我们从Python开源项目中，提取了以下14个代码示例，用于说明如何使用model.inference()。
def test(): with tf.Graph().as_default(): image, label = input.get_input(LABEL_PATH, LABEL_FORMAT, IMAGE_PATH, IMAGE_FORMAT) logits = model.inference(image) top_k_op = tf.nn.in_top_k(logits, label, 1) variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY) variables_to_restore = variable_averages.variables_to_restore() saver = tf.train.Saver(variables_to_restore) # Get summaries for TENSOR BOARD summary_op = tf.merge_all_summaries() graph_def = tf.get_default_graph().as_graph_def() summary_writer = tf.train.SummaryWriter(input.FLAGS.eval_dir, graph_def=graph_def) while True: evaluate_model(saver, summary_writer, top_k_op, summary_op) if input.FLAGS.run_once: break time.sleep(input.FLAGS.eval_interval_secs)
def test_inference(self): with self.test_session() as sess: # Create model net = create_model(tf.zeros([1, IMG_SIZE, IMG_SIZE, 3]), .1) net_ph = tf.placeholder(tf.float32, shape=net.shape) infer = inference(net_ph, .1) # Test inference results output = np.zeros(net.shape).astype(np.float32) output[0, 1, 1, :5] = [.84, .4, .68, .346, .346] output[0, 1, 1, 10] = .3 # class output[0, 2, 2, :5] = [.84, .4, .68, .346, .346] output[0, 2, 2, 11] = .03 # class result = sess.run([infer], feed_dict={net_ph: output}) p_box, p_classes, confidence, mask = result[0] # Test self.assertEqual(mask[0, 1, 1], 1) self.assertEqual(p_classes, 5) self.assertEqual(confidence, .3 * .84) self.assertListEqual( [round(x) for x in p_box.tolist()[0]], [50, 60, 30, 30],)
def evaluate(run_dir): with tf.Session() as sess: input_file = os.path.join(FLAGS.train_dir, 'md.json') print(input_file) with open(input_file, 'r') as f: md = json.load(f) num_eval = md['%s_counts' % FLAGS.eval_data] images, labels, _ = inputs(FLAGS.train_dir, FLAGS.batch_size, FLAGS.image_size, mode='test', num_preprocess_threads=FLAGS.num_preprocess_threads) logits = inference(images, md['nlabels'], 1, reuse=False) summary_op = tf.summary.merge_all() summary_writer = tf.summary.FileWriter(run_dir, sess.graph) saver = tf.train.Saver() eval_once(sess, saver, summary_writer, summary_op, logits, labels, num_eval)
def evaluate(): """Eval MNIST for a number of steps.""" with tf.Graph().as_default() as g: # Get images and labels for MNIST. mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=False) images = mnist.test.images labels = mnist.test.labels # Build a Graph that computes the logits predictions from the # inference model. logits = model.inference(images, keep_prob=1.0) # Calculate predictions. top_k_op = tf.nn.in_top_k(predictions=logits, targets=labels, k=1) # Create saver to restore the learned variables for eval. saver = tf.train.Saver() eval_once(saver, top_k_op)
def train(): with tf.Graph().as_default(): global_step = tf.Variable(0, trainable=False) image, label = input.get_input(LABEL_PATH, LABEL_FORMAT, IMAGE_PATH, IMAGE_FORMAT) logits = model.inference(image) loss = model.loss(logits, label) train_op = model.train(loss, global_step) saver = tf.train.Saver(tf.all_variables()) summary_op = tf.merge_all_summaries() init = tf.initialize_all_variables() sess = tf.Session(config=tf.ConfigProto(log_device_placement=input.FLAGS.log_device_placement)) sess.run(init) # Start the queue runners. tf.train.start_queue_runners(sess=sess) summary_writer = tf.train.SummaryWriter(input.FLAGS.train_dir, graph_def=sess.graph_def) for step in xrange(input.FLAGS.max_steps): start_time = time.time() _, loss_value = sess.run([train_op, loss]) duration = time.time() - start_time assert not np.isnan(loss_value), 'Model diverged with loss = NaN' if step % 1 == 0: num_examples_per_step = input.FLAGS.batch_size examples_per_sec = num_examples_per_step / duration sec_per_batch = float(duration) format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f sec/batch)') print (format_str % (datetime.now(), step, loss_value, examples_per_sec, sec_per_batch)) if step % 10 == 0: summary_str = sess.run(summary_op) summary_writer.add_summary(summary_str, step) # Save the model checkpoint periodically. if step % 25 == 0: checkpoint_path = os.path.join(input.FLAGS.train_dir, 'model.ckpt') saver.save(sess, checkpoint_path, global_step=step)
