-
Notifications
You must be signed in to change notification settings - Fork 256
Closed
Description
Hello,Thank you very much for your open-sourcing code!
when trying to run the demo,I have been encountering some problems.
when i want to create MPIs using pretrained network,
(j3) m00486393@ubuntu:~/j500003470/Code/LLFF$ python imgs2mpis.py data/testscene/ data/testscene/mpis_360 --height 360
factor/width/height args: [None, None, 360]
Loaded image data (360, 480, 3, 20) [ 360. 480. 391.3782448]
Creating session
2019-08-05 23:28:31.966128: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2019-08-05 23:28:31.966155: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2019-08-05 23:28:31.966163: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2019-08-05 23:28:31.966171: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2019-08-05 23:28:31.966178: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2019-08-05 23:28:40.093371: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 0 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:2d:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2019-08-05 23:28:40.595427: W tensorflow/stream_executor/cuda/cuda_driver.cc:523] A non-primary context 0x333ce40 exists before initializing the StreamExecutor. We haven't verified StreamExecutor works with that.
2019-08-05 23:28:40.597315: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 1 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:31:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2019-08-05 23:28:41.108226: W tensorflow/stream_executor/cuda/cuda_driver.cc:523] A non-primary context 0x3341140 exists before initializing the StreamExecutor. We haven't verified StreamExecutor works with that.
2019-08-05 23:28:41.110100: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 2 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:35:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2019-08-05 23:28:41.655882: W tensorflow/stream_executor/cuda/cuda_driver.cc:523] A non-primary context 0x3345440 exists before initializing the StreamExecutor. We haven't verified StreamExecutor works with that.
2019-08-05 23:28:41.657770: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 3 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:39:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2019-08-05 23:28:42.211243: W tensorflow/stream_executor/cuda/cuda_driver.cc:523] A non-primary context 0x33497a0 exists before initializing the StreamExecutor. We haven't verified StreamExecutor works with that.
2019-08-05 23:28:42.213097: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 4 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:a9:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2019-08-05 23:28:42.785812: W tensorflow/stream_executor/cuda/cuda_driver.cc:523] A non-primary context 0x334dce0 exists before initializing the StreamExecutor. We haven't verified StreamExecutor works with that.
2019-08-05 23:28:42.787681: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 5 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:ad:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2019-08-05 23:28:43.374371: W tensorflow/stream_executor/cuda/cuda_driver.cc:523] A non-primary context 0x3352220 exists before initializing the StreamExecutor. We haven't verified StreamExecutor works with that.
2019-08-05 23:28:43.376293: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 6 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:b1:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2019-08-05 23:28:43.974571: W tensorflow/stream_executor/cuda/cuda_driver.cc:523] A non-primary context 0x3356760 exists before initializing the StreamExecutor. We haven't verified StreamExecutor works with that.
2019-08-05 23:28:43.976437: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 7 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:b5:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2019-08-05 23:28:43.982265: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 0 and 4
2019-08-05 23:28:43.982292: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 0 and 5
2019-08-05 23:28:43.982308: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 0 and 6
2019-08-05 23:28:43.982324: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 0 and 7
2019-08-05 23:28:43.986110: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 1 and 4
2019-08-05 23:28:43.986132: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 1 and 5
2019-08-05 23:28:43.986147: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 1 and 6
2019-08-05 23:28:43.986162: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 1 and 7
2019-08-05 23:28:43.988118: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 2 and 4
2019-08-05 23:28:43.988140: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 2 and 5
2019-08-05 23:28:43.988156: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 2 and 6
2019-08-05 23:28:43.988171: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 2 and 7
2019-08-05 23:28:43.988254: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 3 and 4
2019-08-05 23:28:43.988270: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 3 and 5
2019-08-05 23:28:43.988285: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 3 and 6
2019-08-05 23:28:43.988299: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 3 and 7
2019-08-05 23:28:43.988315: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 4 and 0
2019-08-05 23:28:43.988330: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 4 and 1
2019-08-05 23:28:43.988344: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 4 and 2
2019-08-05 23:28:43.988359: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 4 and 3
2019-08-05 23:28:43.994068: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 5 and 0
2019-08-05 23:28:43.994091: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 5 and 1
2019-08-05 23:28:43.994106: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 5 and 2
2019-08-05 23:28:43.994121: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 5 and 3
2019-08-05 23:28:43.997893: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 6 and 0
2019-08-05 23:28:43.997915: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 6 and 1
2019-08-05 23:28:43.997930: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 6 and 2
