Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

convert the ckpt model to movidius graph

idata
Employee
1,549 Views

when I convert the ckpt model to movidius graph, I meet the problem:

 

InvalidArgumentError (see above for traceback): Number of ways to split should evenly divide the split dimension, but got split_dim 3 (size = 224) and num_split 3 [[Node: Validation/Validation/Processing/split = Split[T=DT_FLOAT, num_split=3, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Validation/Validation/Processing/split/split_dim, Validation/ExpandDims)]]」

 

then I find the code in tensorflow split_op.cc

 

OP_REQUIRES(context, input_shape.dim_size(split_dim) % num_split == 0, errors::InvalidArgument( "Number of ways to split should evenly divide the split " "dimension, but got split_dim ", split_dim, " (size = ", input_shape.dim_size(split_dim), ") ", "and num_split ", num_split));

 

I read code in KittiSeg/submodules/tensorflow-fcn/fcn8_vgg.py , the following code execute "tf.split()" function.

 

 

red, green, blue = tf.split(rgb, 3, 3) # assert red.get_shape().as_list()[1:] == [224, 224, 1] # assert green.get_shape().as_list()[1:] == [224, 224, 1] # assert blue.get_shape().as_list()[1:] == [224, 224, 1] bgr = tf.concat([ blue - VGG_MEAN[0], green - VGG_MEAN[1], red - VGG_MEAN[2], ], 3)

 

 

this code means the image channels which divided by 3, but the log shows 224 divided 3 , so 224%3 != 0.

0 Kudos
6 Replies
idata
Employee
1,219 Views

@zhanghanbin3159 Can you provide your model files for issue reproduction? Thanks.

0 Kudos
idata
Employee
1,219 Views

@Tome_at_Intel hi,this model is KittiSeg, I want to know that movidius support some segmentation models?

0 Kudos
idata
Employee
1,219 Views

@zhanghanbin3159 At the moment we don't have support for image segmentation.

0 Kudos
idata
Employee
1,219 Views

@Tome_at_Intel thank you for your reply,Semantic segmentation need deconvolution,the movidius hardware do not supported deconvolution,or the ncsdk api not support deconvolution?

0 Kudos
idata
Employee
1,219 Views

@zhanghanbin3159 If you view the release notes we do support deconvolution. Image segmentation isn't supported yet due to some TensorFlow operations not being implemented yet in the NCSDK.

0 Kudos
idata
Employee
1,219 Views

@Tome_at_Intel I understand.

 

The Caffe operations about deconvolution is supported in the NCSDK?

 

How long can this TensorFlow operations be added in the NCSDK?

 

thank you very much!
0 Kudos
Reply