def load_inference(sess, ckptdir, threshold): images = tf.placeholder(tf.float32, shape=[None, IMG_SIZE, IMG_SIZE, 3]) net = create_model(images, .1) sess.run(tf.global_variables_initializer()) saver = tf.train.Saver(max_to_keep=10) if ckptdir and os.path.exists(ckptdir) and not FLAGS.debug: checkpoint = tf.train.latest_checkpoint(ckptdir) if checkpoint: print('Restoring', checkpoint) saver.restore(sess, checkpoint) return inference(net, threshold), images ########### # Helpers # ###########
def evaluate(): # compare with labels fetch accuracy encode_to_tfrecords("/home/exbot/ros_kinect_gazebo/src/turtlemove/scripts/one_pictest/test.txt", "/home/exbot/ros_kinect_gazebo/src/turtlemove/scripts/one_pictest", 'test.tfrecords', (37, 37)) test_image, test_label = decode_from_tfrecords( '/home/exbot/ros_kinect_gazebo/src/turtlemove/scripts/one_pictest/test.tfrecords', num_epoch=None) test_images, test_labels = get_test_batch( test_image, test_label, batch_size=BATCH_SIZE, crop_size=32) # [batch, in_height, in_width, in_channels] test_images = tf.reshape(test_images, shape=[-1, 32, 32, 3]) test_images = (tf.cast(test_images, tf.float32) / 255. - 0.5) * 2 # guiyi logits = model.inference(test_images, BATCH_SIZE, NUM_CLASSES) saver = tf.train.Saver(tf.global_variables()) with tf.Session() as sess: coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(coord=coord) rospy.loginfo("Reading checkpoints...") ckpt = tf.train.get_checkpoint_state(train_dir_mydata) if ckpt and ckpt.model_checkpoint_path: ckpt_name = os.path.basename(ckpt.model_checkpoint_path) global_step = ckpt.model_checkpoint_path.split( '/')[-1].split('-')[-1] saver.restore(sess, os.path.join(train_dir_mydata, ckpt_name)) rospy.loginfo('Loading success, global_step is %s' % global_step) test_number = sess.run(tf.argmax(logits, 1)) rospy.loginfo('*****recognized label:%s' % recognize_label[test_number[0]] + '*****') os.remove( "/home/exbot/ros_kinect_gazebo/src/turtlemove/scripts/one_pictest/test.png") contr_turtle.contr(test_number[0]) coord.request_stop() # queue close coord.join(threads)
def tower_loss(scope): """Calculate the total loss on a single tower running the MNIST model. Args: scope: unique prefix string identifying the MNIST tower, e.g. 'tower_0' Returns: Tensor of shape [] containing the total loss for a batch of data """ # Get images and labels for MSNIT. images, labels = model.inputs(FLAGS.batch_size) # Build inference Graph. logits = model.inference(images, keep_prob=0.5) # Build the portion of the Graph calculating the losses. Note that we will # assemble the total_loss using a custom function below. _ = model.loss(logits, labels) # Assemble all of the losses for the current tower only. losses = tf.get_collection('losses', scope) # Calculate the total loss for the current tower. total_loss = tf.add_n(losses, name='total_loss') # Attach a scalar summary to all individual losses and the total loss; do # the same for the averaged version of the losses. if (FLAGS.tb_logging): for l in losses + [total_loss]: # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU # training session. This helps the clarity of presentation on # tensorboard. loss_name = re.sub('%s_[0-9]*/' % model.TOWER_NAME, '', l.op.name) tf.summary.scalar(loss_name, l) return total_loss
