Compile Deeplab

[idata]

I’m trying to compile the frozen graph for deeplab from tensorflow models, in particular, the mobilenetv2_coco_voc_trainval variant.

I got the input and output from tensorboard and tried compiling with the following command:

mvNCCompile frozen_graph.pb -s 12 -in=ImageTensor -on SemanticPredictions -is 513 513 -o deeplab.pb

this returned the following error:

"

shape: (1, ?, ?, 3)

Traceback (most recent call last): File "/usr/local/bin/mvNCCompile", line 156, in create_graph(args.network, args.inputnode, args.outputnode, args.outfile, args.nshaves, args.inputsize, args.weights, args.explicit_concat, args.ma2480, args.scheduler, args) File "/usr/local/bin/mvNCCompile", line 137, in create_graph load_ret = load_network(args, parser, myriad_config) File "/usr/local/bin/ncsdk/Controllers/Scheduler.py", line 82, in load_network parse_ret = parse_tensor(arguments, myriad_conf) File "/usr/local/bin/ncsdk/Controllers/TensorFlowParser.py", line 259, in parse_tensor input_data = np.random.uniform(0, 1, shape) File "mtrand.pyx", line 1307, in mtrand.RandomState.uniform File "mtrand.pyx", line 242, in mtrand.cont2_array_scTypeError: index returned non-int (type NoneType)

"

Thanks for any help

[idata]

I meet the same problem，Do you solve these problems？

[idata]

@rosenblat Can you provide a link to the model?

[idata]

@Tome_at_Intel deeplap link:https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md

I use mobilenet V2

[idata]

@zhanghanbin3159 Unfortunately at the moment, the NCSDK doesn't have support for semantic image segmentation.

[idata]

@Tome_at_Intel do you have an ETA of NCSDK support for semantic image segmentation?