python - InvalidArgumentError In Tensorflow Placeholder -


trying create simple perceptron 2 hidden layers learns function defined f. problem i'm having (besides not having clue i'm doing) i'm getting long stack trace (at bottom) think originating @ line y_ defined. final part of error is:

invalidargumenterror (see above traceback): must feed value placeholder tensor 'placeholder_1' dtype float

code:

import tensorflow tf import numpy np  def f(x):     y1 = 2.41*x[0] + 0.09 + np.random.normal()     y2 = 3.84*x[1] + 5.3 + np.random.normal()     y3 = 0.79*x[2] + 13.0 + np.random.normal()      return [y1, y2, y3]  x = tf.placeholder(tf.float32, shape = ([none, 3])) y_ = tf.placeholder(tf.float32, shape = ([none, 3]))  w1 = tf.variable(tf.zeros([3, 10])) b = tf.variable(tf.zeros([10]))  x_med = tf.matmul(x, w1) + b  w2 = tf.variable(tf.zeros([10, 3]))  y = tf.matmul(x_med, w2)  dif = tf.subtract(y_, y) sqrd = tf.reduce_mean(tf.multiply(dif, dif)) / 3  #loss = tf.reduce_sum( tf.matmul(np.array(y_ - y), np.array(y_ - y))) loss = tf.reduce_sum(sqrd)  optimizer = tf.train.gradientdescentoptimizer(learning_rate = 0.03).minimize(loss)  correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))  x_train = [] y_train = [] = 0 while < 100000:     x1 = np.random.uniform(0, 100)     x2 = np.random.uniform(0, 100)     x3 = np.random.uniform(0, 100)      x_train.append([x1, x2, x3])     y_train.append(f([x1, x2, x3]))      += 1  x_test = [] y_test = [] = 0 while < 250:     x1 = np.random.uniform(0, 100)     x2 = np.random.uniform(0, 100)     x3 = np.random.uniform(0, 100)      x_test.append([x1, x2, x3])     y_test.append(f([x1, x2, x3]))      += 1  epochs = 1 init_op = tf.global_variables_initializer() tf.session() sess:     # initialise variables     sess.run(init_op)     epoch in range(epochs):          avg_cost = 0          batchnum = 0          batch_size = 10          total_batch = int(len(x_train) / batch_size)          in range(total_batch):              batch_x = x_train[batchnum: batchnum + batch_size]              batch_y = y_train[batchnum: batchnum + batch_size]              batchnum += batch_size              _, c = sess.run([optimizer, loss],                            feed_dict={x:batch_x, y: batch_y})              print(c)              avg_cost += c / total_batch           print("epoch: " + str(epoch) + " avg cost: " + str(avg_cost))

stack trace:

traceback (most recent call last):   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1039, in _do_call     return fn(*args)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1021, in _run_fn     status, run_metadata)   file "c:\users\allbee\anaconda3\lib\contextlib.py", line 89, in __exit__     next(self.gen)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 466, in raise_exception_on_not_ok_status     pywrap_tensorflow.tf_getcode(status)) tensorflow.python.framework.errors_impl.invalidargumenterror: must feed value placeholder tensor 'placeholder_1' dtype float          [[node: placeholder_1 = placeholder[dtype=dt_float, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]  during handling of above exception, exception occurred:  traceback (most recent call last):   file "anntest.py", line 74, in <module>     feed_dict={x:batch_x, y: batch_y})   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 778, in run     run_metadata_ptr)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 982, in _run     feed_dict_string, options, run_metadata)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1032, in _do_run     target_list, options, run_metadata)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1052, in _do_call     raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.invalidargumenterror: must feed value placeholder tensor 'placeholder_1' dtype float          [[node: placeholder_1 = placeholder[dtype=dt_float, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]  caused op 'placeholder_1', defined at:   file "anntest.py", line 12, in <module>     y_ = tf.placeholder(tf.float32, shape = ([none, 3]))   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1507, in placeholder     name=name)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 1997, in _placeholder     name=name)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 768, in apply_op     op_def=op_def)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2336, in create_op     original_op=self._default_original_op, op_def=op_def)   file "c:\users\allbee\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1228, in __init__     self._traceback = _extract_stack()  invalidargumenterror (see above traceback): must feed value placeholder tensor 'placeholder_1' dtype float          [[node: placeholder_1 = placeholder[dtype=dt_float, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

i suspect problem stems line, feed y instead of y_:

         _, c = sess.run([optimizer, loss],                        feed_dict={x:batch_x, y: batch_y})

rewriting following should work:

         _, c = sess.run([optimizer, loss],                        feed_dict={x:batch_x, y_: batch_y})

Comments

Post a Comment

Popular posts from this blog

Is there a better way to structure post methods in Class Based Views -

i'm using class based views in django , never specify url in ajax calls , omit action parameter in form because know these requests go through post method of class based view. notice view - profile page make many requests depending on user updating on page - post method become convoluted , if/else mess example: def post(self, request, *args, **kwargs): # handle user changing available date if request.post.get('availabledate') != none: self.updateavailabledate(request) return jsonresponse({'result':'success'}) if request.post.get('newprojectname') != none: creative_user = creativeuserprofile.objects.get(id = request.user.id) project = project.create_project(creative_user, request.post['newprojectname']) project.save() return jsonresponse({'projectid': project.id }) if request.post.get('projectimage') != none , request.files['file']: proj
Read more

performance - Why is XCHG reg, reg a 3 micro-op instruction on modern Intel architectures? -

i'm doing micro-optimization on performance critical part of code , came across sequence of instructions (in at&t syntax): add %rax, %rbx mov %rdx, %rax mov %rbx, %rdx i thought had use case xchg allow me shave instruction , write: add %rbx, %rax xchg %rax, %rdx however, dimay found agner fog's instruction tables , xchg 3 micro-op instruction 2 cycle latency on sandy bridge, ivy bridge, broadwell, haswell , skylake. 3 whole micro-ops , 2 cycles of latency! 3 micro-ops throws off 4-1-1-1 cadence , 2 cycle latency makes worse original in best case since last 2 instructions in original might execute in parallel. now... cpu might breaking instruction micro-ops equivalent to: mov %rax, %tmp mov %rdx, %rax mov %tmp, %rdx where tmp anonymous internal register , suppose last 2 micro-ops run in parallel latency 2 cycles. given register renaming occurs on these micro-architectures, though, doesn't make sense me done way. why wouldn't register renamer
Read more

jquery - Responsive Navbar with Sub Navbar -

good day, forgive me nav vocabulary not best. if question confusing apologize. i'm working on navigation bar needs centered on page @ 768px , above. items in nav open (or perhaps toggle) subnav lives directly below. these nav should appear centered on page. i have been able work through responsive portion of nav bar, having main items align vertically , sub nav menu of each item roll out below, , gave them indent separation. working well. however, issue not responsive side, behavior @ width greater 768px. happens toggling menu's sub navigation pushes other main items down page below sub nav. here's code: $(document).ready(function () { //stick in fixed 100% height behind navbar don't wrap $('#slide-nav.navbar-inverse').after($('<div class="inverse" id="navbar-height-col"></div>')); $('#slide-nav.navbar-default').after($('<div id="navbar-height-col"></d
Read more