topic Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ? in Intel® Distribution of OpenVINO™ Toolkit

Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Tue, 31 Oct 2017 04:34:15 GMT

Hello,

I am trying to run facenet (Inception Resnet V1 on movidius). Please point me towards any tutorial as to how to start compiling for tensorflow. I tried mvCCompile on mnist softmax.py example from the tensorflow website and got the following error. Please help. I am also attaching the softmax.py which I used to create a frozen graph.

mvNCCompile mnist_output/mnist_default.meta -in=input -s12 -o=mnist_graph -on=output
mvNCCompile v02.00, Copyright @ Movidius Ltd 2016

/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/tf_inspect.py:45: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
  if d.decorator_argspec is not None), _inspect.getargspec(target))
[Error 34] Setup Error: Values for input contain placeholder. Pass an absolute value.

softmax.py code below:

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import sys
import tempfile

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

FLAGS = None


def deepnn(x):
  """deepnn builds the graph for a deep net for classifying digits.
  Args:
    x: an input tensor with the dimensions (N_examples, 784), where 784 is the
    number of pixels in a standard MNIST image.
  Returns:
    A tuple (y, keep_prob). y is a tensor of shape (N_examples, 10), with values
    equal to the logits of classifying the digit into one of 10 classes (the
    digits 0-9). keep_prob is a scalar placeholder for the probability of
    dropout.
  """
  # Reshape to use within a convolutional neural net.
  # Last dimension is for "features" - there is only one here, since images are
  # grayscale -- it would be 3 for an RGB image, 4 for RGBA, etc.
  with tf.name_scope('reshape'):
    x_image = tf.reshape(x, [-1, 28, 28, 1])

  # First convolutional layer - maps one grayscale image to 32 feature maps.
  with tf.name_scope('conv1'):
    W_conv1 = weight_variable([5, 5, 1, 32])
    b_conv1 = bias_variable([32])
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)

  # Pooling layer - downsamples by 2X.
  with tf.name_scope('pool1'):
    h_pool1 = max_pool_2x2(h_conv1)

  # Second convolutional layer -- maps 32 feature maps to 64.
  with tf.name_scope('conv2'):
    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])
    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)

  # Second pooling layer.
  with tf.name_scope('pool2'):
    h_pool2 = max_pool_2x2(h_conv2)

  # Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
  # is down to 7x7x64 feature maps -- maps this to 1024 features.
  with tf.name_scope('fc1'):
    W_fc1 = weight_variable([7 * 7 * 64, 1024])
    b_fc1 = bias_variable([1024])

    h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

  # Dropout - controls the complexity of the model, prevents co-adaptation of
  # features.
  with tf.name_scope('dropout'):
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

  # Map the 1024 features to 10 classes, one for each digit
  with tf.name_scope('fc2'):
    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])

    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
  return y_conv, keep_prob


def conv2d(x, W):
  """conv2d returns a 2d convolution layer with full stride."""
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


def max_pool_2x2(x):
  """max_pool_2x2 downsamples a feature map by 2X."""
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')


def weight_variable(shape):
  """weight_variable generates a weight variable of a given shape."""
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)


def bias_variable(shape):
  """bias_variable generates a bias variable of a given shape."""
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)


def main(_):
  # Import data
  mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)

  # Create the model
  x = tf.placeholder(tf.float32, [None, 784], name ="input")

  # Define loss and optimizer
  y_ = tf.placeholder(tf.float32, [None, 10], name = "output")

  # Build the graph for the deep net
  y_conv, keep_prob = deepnn(x)

  with tf.name_scope('loss'):
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,
                                                            logits=y_conv)
  cross_entropy = tf.reduce_mean(cross_entropy)

  with tf.name_scope('adam_optimizer'):
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

  with tf.name_scope('accuracy'):
    correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
    correct_prediction = tf.cast(correct_prediction, tf.float32)
  accuracy = tf.reduce_mean(correct_prediction)

  graph_location = tempfile.mkdtemp()
  print('Saving graph to: %s' % graph_location)
  train_writer = tf.summary.FileWriter(graph_location)
  train_writer.add_graph(tf.get_default_graph())

  with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(20000):
      batch = mnist.train.next_batch(50)
      if i % 100 == 0:
        train_accuracy = accuracy.eval(feed_dict={
            x: batch[0], y_: batch[1], keep_prob: 1.0})
        print('step %d, training accuracy %g' % (i, train_accuracy))
      train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
    saver = tf.train.Saver(tf.global_variables())
    saver.save(sess, "mnist_output/"+'mnist_default')
    print('test accuracy %g' % accuracy.eval(feed_dict={
        x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

if __name__ == '__main__':
  parser = argparse.ArgumentParser()
  parser.add_argument('--data_dir', type=str,
                      default='/tmp/tensorflow/mnist/input_data',
                      help='Directory for storing input data')
  FLAGS, unparsed = parser.parse_known_args()
  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Tue, 31 Oct 2017 04:59:24 GMT

Please look at this page https://movidius.github.io/ncsdk/TensorFlow.html especially the section "Save Session with graph and checkpoint information".