def generate_predictions(tfrecord_file, train_dir, predictions_file, features_file, batch_size, num_k): ids, vectors, _ = data_loader.inputs([tfrecord_file], batch_size=batch_size, num_threads=16, capacity=batch_size*4, num_epochs=1, is_training=False) predictions = model.inference(vectors) features = tf.get_default_graph().get_tensor_by_name('fc1/relu:0') init_op = tf.local_variables_initializer() saver = tf.train.Saver() with tf.Session() as sess: sess.run(init_op) saver.restore(sess, tf.train.latest_checkpoint(train_dir)) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) with open(predictions_file, 'w') as f1, open(features_file, 'w') as f2: f1.write('VideoId,LabelConfidencePairs\n') while True: try: ids_out, predictions_out = sess.run( [ids, predictions]) except tf.errors.OutOfRangeError: break for i, _ in enumerate(ids_out): f1.write(ids_out[i].decode()) f1.write(',') top_k = np.argsort(predictions_out[i])[::-1][:num_k] for j in top_k: f1.write('{} {:5f} '.format(j, predictions_out[i][j])) f1.write('\n') #f2.write(ids_out[i].decode()) #f2.write(',') #for j in range(len(features_out[i]) - 1): # f2.write('{:6e},'.format(features_out[i][j])) #f2.write('{:6e}'.format(features_out[i][-1])) #f2.write('\n') coord.request_stop() coord.join(threads)
def main(argv=None): # pylint: disable=unused-argument files = [] if FLAGS.face_detection_model: print('Using face detector (%s) %s' % (FLAGS.face_detection_type, FLAGS.face_detection_model)) face_detect = face_detection_model(FLAGS.face_detection_type, FLAGS.face_detection_model) face_files, rectangles = face_detect.run(FLAGS.filename) print(face_files) files += face_files with tf.Session() as sess: label_list = AGE_LIST if FLAGS.class_type == 'age' else GENDER_LIST nlabels = len(label_list) print('Executing on %s' % FLAGS.device_id) images = tf.placeholder(tf.float32, [None, RESIZE_FINAL, RESIZE_FINAL, 3]) logits = inference(images, nlabels, 1, reuse=False) checkpoint_path = '%s' % (FLAGS.model_dir) model_checkpoint_path, global_step = get_checkpoint(checkpoint_path) saver = tf.train.Saver() saver.restore(sess, model_checkpoint_path) softmax_output = tf.nn.softmax(logits) coder = ImageCoder() # Support a batch mode if no face detection model if len(files) == 0: files.append(FLAGS.filename) # If it happens to be a list file, read the list and clobber the files if one_of(FLAGS.filename, ('csv', 'tsv', 'txt')): files = batchlist(FLAGS.filename) writer = None output = None if FLAGS.target: print('Creating output file %s' % FLAGS.target) output = open(FLAGS.target, 'w') writer = csv.writer(output) writer.writerow(('file', 'label', 'score')) for f in files: image_file = resolve_file(f) if image_file is None: continue try: best_choice = classify(sess, label_list, softmax_output, coder, images, image_file) if writer is not None: writer.writerow((f, best_choice[0], '%.2f' % best_choice[1])) except Exception as e: print(e) print('Failed to run image %s ' % image_file) if output is not None: output.close()
def train(): with tf.Graph().as_default(): # global step number global_step = tf.get_variable('global_step', [], initializer=tf.constant_initializer(0), trainable=False) dataset = DataSet() # get training set print("The number of training images is: %d" % (dataset.cnt_samples(FLAGS.predictcsv))) csv_predict = FLAGS.predictcsv lines = dataset.load_csv(csv_predict) lines.sort() images_ph = tf.placeholder(tf.float32, [1, 229, 229, 3]) num_classes = FLAGS.num_classes restore_logits = not FLAGS.fine_tune # inference logits = model.inference(images_ph, num_classes, for_training=False, restore_logits=restore_logits) # Retain the summaries from the final tower. batchnorm_updates = tf.get_collection(slim.ops.UPDATE_OPS_COLLECTION) # saver saver = tf.train.Saver(tf.all_variables()) # Build the summary operation from the last tower summaries. summary_op = tf.merge_all_summaries() # initialization init = tf.initialize_all_variables() # session sess = tf.Session(config=tf.ConfigProto( allow_soft_placement=True, log_device_placement=FLAGS.log_device_placement)) sess.run(init) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) ckpt = tf.train.get_checkpoint_state(FLAGS.train_dir) if ckpt and ckpt.model_checkpoint_path: print("load: checkpoint %s" % (ckpt.model_checkpoint_path)) saver.restore(sess, ckpt.model_checkpoint_path) print("start to predict.") for step, line in enumerate(lines): pil_img = Image.open(line[0]) pil_img = pil_img.resize((250, 250)) img_array_r = np.asarray(pil_img) img_array_r = img_array_r[15:244,15:244,:] img_array = img_array_r[None, ...] softmax_eval = sess.run([logits[2]], feed_dict={images_ph: img_array}) print("%s,%s,%s" % (line[0], line[1], np.argmax(softmax_eval))) print("finish to predict.") coord.request_stop() coord.join(threads) sess.close()
def run_training(): # ??? train_dir = '/Users/yangyibo/GitWork/pythonLean/AI/????/img/' #My dir--20170727-csq #logs_train_dir ??????????????tensorboard ??? logs_train_dir = '/Users/yangyibo/GitWork/pythonLean/AI/????/saveNet/' # ???????? train, train_label = input_data.get_files(train_dir) # ???? train_batch, train_label_batch = input_data.get_batch(train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY) # ???? train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES) # ?? loss train_loss = model.losses(train_logits, train_label_batch) # ?? train_op = model.trainning(train_loss, learning_rate) # ????? train__acc = model.evaluation(train_logits, train_label_batch) # ?? summary summary_op = tf.summary.merge_all() sess = tf.Session() # ??summary train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph) saver = tf.train.Saver() sess.run(tf.global_variables_initializer()) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) try: for step in np.arange(MAX_STEP): if coord.should_stop(): break _, tra_loss, tra_acc = sess.run([train_op, train_loss, train__acc]) if step % 50 == 0: print('Step %d, train loss = %.2f, train accuracy = %.2f%%' %(step, tra_loss, tra_acc*100.0)) summary_str = sess.run(summary_op) train_writer.add_summary(summary_str, step) if step % 2000 == 0 or (step + 1) == MAX_STEP: # ??2000????????????? checkpoint_path ? checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt') saver.save(sess, checkpoint_path, global_step=step) except tf.errors.OutOfRangeError: print('Done training -- epoch limit reached') finally: coord.request_stop() coord.join(threads) sess.close() # train
def evaluate_one_image(): train_dir = '/Users/yangyibo/GitWork/pythonLean/AI/????/testImg/' # ??????????? train, train_label = input_data.get_files(train_dir) image_array = get_one_image(train) with tf.Graph().as_default(): BATCH_SIZE = 1 # ????????? ??batch ???1 N_CLASSES = 2 # 2????????1?0? ?? ?0?1??????? # ?????? image = tf.cast(image_array, tf.float32) # ????? image = tf.image.per_image_standardization(image) # ???????? [208, 208, 3] ???????? ????4D ??? tensor image = tf.reshape(image, [1, 208, 208, 3]) logit = model.inference(image, BATCH_SIZE, N_CLASSES) # ?? inference ????????????????????softmax ?? logit = tf.nn.softmax(logit) # ??????????????????? placeholder x = tf.placeholder(tf.float32, shape=[208, 208, 3]) # ????????? logs_train_dir = '/Users/yangyibo/GitWork/pythonLean/AI/????/saveNet/' # ??saver saver = tf.train.Saver() with tf.Session() as sess: print("???????????????") # ??????sess ? ckpt = tf.train.get_checkpoint_state(logs_train_dir) if ckpt and ckpt.model_checkpoint_path: global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1] saver.restore(sess, ckpt.model_checkpoint_path) print('??????, ?????? %s' % global_step) else: print('???????????????') # ?????????? prediction = sess.run(logit, feed_dict={x: image_array}) # ?????????????? max_index = np.argmax(prediction) if max_index==0: print('???? %.6f' %prediction[:, 0]) else: print('???? %.6f' %prediction[:, 1]) # ??
