python - I can't figure out how to feed a Placeholder by data from matlab -

-

i trying implement simple feed forward network. however, can't figure out how feed placeholder data matlab. example:

import tensorflow tf import numpy np import scipy.io scio import math  # # create data train_input=scio.loadmat('/users/liutianyuan/desktop/image_restore/data/input_for_tensor.mat') train_output=scio.loadmat('/users/liutianyuan/desktop/image_restore/data/output_for_tensor.mat') x_data=np.float32(train_input['input_for_tensor']) y_data=np.float32(train_output['output_for_tensor'])  print x_data.shape print y_data.shape ## create tensorflow structure start ### def add_layer(inputs, in_size, out_size, activation_function=none):     weights = tf.variable(tf.random_uniform([in_size,out_size], -4.0*math.sqrt(6.0/(in_size+out_size)), 4.0*math.sqrt(6.0/(in_size+out_size))))     biases = tf.variable(tf.zeros([1, out_size]))     wx_plus_b = tf.matmul(inputs, weights) + biases     if activation_function none:         outputs = wx_plus_b     else:         outputs = activation_function(wx_plus_b)     return outputs  xs = tf.placeholder(tf.float32, [none, 256]) ys = tf.placeholder(tf.float32, [none, 1024]) y= add_layer(xs, 256, 1024, activation_function=none)  loss = tf.reduce_mean(tf.square(y - ys)) optimizer = tf.train.gradientdescentoptimizer(0.1) train = optimizer.minimize(loss)  init = tf.initialize_all_variables() ### create tensorflow structure end ###  sess = tf.session() sess.run(init)    step in range(201):     sess.run(train)     if step % 20 == 0:        print(step, sess.run(loss,feed_dict={xs: x_data, ys: y_data}))

gives me following error:

/usr/local/cellar/python/2.7.12_2/frameworks/python.framework/versions/2.7/bin/python2.7 /users/liutianyuan/pycharmprojects/untitled1/easycode.py  (1, 256)  (1, 1024)  traceback (most recent call last):   file "/users/liutianyuan/pycharmprojects/untitled1/easycode.py", line 46, in <module>     sess.run(train)    file "/library/python/2.7/site-packages/tensorflow/python/client/session.py", line 340, in run     run_metadata_ptr)    file "/library/python/2.7/site-packages/tensorflow/python/client/session.py", line 564, in _run     feed_dict_string, options, run_metadata)    file "/library/python/2.7/site-packages/tensorflow/python/client/session.py", line 637, in _do_run     target_list, options, run_metadata)    file "/library/python/2.7/site-packages/tensorflow/python/client/session.py", line 659, in _do_call     e.code)  tensorflow.python.framework.errors.invalidargumenterror: **you must feed value placeholder tensor 'placeholder' dtype float**      [[node: placeholder = placeholder[dtype=dt_float, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]  caused op u'placeholder', defined at:    file "/users/liutianyuan/pycharmprojects/untitled1/easycode.py", line 30, in <module>     xs = tf.placeholder(tf.float32, [none, 256])    file "/library/python/2.7/site-packages/tensorflow/python/ops/array_ops.py", line 762, in placeholder     name=name)    file "/library/python/2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 976, in _placeholder     name=name)    file "/library/python/2.7/site-packages/tensorflow/python/ops/op_def_library.py", line 655, in apply_op     op_def=op_def)    file "/library/python/2.7/site-packages/tensorflow/python/framework/ops.py", line 2154, in create_op     original_op=self._default_original_op, op_def=op_def)    file "/library/python/2.7/site-packages/tensorflow/python/framework/ops.py", line 1154, in __init__     self._traceback = _extract_stack()

i have checked both type , shape of x_data , y_data, seams corret. have no ideal goes wrong.

your train operation depends on placeholders xs , ys, must feed values placeholders when call sess.run(train).

a common way divide input data mini-batches:

batch_size = ... step in range(201):     # n.b. you'll need code handle cases start_index and/or end_index     # wrap around end of x_data , y_data.     start_index = step * batch_size     end_index = (step + 1) * batch_size     start_index = sess.run(train, {xs: x_data[start_index:end_index,:],                                    ys: y_data[start_index:end_index,:]})

the code in example started. more flexible way of generating data feeding, see mnist dataset example in tf.learn codebase.


Comments

Post a Comment

Popular posts from this blog

Formatting string according to pattern without regex in php -

-
how can format arbitrary string according flexible pattern? solution came using regular expressions, need 2 "patterns" (one search , 1 output). example: $str = '123abc5678"; desired output: 12.3ab-c5-67.8 i use pattern in variable (one user can define without knowledge of regular expressions) this: $pattern = '%%.%%%-%%-%%.%'; so user have use 2 different characters (% , .) a solution regex this: $str = '123abc5678'; $pattern_src = '@(.{2})(.{3})(.{2})(.{2})(.{1})@'; $pattern_rpl = "$1.$2-$3-$4.$5"; $res = preg_replace($pattern_src, $pattern_rpl, $str); //$res eq 12.3ab-c5-67.8 way complicated since user need define $pattern_src , $pattern_rpl. if string vary in length, more complex explain. yes, write function/parser builds required regular expressions based on simple user pattern %%.%%%-%%-%%.%. wonder if there "built in" way achieve php? thinking sprintf etc., doesn't seem trick. ideas? ...
Read more

c - zlib and gdi32 with OpenSSL? -

-
this follow question undefined reference rsa_generate_key in openssl? have openssl program generate rsa key, follows : #include <stdio.h> #include <openssl/rsa.h> #include <openssl/pem.h> int main(int argc, char* argv[]) { rsa *r = null; int ret; r = rsa_new(); bignum *bne = null; ret = rsa_generate_key_ex(r, 2048, bne, null); return 0; } when compile gcc -i../include rsatest.c -lcrypto -l. i undefined reference errors functions in libraries gdi32 , zlib. so correct this, have add -lz , -lgdi32, as gcc -i../include/ rsatest.c -lcrypto -lz -lgdi32 -l. my question is, aren't static libcrypto , libssl self sufficient? in why having add libraries make work? there option should have added while compiling library prevent this? i'm using 64 bit windows mingw compiler. made openssl library of msys , make.
Read more

java - inputmismatch exception -

-
Image
this question has answer here: scanner skipping nextline() after using next(), nextint() or other nextfoo()? 14 answers import java.util.*; public class ngg { static scanner numberentered; static scanner userinput = new scanner(system.in); static int guessednumber; static int randomnumber = (int) (math.random()* 11); static scanner reply; static string answer; public static void main(string[] args) { guesschecker(guessednumber); } public static void guesschecker(int userguess) { while (userguess != randomnumber) { intro(); userguess = intchecker(); if (userguess == randomnumber) { system.out.println("congradulations!"); system.exit(0); } else { system.out.println("that incorrect!");...
Read more