neural network - about tensorflow backpropagation -


if have 2 neural networks , b, , use output of network feed input(placeholder) of network b. , use optimizer minimize loss of network b, can network a's parameters updated backpropagation?

yes, if "feed" done in tensorflow; no, if manually.

specifically, if evaluate a, train b outputs manually fed in (say, feed dict), not change, because not involved in training stage.

if set input of b network output of op in (instead of tf.placeholder, instance), can train combined network, update a's parameters. in case, though, you're training combined network "ab", not 2 separate networks.

a concrete example:

import numpy np import tensorflow tf  # network a_input = tf.placeholder(tf.float32, [none,100]) a_weights = tf.variable(tf.random_normal([100,10])) a_output = tf.matmul(a_input,a_weights)  # b network b_input = tf.placeholder(tf.float32, [none,10]) b_weights = tf.variable(tf.random_normal([10,5])) b_output = tf.matmul(b_input,b_weights)  # ab network ab_input = a_output ab_weights = tf.variable(tf.random_normal([10,5])) ab_output = tf.matmul(ab_input,ab_weights)  test_inputs = np.random.rand(17,100) sess = tf.session() sess.run(tf.global_variables_initializer()) a_out = sess.run(a_output, feed_dict={a_input: test_inputs}) print 'a output shape:',a_out.shape b_out = sess.run(b_output, feed_dict={b_input: a_out}) print 'b output shape:',b_out.shape  ab_out = sess.run(ab_output, feed_dict={a_input: test_inputs}) print 'ab output shape:',ab_out.shape

in first case, we've fed network b outputs network using feed_dict. evaluating network in tensorflow, pulling results python, evaluating network b in tensorflow. if try train network b in fashion, you'll update parameters in network b.

in second case, we've fed "b" part of network ab directly connecting outputs of network input of network ab. evaluating network ab never pulls intermediate results of network python, if train network ab in fashion, can update parameters combined network. (note: training inputs feed a_input of network ab, not intermediate tensor ab_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