I am trying to customize the AWS semantic segmentation example using MXNET FCN to detect solar panels in aerial imagery. I was able to generat annotations using Sagemaker ground truth and followed example to create label maps for validation and training dataset, but on initiating training I am getting several error messages… This is for my MSC project and I am relatively new to machine learning. Can any one help or point me in right direction regarding how to customize the FCN in the VOC2012 AWS example to change classes and categories?
Below are some of the errors;
[07/02/2019 14:40:37 INFO 140328080901952] Number of GPUs being used: 1
[14:40:39] /opt/brazil-pkg-cache/packages/AIAlgorithmsMXNet/AIAlgorithmsMXNet-1.3.x.1456.0/AL2012/generic-flavor/src/src/storage/storage.cc:129: Using GPUPooledRoundedStorageManager.
/opt/amazon/lib/python2.7/site-packages/mxnet/gluon/parameter.py:811: UserWarning: Parameter ‘fcn0_resnetv1b0_conv0_weight’ is already initialized, ignoring. Set force_reinit=True to re-initialize.
v.initialize(None, ctx, init, force_reinit=force_reinit)
/opt/amazon/lib/python2.7/site-packages/mxnet/gluon/parameter.py:811: UserWarning: Parameter ‘fcn0_resnetv1b0_batchnorm0_gamma’ is already initialized, ignoring. Set force_reinit=True to re-initialize.
v.initialize(None, ctx, init, force_reinit=force_reinit)
Process Process-3:
Traceback (most recent call last):
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 267, in _bootstrap
self.run()
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 114, in run
self._target(*self._args, **self._kwargs)
File “/opt/amazon/lib/python2.7/site-packages/mxnet/gluon/data/dataloader.py”, line 169, in worker_loop
batch = batchify_fn([dataset[i] for i in samples])
File “/opt/amazon/lib/python2.7/site-packages/algorithm/dataset.py”, line 155, in getitem
img, mask = self._get_image_mask_pair(index)
File “/opt/amazon/lib/python2.7/site-packages/algorithm/dataset.py”, line 236, in _get_image_mask_pair
raise CustomerError('Unable to open label file ’ + mask_file_name)
CustomerError: Unable to open label file img00000010.png
Process Process-1:
Traceback (most recent call last):
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 267, in _bootstrap
self.run()
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 114, in run
self._target(*self._args, **self._kwargs)
File “/opt/amazon/lib/python2.7/site-packages/mxnet/gluon/data/dataloader.py”, line 169, in worker_loop
batch = batchify_fn([dataset[i] for i in samples])
Process Process-4:
Traceback (most recent call last):
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 267, in _bootstrap
Process Process-5:
Traceback (most recent call last):
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 267, in _bootstrap
self.run()
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 114, in run
self._target(*self._args, **self._kwargs)
File “/opt/amazon/lib/python2.7/site-packages/mxnet/gluon/data/dataloader.py”, line 169, in worker_loop
self.run()
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 114, in run
self._target(*self._args, **self._kwargs)
File “/opt/amazon/lib/python2.7/site-packages/mxnet/gluon/data/dataloader.py”, line 169, in worker_loop
batch = batchify_fn([dataset[i] for i in samples])
File “/opt/amazon/lib/python2.7/site-packages/algorithm/dataset.py”, line 155, in getitem
batch = batchify_fn([dataset[i] for i in samples])
File “/opt/amazon/lib/python2.7/site-packages/algorithm/dataset.py”, line 155, in getitem
img, mask = self._get_image_mask_pair(index)
File “/opt/amazon/lib/python2.7/site-packages/algorithm/dataset.py”, line 236, in _get_image_mask_pair
raise CustomerError('Unable to open label file ’ + mask_file_name)
CustomerError: Unable to open label file img00000052.png
img, mask = self._get_image_mask_pair(index)
File “/opt/amazon/lib/python2.7/site-packages/algorithm/dataset.py”, line 236, in _get_image_mask_pair
raise CustomerError('Unable to open label file ’ + mask_file_name)
CustomerError: Unable to open label file img00000056.png
Process Process-7:
Traceback (most recent call last):
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 267, in _bootstrap
self.run()
File “/opt/amazon/python2.7/lib/python2.7/multiprocessing/process.py”, line 114, in run
self._target(*self._args, **self._kwargs)
File “/opt/amazon/lib/python2.7/site-packages/mxnet/gluon/data/dataloader.py”, line 169, in worker_loop
batch = batchify_fn([dataset[i] for i in samples])
File “/opt/amazon/lib/python2.7/site-packages/algorithm/dataset.py”, line 155, in getitem
img, mask = self._get_image_mask_pair(index)
File “/opt/amazon/lib/python2.7/site-packages/algorithm/dataset.py”, line 236, in _get_image_mask_pair
raise CustomerError('Unable to open label file ’ + mask_file_name)
CustomerError: Unable to open label file img00000057.png
In :