Detecting robot grasping positions with deep neural networks. The model is trained on Cornell Grasping Dataset. This is an implementation mainly based on the paper 'Real-Time Grasp Detection Using Convolutional Neural Networks' from Redmon and Angelova.
I've added some code to perform automated setup which downloads and extracts the files into ~/.keras, plus moved things to consistently use tf flags.
I also tried loading the models included in the repository and ran into difficulty, do you have any advice on how to load them correctly? I'm not very familiar with the tf saver mechanism:
Traceback (most recent call last):
File "grasp_det.py", line 162, in <module>
tf.app.run(main=main)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "grasp_det.py", line 158, in main
run_training()
File "grasp_det.py", line 120, in run_training
saver_g.restore(sess, FLAGS.model_path)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1666, in restore
{self.saver_def.filename_tensor_name: save_path})
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
options, run_metadata)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.DataLossError: Unable to open table file /home/ahundt/src/robot-grasp-detection/models/imagenet/m2/m2.ckpt.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
[[Node: save_1/RestoreV2_15 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_1/Const_0_0, save_1/RestoreV2_15/tensor_names, save_1/RestoreV2_15/shape_and_slices)]]
Caused by op u'save_1/RestoreV2_15', defined at:
File "grasp_det.py", line 162, in <module>
tf.app.run(main=main)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "grasp_det.py", line 158, in main
run_training()
File "grasp_det.py", line 118, in run_training
saver_g = tf.train.Saver(dg)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1218, in __init__
self.build()
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1227, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1263, in _build
build_save=build_save, build_restore=build_restore)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 751, in _build_internal
restore_sequentially, reshape)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 427, in _AddRestoreOps
tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 267, in restore_op
[spec.tensor.dtype])[0])
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1021, in restore_v2
shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "/home/ahundt/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
DataLossError (see above for traceback): Unable to open table file /home/ahundt/src/robot-grasp-detection/models/imagenet/m2/m2.ckpt.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
[[Node: save_1/RestoreV2_15 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_1/Const_0_0, save_1/RestoreV2_15/tensor_names, save_1/RestoreV2_15/shape_and_slices)]]
-> [1]
> python2 grasp_det.py --model_path '/home/ahundt/src/robot-grasp-detection/models/imagenet/m2/m2.ckpt.data-00000-of-00001'
P.S. I don't think this PR is the cause of that particular error...
I've added some code to perform automated setup which downloads and extracts the files into
~/.keras, plus moved things to consistently use tf flags.I also tried loading the models included in the repository and ran into difficulty, do you have any advice on how to load them correctly? I'm not very familiar with the tf saver mechanism:
P.S. I don't think this PR is the cause of that particular error...