In tensorflow, how to calculate sequence loss using output from dynamic_decode -


hi fellow tensorflowers, trying implement sequence sequence model using new seq2seq module under development , release tf1.0 , 1.1. there dynamic_decode function here returns logits in form of rnn_output. then, need calculate loss using output of rnn. when run naively, calling tf.contrib.seq2seq.loss.sequence_loss (rnn_output, weights, logits) crashes with:

invalidargumenterror (see above traceback): incompatible shapes: [1856,1,1024] vs. [9600,1,1024]          [[node: optimize/gradients/loss/sequence_loss/sampled_softmax_loss/mul_grad/broadcastgradientargs = broadcastgradientargs[t=dt_int32, _device="/job:localhost/replica:0/task:0/gpu:0"](optimize/gradients/loss/sequence_loss/sampled_softmax_loss/mul_grad/shape/_3099, optimize/gradients/loss/sequence_loss/sampled_softmax_loss/mul_grad/shape_1/_3101)]]          [[node: optimize/gradients/add/_824 = _recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:3", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_2787_optimize/gradients/add", tensor_type=dt_float, _device="/job:localhost/replica:0/task:0/gpu:3"](^_cloopmaindynamicdecoderwithattention/decoder/decoder/while/basicdecoderstep/multi_rnn_cell/cell_1/multi_rnn_cell/cell_2/lstm_cell/zeros/_128)]]

which natural, since rnn_output dynamicly shaped. have 2 possible solutions: 1. "pack" dynamic tensor tensor of size equal maximum allowed length. don't know how pack dynamic tensor tensor of fixed size, has smth new interfaces dynamic shape: tf.while_loop , tensorarrays. great hear advice on 2. dynamically calculate sequence_loss. knowledge of inner tensorflow implementation limited assess correctly whether it's easy do. suggestions here?

the general question

what right approach calculate sampled/normal softmax cross-entropy loss dynamicaly shaped rnn_output of dynamic_decode?

i have following code:

decoder_outputs, decoder_state = seq2seq.dynamic_decode(my_decoder, output_time_major=false, parallel_iterations=512,                    swap_memory = true)  self.logits = decoder_outputs.rnn_output self.loss = loss.sequence_loss(self.logits, tf.transpose(tf.stack(targets), [1,0], name="targets_"),                                                  tf.transpose(tf.stack(self.target_weights), [1,0], name="weights_"),                                                  softmax_loss_function = softmax_loss_function)

ipdb> tf.version '1.1.0-rc0'

python: 2.7

i guess using greedyembeddinghelper? during training, should use tf's "traininghelper". output dimension should match target dimension because @ ever time step, target used input.


Comments

Post a Comment

Popular posts from this blog

inversion of control - Autofac named registration constructor injection -

does autofac support specifying registration name in components' constructors? example: ninject's namedattribute . you need use autofac.extras.attributed package on top achieve this so let's have 1 interface , 2 classes: public interface ihello { string sayhello(); } public class englishhello : ihello { public string sayhello() { return "hello"; } } public class frenchhello : ihello { public string sayhello() { return "bonjour"; } } then have consumer class, in want select instance injected: public class helloconsumer { private readonly ihello helloservice; public helloconsumer([withkey("en")] ihello helloservice) { if (helloservice == null) { throw new argumentnullexception("helloservice"); } this.helloservice = helloservice; } public string sayhello() { return this.helloservice.sayhello()...
Read more

verilog - Systemverilog dynamic casting issues -

i've code snippet following in testbench function void write_to_port( my_data_type_base data ); my_data_type_extended data_ext; if(!$cast(data_ext, data)); `uvm_error(get_type_name(), "failed cast"); `uvm_info(get_name(), $psprintf("data_ext :\n%s", data_ext.sprint()), uvm_medium) // write data_ext out port.... endfunction when run it, i'm getting uvm_error "failed cast." i'm not quire sure why $cast not returning 1. can see, i'm printing out extended class data item after casting uvm_info. can see it's being cast properly. if don't use $cast if condition, don't runtime error. isn't coding practice use if dynamic cast check if $cast returning 1 ? what might reason behind cast not returning 1 in above case? i think semicolon on line 'if' not belong? i think consumes if statement, , uvm_error executes regardless of how if evaluates: if(!$cast(data_ext, data)); <- no semico...
Read more

ios - Change Storyboard View using Seague -

i have following code checks connection server, , depending on want change views if no connection found. nsstring *connect = [nsstring stringwithcontentsofurl:[nsurl urlwithstring:@"http://myserver.com"] encoding:nsutf8stringencoding error:nil]; if (connect == null) { [self performseguewithidentifier:@"network_failure" sender:self]; } else { // other code here } my problem not change views. have added storyboard segue between 2 views identifier of network_failure . not have navigation controller or that, problem? thanks help! no not problem. first of all, in objectivec exists nil object oriented null . must use that. so: if(connect == nil) or better: if(!connect) so due fact nil not same of null , probably code does't enter in if scope . you have been able discover breakpoint. anyway: be sure set trigger segue (line) 2 view controller , , name network_failure (that not best name. should instead view1toview2 ) as, m...
Read more