2019-08-05 23:28:43.997945: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 6 and 3
2019-08-05 23:28:43.999903: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 7 and 0
2019-08-05 23:28:43.999925: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 7 and 1
2019-08-05 23:28:43.999941: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 7 and 2
2019-08-05 23:28:43.999956: I tensorflow/core/common_runtime/gpu/gpu_device.cc:847] Peer access not supported between device ordinals 7 and 3
2019-08-05 23:28:44.000405: I tensorflow/core/common_runtime/gpu/gpu_device.cc:976] DMA: 0 1 2 3 4 5 6 7
2019-08-05 23:28:44.000418: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 0: Y Y Y Y N N N N
2019-08-05 23:28:44.000426: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 1: Y Y Y Y N N N N
2019-08-05 23:28:44.000434: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 2: Y Y Y Y N N N N
2019-08-05 23:28:44.000441: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 3: Y Y Y Y N N N N
2019-08-05 23:28:44.000448: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 4: N N N N Y Y Y Y
2019-08-05 23:28:44.000456: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 5: N N N N Y Y Y Y
2019-08-05 23:28:44.000463: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 6: N N N N Y Y Y Y
2019-08-05 23:28:44.000470: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 7: N N N N Y Y Y Y
2019-08-05 23:28:44.000485: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:0) -> (device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:2d:00.0)
2019-08-05 23:28:44.000495: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:1) -> (device: 1, name: Tesla P100-PCIE-16GB, pci bus id: 0000:31:00.0)
2019-08-05 23:28:44.000504: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:2) -> (device: 2, name: Tesla P100-PCIE-16GB, pci bus id: 0000:35:00.0)
2019-08-05 23:28:44.000510: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:3) -> (device: 3, name: Tesla P100-PCIE-16GB, pci bus id: 0000:39:00.0)
2019-08-05 23:28:44.000518: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:4) -> (device: 4, name: Tesla P100-PCIE-16GB, pci bus id: 0000:a9:00.0)
2019-08-05 23:28:44.000525: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:5) -> (device: 5, name: Tesla P100-PCIE-16GB, pci bus id: 0000:ad:00.0)
2019-08-05 23:28:44.000532: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:6) -> (device: 6, name: Tesla P100-PCIE-16GB, pci bus id: 0000:b1:00.0)
2019-08-05 23:28:44.000539: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:7) -> (device: 7, name: Tesla P100-PCIE-16GB, pci bus id: 0000:b5:00.0)
Restoring from ./checkpoints/papermodel/checkpoint
Meta restored
Found inputs:
['imgs:0', 'depths:0', 'poses:0', 'num_depths:0', 'close_depth:0', 'inf_depth:0', 'window:0']
Found outputs:
['accum', 'alpha_acc', 'base_img', 'disp0', 'disps', 'imgs', 'inplaces', 'mpi0', 'mpis', 'psv', 'psv1', 'renderings', 'renderings_all', 'renderings_mean', 'renderings_single', 'scales', 'target_disp', 'target_img']
Setup renderer
Weights restored
0 (of 20) <- [0, 8, 9, 1, 10, 0] depths 15.6985977596 166.511276286
('abdriged outputs to', dict_keys(['mpi0', 'disps', 'psv']))
('0 of 1',)
('(360, 480) gridded into 3 x 4',)
('.',)
Traceback (most recent call last):
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call
return fn(*args)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1306, in _run_fn
status, run_metadata)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/contextlib.py", line 88, in __exit__
next(self.gen)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits must be 2-dimensional
[[Node: get_mpi3d_multi/Softmax = Softmax[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"](get_mpi3d_multi/concat_1)]]
[[Node: disps_1/_731 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_12995_disps_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "imgs2mpis.py", line 83, in <module>
args.numplanes, args.no_mpis, True, args.psvs)
File "imgs2mpis.py", line 54, in gen_mpis
mpis = run_inference(imgs, poses, mpi_bds, ibr_runner, num_planes, patched, disps=disps, psvs=psvs)
File "/home/m00486393/j500003470/Code/LLFF/llff/inference/mpi_utils.py", line 156, in run_inference
mpi.generate(generator, num_planes)
File "/home/m00486393/j500003470/Code/LLFF/llff/inference/mpi_utils.py", line 55, in generate
outputs = generator(inputs)
File "/home/m00486393/j500003470/Code/LLFF/llff/inference/mpi_utils.py", line 136, in <lambda>
generator = lambda inputs : ibr_runner.run_inference(inputs, test_keys=keys, patched=patched, valid=120, buffer=80)
File "/home/m00486393/j500003470/Code/LLFF/llff/inference/mpi_tester.py", line 216, in run_inference
out_ = sess.run(outputs, feed_dict=fdict)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits must be 2-dimensional
[[Node: get_mpi3d_multi/Softmax = Softmax[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"](get_mpi3d_multi/concat_1)]]
[[Node: disps_1/_731 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_12995_disps_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op 'get_mpi3d_multi/Softmax', defined at:
File "imgs2mpis.py", line 83, in <module>
args.numplanes, args.no_mpis, True, args.psvs)
File "imgs2mpis.py", line 44, in gen_mpis
ibr_runner.load_graph(logdir)
File "/home/m00486393/j500003470/Code/LLFF/llff/inference/mpi_tester.py", line 112, in load_graph
self.saver = tf.train.import_meta_graph(ckpt_path + '.meta')
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1698, in import_meta_graph
**kwargs)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/framework/meta_graph.py", line 656, in import_scoped_meta_graph
producer_op_list=producer_op_list)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 313, in import_graph_def
op_def=op_def)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/m00486393/anaconda2/envs/j3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1204, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): logits must be 2-dimensional
[[Node: get_mpi3d_multi/Softmax = Softmax[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"](get_mpi3d_multi/concat_1)]]
[[Node: disps_1/_731 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_12995_disps_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
I don't know how to fix the problem, Could you please help me identify where could possibly go wrong?
Metadata
Metadata
Assignees
Labels
No labels