model_fn_ops.train_op, model_fn_ops.loss]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 484, in run run_metadata=run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 820, in run run_metadata=run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 776, in run return self._sess.run(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/monitored_session.py", line 938, in run run_metadata=run_metadata)) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 1155, in after_run induce_stop = m.step_end(self._last_step, result) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 356, in step_end return self.every_n_step_end(step, output) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 662, in every_n_step_end name=self.name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 281, in new_func return func(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 518, in evaluate log_progress=log_progress) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 804, in _evaluate_model eval_dict = self._get_eval_ops(features, labels, metrics).eval_metric_ops File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1160, in _get_eval_ops features, labels, model_fn_lib.ModeKeys.EVAL) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1103, in _call_model_fn model_fn_results = self._model_fn(features, labels, **kwargs) File "/root/seq2seq/bin/train.py", line 182, in model_fn return model(features, labels, params) File "seq2seq/models/model_base.py", line 146, in __call__ return self._build(features, labels, params) File "seq2seq/models/seq2seq_model.py", line 298, in _build decoder_output, _, = self.decode(encoder_output, features, labels) File "seq2seq/graph_utils.py", line 38, in func_wrapper return templated_func(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/template.py", line 277, in __call__ return self._call_func(args, kwargs, check_for_new_variables=False) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/template.py", line 217, in _call_func result = self._func(*args, **kwargs) File "seq2seq/models/basic_seq2seq.py", line 125, in decode labels) File "seq2seq/models/basic_seq2seq.py", line 88, in _decode_train return decoder(decoder_initial_state, helper_train) File "seq2seq/graph_module.py", line 57, in __call__ return self._template(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/template.py", line 268, in __call__ return self._call_func(args, kwargs, check_for_new_variables=False) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/template.py", line 217, in _call_func result = self._func(*args, **kwargs) File "seq2seq/decoders/rnn_decoder.py", line 120, in _build maximum_iterations=maximum_iterations) File "seq2seq/contrib/seq2seq/decoder.py", line 287, in dynamic_decode swap_memory=swap_memory) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2623, in while_loop result = context.BuildLoop(cond, body, loop_vars, shape_invariants) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2456, in BuildLoop pred, body, original_loop_vars, loop_vars, shape_invariants) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2406, in _BuildLoop body_result = body(*packed_vars_for_body) File "seq2seq/contrib/seq2seq/decoder.py", line 240, in body decoder_finished) = decoder.step(time, inputs, state) File "seq2seq/decoders/attention_decoder.py", line 167, in step self.compute_output(cell_output) File "seq2seq/decoders/attention_decoder.py", line 121, in compute_output values_length=self.attention_values_length) File "seq2seq/graph_module.py", line 57, in __call__ return self._template(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/template.py", line 268, in __call__ return self._call_func(args, kwargs, check_for_new_variables=False) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/template.py", line 217, in _call_func result = self._func(*args, **kwargs) File "seq2seq/decoders/attention.py", line 104, in _build scope="att_keys") File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args return func(*args, **current_args) File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1433, in fully_connected outputs = layer.apply(inputs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/layers/base.py", line 320, in apply return self.__call__(inputs, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/layers/base.py", line 290, in __call__ outputs = self.call(inputs, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/layers/core.py", line 140, in call [0]]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 2378, in tensordot a_reshape, a_free_dims, a_free_dims_static = _tensordot_reshape(a, a_axes) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 2345, in _tensordot_reshape reshaped_a = array_ops.reshape(array_ops.transpose(a, perm), new_shape) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 2510, in reshape name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2336, in create_op original_op=self._default_original_op, op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1228, in __init__ self._traceback = _extract_stack() InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 303104 values, but the requested shape has 0 [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]]