nengwp
commented
4 years ago 设置use_beamsearch_decode = True时，它显示ValueError：t必须具有静态已知的等级。
在主 run_program（hparams，FLAGS）中的行755中的 文件“ seq2seq_sleep_sleep-EDF.py”，在运行程序 logits中的行“ seq2seq_sleep_sleep-EDF.py”，行607 ，pred_outputs，loss，optimizer，dec_states = build_whole_model（hparams，char2numY输入，目标，dec_inputs，keepprob） 文件“ seq2seq_sleep_sleep-EDF.py”，第385行，在build_whole_model logits中，pred_outputs，dec_states = build_network（hparams，char2numY，inputs，dec_inputs，keepprob） 文件“ seq2ED-seq_sleep”。 295，位于build_network编码器状态 = tf.contrib.seq2seq.tile_batch（encoder_state，multiplier = hparams.beam_width） 文件“ /home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/contrib/seq2seq/ python / ops / beam_search_decoder.py”，第126行，在tile_batch中 返回nest.mapstructure（lambda t：_tilebatch（t，multiplier），t） 文件“ /home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/python/util/nest.py”，第515行，在map_structure 结构[0]中，[项中的x为func（ x）]， 文件“ /home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/python/util/ nest.py”，第515行，位于 结构[0]中，[用于x项的func（ x）]， 文件“ /home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/ contrib / seq2seq / python / ops / beam_search_decoder.py“，第126行， 返回nest.mapstructure（lambda t：_tilebatch（t，multiplier），t） _tile_batch中的文件“ /home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/contrib/seq2seq/python/ops/beam_search_decoder.py”第85行 提高ValueError（“ t必须静态已知等级”） ValueError：t必须具有静态已知等级
I encountered the same difficulty, did you solve this problem, and if it solves, can you share the solution?
When setting the use_beamsearch_decode=True, it shows the ValueError: t must have statically known rank.
File "seq2seq_sleep_sleep-EDF.py", line 755, in main run_program(hparams,FLAGS) File "seq2seq_sleep_sleep-EDF.py", line 607, in run_program logits, pred_outputs, loss, optimizer,dec_states = build_whole_model(hparams,char2numY,inputs,targets, dec_inputs, keepprob) File "seq2seq_sleep_sleep-EDF.py", line 385, in build_whole_model logits, pred_outputs,dec_states = build_network(hparams,char2numY,inputs, dec_inputs, keepprob) File "seq2seq_sleep_sleep-EDF.py", line 295, in build_network encoder_state = tf.contrib.seq2seq.tile_batch(encoder_state, multiplier=hparams.beam_width) File "/home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/contrib/seq2seq/python/ops/beam_search_decoder.py", line 126, in tile_batch return nest.mapstructure(lambda t: _tilebatch(t, multiplier), t) File "/home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/python/util/nest.py", line 515, in map_structure structure[0], [func(x) for x in entries], File "/home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/python/util/nest.py", line 515, in
structure[0], [func( x) for x in entries],
File "/home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/contrib/seq2seq/python/ops/beam_search_decoder.py", line 126, in
return nest.mapstructure(lambda t: _tilebatch(t, multiplier), t)
File "/home/Student/s4518991/.local/lib/python3.6/site-packages/tensorflow/contrib/seq2seq/python/ops/beam_search_decoder.py", line 85, in _tile_batch
raise ValueError("t must have statically known rank")
ValueError: t must have statically known rank