Error to make run video_face_matcher in Raspberry Pi 3

idata · ‎04-07-2018

ERROR log as below, platform in Raspberry Pi 3 (but the same example able to run in UBUNTU 16.0):

making model

Zip file exists.

Zip file unzipped.

data file exists

index file exists

meta file exists

Converted directory does not exist, doing conversion

model base file name is: facenet_celeb

Traceback (most recent call last):

File "../convert_facenet.py", line 99, in

sys.exit(main())

File "../convert_facenet.py", line 61, in main

prelogits, _ = network.inference(image, 1.0, phase_train=False)

File "/var/ncappzoo/tensorflow/facenet/inception_resnet_v1.py", line 149, in inference

dropout_keep_prob=keep_probability, bottleneck_layer_size=bottleneck_layer_size, reuse=reuse)

File "/var/ncappzoo/tensorflow/facenet/inception_resnet_v1.py", line 207, in inception_resnet_v1

net = slim.repeat(net, 5, block35, scale=0.17)

File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1082, in repeat

outputs = layer(outputs, *args, **kwargs)

File "/var/ncappzoo/tensorflow/facenet/inception_resnet_v1.py", line 42, in block35

mixed = tf.concat([tower_conv, tower_conv1_1, tower_conv2_2], 3)

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/array_ops.py", line 867, in concat

dtype=dtypes.int32).get_shape(

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 657, in convert_to_tensor

ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 180, in _constant_tensor_conversion_function

return constant(v, dtype=dtype, name=name)

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 163, in constant

tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape))

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 353, in make_tensor_proto

_AssertCompatible(values, dtype)

File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 290, in _AssertCompatible

(dtype.name, repr(mismatch), type(mismatch).name))

TypeError: Expected int32, got list containing Tensors of type '_Message' instead.

making compile

/bin/sh: 7: cd: can't cd to 20170512-110547/facenet_celeb_ncs

Command line: mvNCCompile facenet_celeb_ncs.meta -w facenet_celeb_ncs -s 12 -in input -on output -o facenet_celeb_ncs.graph

Please help. Thanks in advanced!

idata · ‎04-09-2018

@yockgen The video_face_matcher app uses the TensorFlow model FaceNet. At the moment, we don't have TensorFlow support for the Raspberry Pi yet. Please see the release notes https://github.com/movidius/ncsdk/releases/tag/v1.12.00.01 and scroll down to the Errata section (#2 issue).