TFOD custom training in Mask RCNN

TensorFlow
, ,
1

I am not able to troubleshoot this error

tensorflow.python.framework.errors_impl.InvalidArgumentError: {{function_node _wrapped__IteratorGetNext_output_types_18_device/job:localhost/replica:0/task:0/device:GPU:0}} indices[0] = 0 is not in [0, 0)
[[{{node GatherV2_7}}]]
[[MultiDeviceIteratorGetNextFromShard]]
[[RemoteCall]] [Op:IteratorGetNext]

3

Hi @BISWAJIT_ROY ,

We cannot say why this error is coming based on the factors mentioned above.

Could you please share the full reproducible code so that we can have a better understanding of the exact problem?

Meanwhile, you can have a look at Instance Segmentation with official Model Garden to use the latest supported Tensorflow Model Garden API’s.

Thanks

5

Hi,

i am making use of this repo GitHub - tensorflow/models: Models and examples built with TensorFlow