I deployed your code in my own environment and also wrote the program that reads the JRDB dataset and released it via ROS. When I run 3d_detector.py
, I can get into the get_3d_feature()
callback function.
However, my program would crash and abort immediately after running. When I use breakpoints for debugging, the place where I find the program aborts is here:
# jpda_rospack/src/featurepointnet_model.py
try:
batch_centers, \
batch_heading_scores, batch_heading_residuals, \
batch_size_scores, batch_size_residuals, batch_features = \
self.sess.run([self.ops['center'],
ep['heading_scores'], ep['heading_residuals'],
ep['size_scores'], ep['size_residuals'], self.ops['depth_feature']],
feed_dict=feed_dict)
except Exception as e:
print(e)
[INFO] [1600131005.769569]: 3D detector ready.
2020-09-15 08:50:08.476800: E tensorflow/stream_executor/cuda/cuda_dnn.cc:378] Loaded runtime CuDNN library: 7102 (compatibility version 7100) but source was compiled with 6021 (compatibility version 6000). If using a binary install, upgrade your CuDNN library to match. If building from sources, make sure the library loaded at runtime matches a compatible version specified during compile configuration.
2020-09-15 08:50:08.477254: W ./tensorflow/stream_executor/stream.h:1939] attempting to perform DNN operation using StreamExecutor without DNN support
cuDNN launch failure : input shape ([4,1024,1,64])
[[Node: conv1/bn/cond/FusedBatchNorm_1 = FusedBatchNorm[T=DT_FLOAT, data_format="NHWC", epsilon=0.001, is_training=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1/bn/cond/FusedBatchNorm_1/Switch, conv1/bn/cond/FusedBatchNorm_1/Switch_1, conv1/bn/cond/FusedBatchNorm_1/Switch_2, conv1/bn/cond_1/AssignMovingAvg/sub/Switch, conv1/bn/cond_1/AssignMovingAvg_1/sub/Switch)]]
Caused by op 'conv1/bn/cond/FusedBatchNorm_1', defined at:
File "/home/zlin/software/pycharm-2020-2/plugins/python/helpers/pydev/pydevd.py", line 2141, in <module>
main()
File "/home/zlin/software/pycharm-2020-2/plugins/python/helpers/pydev/pydevd.py", line 2132, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "/home/zlin/software/pycharm-2020-2/plugins/python/helpers/pydev/pydevd.py", line 1441, in run
return self._exec(is_module, entry_point_fn, module_name, file, globals, locals)
File "/home/zlin/software/pycharm-2020-2/plugins/python/helpers/pydev/pydevd.py", line 1448, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/zlin/software/pycharm-2020-2/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/3d_detector.py", line 203, in <module>
main(sys.argv)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/3d_detector.py", line 197, in main
Detector_3d()
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/3d_detector.py", line 51, in __init__
self.depth_model = create_depth_model('FPointNet', fpointnet_config)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/featurepointnet_model.py", line 339, in create_depth_model
return FPointNet(config_path)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/featurepointnet_model.py", line 28, in __init__
end_points, depth_feature = self.get_model(pointclouds_pl, one_hot_vec_pl, is_training_pl)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/featurepointnet_model.py", line 271, in get_model
is_training, bn_decay, end_points)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/featurepointnet_model.py", line 154, in get_instance_seg_v1_net
scope='conv1', bn_decay=bn_decay)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/featurepointnet_tf_util.py", line 181, in conv2d
data_format=data_format)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/featurepointnet_tf_util.py", line 577, in batch_norm_for_conv2d
return batch_norm_template(inputs, is_training, scope, [0,1,2], bn_decay, data_format)
File "/home/zlin/PycharmProjects/MOT/catkin_ws_jrmot/src/jpda_rospack/src/featurepointnet_tf_util.py", line 531, in batch_norm_template
data_format=data_format)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
return func(*args, **current_args)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 592, in batch_norm
scope=scope)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 401, in _fused_batch_norm
_fused_batch_norm_inference)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/utils.py", line 217, in smart_cond
return control_flow_ops.cond(pred, fn1, fn2, name)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 316, in new_func
return func(*args, **kwargs)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 1864, in cond
orig_res_f, res_f = context_f.BuildCondBranch(false_fn)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 1725, in BuildCondBranch
original_result = fn()
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 398, in _fused_batch_norm_inference
data_format=data_format)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/nn_impl.py", line 831, in fused_batch_norm
name=name)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 2034, in _fused_batch_norm
is_training=is_training, name=name)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "/home/zlin/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InternalError (see above for traceback): cuDNN launch failure : input shape ([4,1024,1,64])
[[Node: conv1/bn/cond/FusedBatchNorm_1 = FusedBatchNorm[T=DT_FLOAT, data_format="NHWC", epsilon=0.001, is_training=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1/bn/cond/FusedBatchNorm_1/Switch, conv1/bn/cond/FusedBatchNorm_1/Switch_1, conv1/bn/cond/FusedBatchNorm_1/Switch_2, conv1/bn/cond_1/AssignMovingAvg/sub/Switch, conv1/bn/cond_1/AssignMovingAvg_1/sub/Switch)]]