python - OutOfRangeError : FIFOQueue 'batch/fifo_queue' in tf.train.batch -


i want solve problem. checked num_epochs=none of tf.train.slice_input_producer , reduced batch_size 64 16. however, outofrangeerror not disappear. tried everything(on stackoverflow 'outofrange, fifoqueie, insufficient elements, train.batch, slice_input_producer'... if know solving problem, please let me know.

import matplotlib.pyplot plt import tensorflow tf import numpy np import os import time import re datetime import datetime  datetime import timedelta nets import pam_cnn, fd_cnn import load_jpeg_with_tensorflow  flags = tf.app.flags flags = flags.flags flags.height = 250 flags.width = 250 flags.num_classes = 2 flags.batch_size = 16  ######################################################## load data ######################################################## main_dir = './data/lfwdata/lfw_train/' log_dir = 'tmp/pam/'  num_classes = 2 # number of bubbles x 2  # batch_img, batch_label = load_jpeg_with_tensorflow.read_data_batch(train_dir, 'trainimagelist.csv', height, width, #                                                                    num_channels, batch_size=batch_size)  ######################################################## placeholder variable ########################################################  x = tf.placeholder(tf.float32, shape=[none, flags.height, flags.width, 3], name='input') y = tf.placeholder(tf.float32, shape=[none, num_classes], name='label') y_cls = tf.argmax(y, dimension=1)  image_batch, label_batch, file_batch = load_jpeg_with_tensorflow.read_data_batch(main_dir+'trainimagelist.csv', flags.height, flags.width, flags.batch_size)  ######################################################## training process ########################################################  keep_prob = tf.placeholder(tf.float32) prediction = fd_cnn.build_model(x, keep_prob) loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y)) tf.summary.scalar('loss', loss)  optimizer = tf.train.adamoptimizer(learning_rate=1e-3).minimize(loss)  validate_image_batch, validate_label_batch, validate_file_batch = load_jpeg_with_tensorflow.read_data_batch(main_dir+'testimagelist.csv', flags.height, flags.width, flags.batch_size) label_max = tf.argmax(y, 1) pre_max = tf.argmax(prediction, 1) correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) tf.summary.scalar('accuracy', accuracy)  starttime = datetime.now() iteration = 20  summary = tf.summary.merge_all() ######################################################## tensorflow run ######################################################## tf.session(config=tf.configproto(allow_soft_placement=true, log_device_placement=true)) sess:     saver = tf.train.saver()     summary_writer = tf.summary.filewriter(log_dir, sess.graph)      coord = tf.train.coordinator()     threads = tf.train.start_queue_runners(sess=sess, coord=coord)     sess.run(tf.initialize_all_variables())      in range(iteration):         images_, labels_ = sess.run([image_batch, label_batch])         # images_ = image_batch         # labels_ = label_batch         sess.run(optimizer, feed_dict={x : images_, y : labels_, keep_prob:0.5})          if % 10 == 0:             = datetime.now() - starttime             print('## time:', now, ' steps:', i)              rt = sess.run([label_max, pre_max, loss, accuracy], feed_dict={x : images_,                                                                            y : labels_,                                                                            keep_prob : 1.0})             print('prediction loss:', rt[2], ' accuracy:', rt[3])             # validation steps             validate_images_, validate_labels_ = sess.run([validate_image_batch, validate_label_batch])             rv = sess.run([label_max, pre_max, loss, accuracy], feed_dict={x: validate_images_,                                                                            y: validate_labels_,                                                                            keep_prob: 1.0})             print('validation loss:', rv[2], ' accuracy:', rv[3])             if (rv[3] > 0.9):                 break             # validation accuracy             summary_str = sess.run(summary, feed_dict={x: validate_images_,                                                        y: validate_labels_,                                                        keep_prob: 1.0})             summary_writer.add_summary(summary_str, i)             summary_writer.flush()          saver.save(sess, 'face_recog')  # save session     coord.request_stop()     coord.join(threads)     print('finish')

'load_jpeg_with_tensorflow.py' below.

def get_input_queue(csv_file_name, num_epochs=none):     train_images = []     train_labels = []     line in open(csv_file_name, 'r'):         cols = re.split(',|\n', line)         train_images.append(cols[0])                                         train_labels.append([float(cols[1])])         # train_labels.append([float(cols[1]), float(cols[2])])     print([train_images, train_labels])     print("number of images :", len(train_images))     input_queue = tf.train.slice_input_producer([train_images, train_labels], num_epochs=num_epochs)         # should small num_epoch                                                                                                                             # batch_size x     return input_queue  def read_data(input_queue):     image_file = input_queue[0]     label = input_queue[1]      image = tf.image.decode_jpeg(tf.read_file(image_file), channels=3)      return image, label, image_file  def read_data_batch(csv_file_name, height, width, batch_size):     input_queue = get_input_queue(csv_file_name)     image, label, file_name = read_data(input_queue)     image = tf.reshape(image, [height, width, 3])      batch_image, batch_label, batch_file = tf.train.batch([image, label, file_name], batch_size=batch_size)                 # add allow_smaller_final_batch=true     batch_file = tf.reshape(batch_file, [batch_size,1])      return batch_image, batch_label, batch_file


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

c# - Asp.net web api : redirect unauthorized requst to forbidden page -

im trying redirect unauthorized request forbidden page instead i'm getting forbidden page in response body , how can fix ? here's startup class : app.createperowincontext(storecontext.create); app.createperowincontext<applicationusermanager>(applicationusermanager.create); app.createperowincontext<applicationsigninmanager>(applicationsigninmanager.create); app.usecookieauthentication(new cookieauthenticationoptions { authenticationtype = defaultauthenticationtypes.applicationcookie, expiretimespan = timespan.fromdays(30), }); app.useexternalsignincookie(defaultauthenticationtypes.externalcookie); app.usetwofactorsignincookie(defaultauthenticationtypes.twofactorcookie, timespan.fromminutes(5)); app.usetwofactorrememberbrowsercookie(defaultauthenticationtypes.twofactorrememberbrowsercookie); the method im trying reach : [httpget] [authorize(roles = "admin")] public string getcurrentusername() { return userman...
Read more