Looks like you need to do something like this to save the session with specific values for input placeholders such as image size etc.

import numpy as np
import tensorflow as tf

from tensorflow.contrib.slim.nets import inception

slim = tf.contrib.slim

def run(name, image_size, num_classes):
  with tf.Graph().as_default():
        image = tf.placeholder("float", [1, image_size, image_size, 3], name="input")
        with slim.arg_scope(inception.inception_v1_arg_scope()):
        logits, _ = inception.inception_v1(image, num_classes, is_training=False, spatial_squeeze=False)
    probabilities = tf.nn.softmax(logits)
    init_fn = slim.assign_from_checkpoint_fn('inception_v1.ckpt', slim.get_model_variables('InceptionV1'))

    with tf.Session() as sess:
        init_fn(sess)
        saver = tf.train.Saver(tf.global_variables())
        saver.save(sess, "output/"+name)

run('inception-v1', 224, 1001)

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Tue, 31 Oct 2017 17:38:50 GMT

@aboggaram ,

i am also getting same error, please let me know if you find the solution.

my detail question is here

https://stackoverflow.com/questions/47012711/how-to-test-custom-created-model-of-tensorflow-on-movidius

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Wed, 01 Nov 2017 05:15:41 GMT

@ramana.rachakonda I have gone through that tutorial and followed the exact same steps but still ending up with the error given mnist example. The documentation given here is not sufficient. @AshwinVijayakumar and Intel team, can you please provide a solid example to compile a custom network rather than those from the tf.contrib.slim module? Thanks a lot,

Achyut

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Thu, 02 Nov 2017 02:19:29 GMT

@Tome_at_Intel Please help me here. Thanks

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Fri, 03 Nov 2017 22:30:07 GMT

@aboggaram we are writing an article about this, and I expect to publish it sometime next week, will let you know as soon as it goes LIVE.

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Tue, 07 Nov 2017 02:54:24 GMT

Awesome, thanks so much!

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Fri, 10 Nov 2017 21:13:58 GMT

@AshwinVijayakumar When can we expect the article?

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Fri, 10 Nov 2017 21:55:50 GMT

Waiting for it too!

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Fri, 10 Nov 2017 22:52:21 GMT

Similarly interested in this article.

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Mon, 13 Nov 2017 05:36:11 GMT

Also waiting for this..

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Tue, 14 Nov 2017 01:50:40 GMT

I'm very interested in this topic,too.

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Thu, 16 Nov 2017 00:29:56 GMT

Hi everyone, I am running a little behind on putting this article together. I was tied up putting the first 2 articles on https://movidius.github.io/blog/, please watch out for the tensorflow article on this blog site.

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Thu, 16 Nov 2017 00:32:34 GMT

Will you be at CES if so whats the booth number?

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Thu, 16 Nov 2017 01:34:09 GMT

@AshwinVijayakumar i am wondering about multiple feature support, it can be built by us somehow or overcome this?

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Thu, 16 Nov 2017 01:40:30 GMT

@chicagobob123 , We will be at the Intel NTG, Movidius Group booth - https://ces18.mapyourshow.com/7_0/exhibitor/exhibitor-details.cfm?ExhID=T0007775

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Thu, 16 Nov 2017 01:42:43 GMT

@GoldenWings, not sure I understand. Can you please clarify what you mean by 'multiple feature support'?

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Thu, 16 Nov 2017 07:54:42 GMT

@AshwinVijayakumar i mean multiple input currently the sdk supports single input i was wondering if there is away to ocercome this

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Wed, 22 Nov 2017 08:09:12 GMT

Also waiting for this.

Re: Is there a tutorial or documentation for running custom tensorflow network in movidius ?

idata — Wed, 22 Nov 2017 20:20:00 GMT

@AshwinVijayakumar : Where exactly is the example for custom tensor flow network in the blog? I am having a custom object detection tensor flow .meta file. I want to run that on Movidius neural stick.

I am using following command:

mvNCCompile -s 12 models/model.meta -in=input_1 -on=conv2_1/bias

and I am getting the following error:

[Error 34] Setup Error: Values for input contain placeholder. Pass an absolute value.