- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
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.
- Tags:
- Tensorflow
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@zhanghanbin3159 Can you provide your model files for issue reproduction? Thanks.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Tome_at_Intel hi,this model is KittiSeg, I want to know that movidius support some segmentation models?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@zhanghanbin3159 At the moment we don't have support for image segmentation.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@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?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@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.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@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!

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page