Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Sign In

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

MYRIAD_ERROR - Running custom TensorFlow model on NCS

Hi all,
I've implemented a custom network (LeNet-5) in TensorFlow, trained it and then saved the graph (
After that, I've created a new version of the network for inference purposes and re-saved the graph.

    import tensorflow as tf
    from tensorflow.contrib.layers import flatten
    import sys

    num_outputs = 10

    def lenet(x):

        # Layer 1: Input 32x32x1, Output 28x28x6
        conv1_kernels = tf.Variable(tf.truncated_normal(shape=[5, 5, 1, 6], mean=0, stddev=1))
        conv1_biases = tf.get_variable(name="conv1_biases", shape=[6],
        with tf.name_scope("ConvPoolReLU1"):
            conv1 = tf.nn.conv2d(x,conv1_kernels, [1, 1, 1, 1], padding='VALID') + conv1_biases
            # Pooling -> from 28x28 to 14x14
            pool1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
            # Activation
            conv1 = tf.nn.relu(pool1)
        # Layer 2: Input 14x14x6, Output 10x10x16
        conv2_kernels = tf.Variable(tf.truncated_normal(shape=[5, 5, 6, 16], mean=0, stddev=1))
        conv2_biases = tf.get_variable(name="conv2_biases", shape=[16],
        with tf.name_scope("ConvPoolReLU2"):
            conv2 = tf.nn.conv2d(conv1, conv2_kernels, [1, 1, 1, 1], padding='VALID') + conv2_biases
            # Pooling -> from 10x10x16 to 5x5x16
            pool2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
            # Activation 2
            conv2 = tf.nn.relu(pool2)

        # Flatten -> from 5x5x16 to 400x1
        flattened = flatten(conv2)

        with tf.name_scope("FullyConnectedLayer1"):
            # Fully Connected Layer n.1
            fcl1_weights = tf.Variable(tf.truncated_normal(shape=[400, 120], mean=0, stddev=1))
            fcl1_biases = tf.get_variable(name="fc1_biases", shape=[120],
            fcl1 = tf.matmul(flattened, fcl1_weights) + fcl1_biases
            # Activation 3
            fcl1 = tf.nn.relu(fcl1)

        with tf.name_scope("FullyConnectedLayer2"):
            # Fully Connected Layer n.2
            fcl2_weights = tf.Variable(tf.truncated_normal(shape=[120, 84], mean=0, stddev=1))
            fcl2_biases = tf.get_variable(name="fc2_biases", shape=[84],
            fcl2 = tf.matmul(fcl1, fcl2_weights) + fcl2_biases
            # Activation 4
            fcl2 = tf.nn.relu(fcl2)

        with tf.name_scope("FullyConnectedLayer3"):
            # Fully Connected Layer n.3
            fcl3_weights = tf.Variable(tf.truncated_normal(shape=[84, 10], mean=0, stddev=1))
            fcl3_biases = tf.get_variable(name="fc3_biases", shape=[10],
            logits = tf.matmul(fcl2, fcl3_weights) + fcl3_biases

        return logits

    def main(_):

        print('Saving model for inference on Intel\'s Neural Compute Stick')
        # Create the model
        x = tf.placeholder(tf.float32, [1,32, 32, 1], name='input')
        logits = lenet(x)
        output = tf.nn.softmax(logits,name='softmax')
        saver = tf.train.Saver(tf.global_variables())

        with tf.Session() as sess:
            saver.restore(sess, 'tmp/model.ckpt')
  , 'tmp/model-inference')

    if __name__ == '__main__':, argv=[sys.argv[0]])

Then I used the mvNCCompile command to export the .graph file needed by the NCS: ``mvNCCompile model-inference.meta -s 12 -in=input -on=softmax -is 32 32 -o lenet5.graph
I've also implemented a new script to load the model on the NCS and make some inference on the MNIST dataset (there's padding around images to make the input size fit) but when I run it, the NCS keeps reporting MYRIAD_ERROR.

from mvnc import mvncapi as mvnc
import sys
import numpy as np
import cv2
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

mnist = input_data.read_data_sets("MNIST_data/", reshape=False, one_hot=True)

X_test, y_test = mnist.test.images, mnist.test.labels
X_test = np.pad(X_test, ((0, 0), (2, 2), (2, 2), (0, 0)), 'constant')

# Enumerating devices
mvnc.SetGlobalOption(mvnc.GlobalOption.LOG_LEVEL, 2)
devices = mvnc.EnumerateDevices()
if len(devices) == 0:
    print('No devices found')

#Opening NCS device
device = mvnc.Device(devices[0])

with open('lenet5.graph',mode='rb') as f:
    graphfile =

print('lenet-5 for MNIST_data - Input Size: 32x32x1')
graph = device.AllocateGraph(graphfile)

for i in range(len(X_test)/10):

    if cv2.waitKey(200) > 0:

    x = np.reshape(X_test[i].astype(np.float32),(1,32,32,1))

        print('Loaded Tensor')
        output, _ = graph.GetResult()
#print('output:' + output)


Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
Device 0 Address: 7 - VID/PID 03e7:2150
Starting wait for connect with 2000ms timeout
Found Address: 7 - VID/PID 03e7:2150
Found EP 0x81 : max packet size is 512 bytes
Found EP 0x01 : max packet size is 512 bytes
Found and opened device
Performing bulk write of 865724 bytes...
Successfully sent 865724 bytes of data in 227.821180 ms (3.623977 MB/s)
Boot successful, device address 7
Device 0 Address: 1 - VID/PID 03e7:f63b
Found Address: 1 - VID/PID 03e7:f63b
Booted 1 -> VSC
lenet-5 for MNIST_data - Input Size: 32x32x1
Loaded Tensor
Traceback (most recent call last):
File "", line 43, in
output, _ = graph.GetResult()
File "/usr/local/lib/python2.7/dist-packages/mvnc/", line 264, in GetResult
raise Exception(Status(status))
Exception: mvncStatus.MYRIAD_ERROR

I'm using the NCS on my MacBook Pro on Ubuntu 16.04.

Is this error related to the inference model or the script I made to load the model on the NCS?


  • 3 Comments sorted by Votes Date Added
  • @vincenzosantopietro Can you provide a link to your meta files? I'd like to try to help you debug this issue by reproducing the issue myself on my bench. Thanks.

  • Hi @Tome_at_Intel , thanks for your comment.
    You can download meta files here.

  • @vincenzosantopietro Hi Vincent. I was not able to reproduce your issue "myriad error", but I did run into a different error "[Error 25] Myriad Error: "5x5 Convolution outputChannels Dimension too small."". I was using your myriad-inference.meta model files. By default, the SDK chooses an optimized function that requires the channels to be >= 8.

    I found a workaround with this issue by including a conf file named "model-inference.conf" with the following content: (Make sure there is an extra line after the last line in the conf file or else it will not parse correctly.)

Sign In or Register to comment.