Wrong variable scope when using tensorflow.python.layers.core.Dense -


i have following code implement decoder of seq2seq model using tensorflow.

    tf.variable_scope('decoder'):         if self._embedding none:             self._embedding = create_embedding(self._embedding_size,                                                self._vocab_size)             self._build_decoder_cell()          tf.variable_scope('output'):             self._output_layer = _core_layers.dense(                 self._vocab_size, name='output_layer')          _, batch_size, _ = tf.unstack(tf.shape(encoder_outputs))          # train or eval         if targets not none:             eos = tf.fill([1, batch_size], self._eos_id)             targets = tf.concat([targets, eos], axis=0)              embedding_targets = tf.nn.embedding_lookup(                 self._embedding, targets)              helper = tf.contrib.seq2seq.traininghelper(                 embedding_targets, sequence_length=lengths, time_major=true)              decoder = tf.contrib.seq2seq.basicdecoder(                 self._cell, helper, encoder_final_state)              outputs, final_state, _ = tf.contrib.seq2seq.dynamic_decode(                 decoder, output_time_major=true, swap_memory=true)              logits = self._output_layer(outputs.rnn_output)          # inference         else:             import pdb; pdb.set_trace()             bos = tf.fill([batch_size], self._bos_id)              helper = tf.contrib.seq2seq.greedyembeddinghelper(                 self._embedding, bos, self._eos_id)              decoder = tf.contrib.seq2seq.basicdecoder(                 self._cell,                 helper,                 encoder_final_state,                 output_layer=self._output_layer)              outputs, final_state, _ = tf.contrib.seq2seq.dynamic_decode(                 decoder,                 maximum_iterations=tf.reduce_max(lengths),                 output_time_major=true,                 swap_memory=true)              logits = outputs.rnn_output      return logits, final_state

the tensorflow.python.layers.core.dense layer seems has undetermined scope until 1 calls instance since build function (where weight/kernel , bias defined) called in __call__ function. creating 1 graph training , 1 graph inference, save graph when training , restore when inference. however, got notfounderror (see above traceback): key basic_seq2seq/decoder/decoder/output_layer/kernel not found in checkpoint.

by using checkpoint inspect tool, find saved training graph has tensor basic_seq2seq/decoder/output_layer/kernel when inference graph request basic_seq2seq/decoder/decoder/output_layer/kernel.

even though output layer of both graphs created before if-else statement, have different names.

how can solve this? in advance.


Comments

Post a Comment

Popular posts from this blog

Sort a complex associative array in PHP -

this question has answer here: php sort array subarray value 5 answers i have associative array in php like: $newarray1 = array ( [producta] => array ( [link] => http://sanjosespartan.com/blog/products/agile-java-development/ [visitcount] => 4 ) [productd] => array ( [link] => http://sanjosespartan.com/blog/products/intro-to-go/ [visitcount] => 1 ) [productg] => array ( [link] => http://sanjosespartan.com/blog/products/node-js-for-developers/ [visitcount] => 1 ) [productb] => array ( [link] => http://sanjosespartan.com/blog/products/beginning-mysql/ [visitcount] => 1 ) [productc] => array ( [link] => http://sanjosespartan.com/blog/products/computer-networks/ [visitcount] => 1 ) ...
Read more

vb.net - How to ignore if a cell is empty nothing -

how use roscolor() ignore value (like empty cell) ? color row if value upper 5 when there nothing in cell, want ignore roscolor() apply, how? public sub roscolor() integer = 0 quotedatagridview1.rows.count() - 1 step +1 dim val integer val = quotedatagridview1.rows(i).cells(3).value if val = vbempty quotedatagridview1.rows(i).defaultcellstyle.backcolor = color.white elseif val < 5 quotedatagridview1.rows(i).defaultcellstyle.backcolor = color.red elseif val > 5 , val < 10 quotedatagridview1.rows(i).defaultcellstyle.backcolor = color.lightyellow end if next end sub you can check empty value following public sub roscolor() integer = 0 quotedatagridview1.rows.count() - 1 step +1 dim val = quotedatagridview1.rows(i).cells(3).value if isdbnull(val) or val nothing quotedatagridview1.rows(i).defaultcellstyle.backcolor = color.white ...
Read more

recursion - Can every recursive algorithm be improved with dynamic programming? -

i first year undergraduate csc student looking competitive programming. recursion involves defining , solving sub problems. understand, top down dynamic programming (dp) involves memoizing solutions sub problems reduce time complexity of algorithm. can top down dp used improve efficiency of every recursive algorithm overlapping sub problems? dp fail work , how can identify this? the short answer is: yes. however, there constraints. obvious 1 recursive calls must overlap. i.e. during execution of algorithm, recursive function must called multiple times same parameters. lets truncate recursion tree memoization. can use memoization reduce number of calls. however, reduction of calls comes price. need store results somewhere. next obvious constraint need have enough memory. comes not-so obvious constraint. memory access requires time. first need find result stored , maybe copy location. in cases, might faster let recursion calculate result instead of loading somewher...
Read more