I tried running this code on a machine with GPUs. Quite reasonably it kept reporting
CUDA driver version is insufficient for CUDA runtime version
Later it failed after iter 144 in coordinator.py. The final output and traceback are:
`iter 144: image-id:0347885, time:25.594(sec), regular_loss: 0.248021, total-loss 0.6710(0.1133, 0.5478, 0.000000, 0.0099, 0.0000), instances: 28, batch:(60|248, 0|46, 0|0)
labels
[]
classes
['background']
Traceback (most recent call last):
File "train/train.py", line 339, in <module>
train()
File "train/train.py", line 335, in train
coord.join(threads)
File "/home/fisher/workspace/FastMaskRCNN/local/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 389, in join
six.reraise(*self._exc_info_to_raise)
File "/home/fisher/workspace/FastMaskRCNN/local/lib/python2.7/site-packages/tensorflow/python/training/queue_runner_impl.py", line 238, in _run
enqueue_callable()
File "/home/fisher/workspace/FastMaskRCNN/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1231, in _single_operation_run
target_list_as_strings, status, None)
File "/home/fisher/workspace/FastMaskRCNN/local/lib/python2.7/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 1 values, but the requested shape has 0
[[Node: Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](DecodeRaw_1, Reshape/shape)]]
Is this code expected to run without GPU support - and if not could it easily be made to do so?
`
I tried running this code on a machine with GPUs. Quite reasonably it kept reporting
CUDA driver version is insufficient for CUDA runtime versionLater it failed after iter 144 in coordinator.py. The final output and traceback are:Is this code expected to run without GPU support - and if not could it easily be made to do so? `