Run main.py error
sidney001 opened this issue · 4 comments
Environment:
.Ubuntu 16.04
.Tensorflow 1.11.0
.Tensorlayer 1.8.2
Models:
├── final_model.ckpt.data-00000-of-00001
├── final_model.ckpt.index
└── final_model.ckpt.meta
2018-12-12 06:55:35.057140: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at save_restore_v2_ops.cc:184 : Not found: Key Unified/UNet/u1/d/W_deconv2d not found in checkpoint
Traceback (most recent call last):
File "main.py", line 155, in
blurmap_3classes(args.index) # test_code
File "main.py", line 106, in blurmap_3classes
saver.restore(sess, "./model/final_model.ckpt")
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1554, in restore
err, "a Variable name or other graph key that is missing")
tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Key Unified/UNet/u1/d/W_deconv2d not found in checkpoint
[[{{node save/RestoreV2}} = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]
[[{{node save/RestoreV2/_71}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_75_save/RestoreV2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]]
Caused by op u'save/RestoreV2', defined at:
File "main.py", line 155, in
blurmap_3classes(args.index) # test_code
File "main.py", line 101, in blurmap_3classes
saver = tf.train.Saver()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1094, in init
self.build()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1106, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1143, in _build
build_save=build_save, build_restore=build_restore)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 787, in _build_internal
restore_sequentially, reshape)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 406, in _AddRestoreOps
restore_sequentially)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 854, in bulk_restore
return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_io_ops.py", line 1466, in restore_v2
shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3272, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1768, in init
self._traceback = tf_stack.extract_stack()
NotFoundError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Key Unified/UNet/u1/d/W_deconv2d not found in checkpoint
[[{{node save/RestoreV2}} = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]
[[{{node save/RestoreV2/_71}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_75_save/RestoreV2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]]
Seem checkpoints isn't qual defined graphy. May need @HyeongseokSon1 supervise the codes. Thanks.
I tested the code again with TF 1.6.0, and it works well.
I guess scope system has slightly changed in the higher versions of TF after 1.10.
I will upgrade the TF version and try to test it again, but it may take a long time.
Please test with TF 1.6 if you are in a hurry.
Thanks.
Thanks for your fast reply. I will try with tf1.6 and 1.9.
Tested with tf 1.9 and works fine. @HyeongseokSon1 Thanks. We can close this issue.