UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Observer lzhao
Observer
171 Views
Registered: ‎07-17-2019

freeze_graph error

I am getting an error while creating frozen graph. 

Tensorflow ver. : 1.12.0

Had both Python(2.7.16) and Python3(3.5.2) installed.

DNNDK ver. : 3.1

Following is my freeze graph script and error message.

Freeze graph script:

freeze_graph \
    --input_graph=./model/saved_model.pb \
    --input_checkpoint=./model/checkpoints/gnn_ckpt.data-00000-of-00001 \
    --input_binary=true \
    --output_graph=./model/frozen_graph.pb \
    --output_node_names=edge_output

Following is the error message.

/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
WARNING:tensorflow:From /harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/tools/freeze_graph.py:127: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
W1201 12:34:03.836834 139924142143232 deprecation.py:323] From /harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/tools/freeze_graph.py:127: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
2019-12-01 12:34:04.073305: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA
2019-12-01 12:34:04.095555: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3500000000 Hz
2019-12-01 12:34:04.096239: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x4364b00 executing computations on platform Host. Devices:
2019-12-01 12:34:04.096277: I tensorflow/compiler/xla/service/service.cc:175]   StreamExecutor device (0): <undefined>, <undefined>
2019-12-01 12:34:04.097876: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open ./model/checkpoints/gnn_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?
Traceback (most recent call last):
  File "/harddisk1/xxxx/.local/bin/freeze_graph", line 11, in <module>
    sys.exit(run_main())
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/tools/freeze_graph.py", line 487, in run_main
    app.run(main=my_main, argv=[sys.argv[0]] + unparsed)
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/absl/app.py", line 299, in run
    _run_main(main, args)
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/absl/app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/tools/freeze_graph.py", line 486, in <lambda>
    my_main = lambda unused_args: main(unused_args, flags)
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/tools/freeze_graph.py", line 378, in main
    flags.saved_model_tags, checkpoint_version)
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/tools/freeze_graph.py", line 361, in freeze_graph
    checkpoint_version=checkpoint_version)
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/tools/freeze_graph.py", line 164, in freeze_graph_with_def_protos
    reader = pywrap_tensorflow.NewCheckpointReader(input_checkpoint)
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 636, in NewCheckpointReader
    return CheckpointReader(compat.as_bytes(filepattern))
  File "/harddisk1/xxxx/.local/lib/python3.5/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 648, in __init__
    this = _pywrap_tensorflow_internal.new_CheckpointReader(filename)
tensorflow.python.framework.errors_impl.DataLossError: Unable to open table file ./model/checkpoints/gnn_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?

 

Is this the checkpoint file issue, or something else? Thanks!

0 Kudos
3 Replies
Xilinx Employee
Xilinx Employee
142 Views
Registered: ‎03-27-2013

Re: freeze_graph error

Hi @lzhao ,

 

Are you using Keras to train the model?

Here is what I did to change keras model into freezed pb file:

https://github.com/gewuek/flower_classification_dnndk_v1/blob/master/x86/freeze_model.py

And in that resposity I also attached all the movement from training to deployment. Hope that can help.

Best Regards,
Jason
-----------------------------------------------------------------------------------------------
Please mark the Answer as "Accept as solution" if the information provided is helpful.

Give Kudos to a post which you think is helpful and reply oriented.
-----------------------------------------------------------------------------------------------
0 Kudos
Newbie lzhao1
Newbie
78 Views
Registered: ‎12-02-2019

Re: freeze_graph error

Hi Jason,

Thanks for the response.

We did not use Keras to train this model. 

Following are the packages used:


import argparse
import logging
import os
import sys

import yaml
import json
import tensorflow as tf

0 Kudos
Xilinx Employee
Xilinx Employee
49 Views
Registered: ‎03-27-2013

Re: freeze_graph error

Hi @lzhao1 ,

 

If so maybe you can refer to this one: https://github.com/Xilinx/Edge-AI-Platform-Tutorials/tree/master/docs/MNIST_tf

Best Regards,
Jason
-----------------------------------------------------------------------------------------------
Please mark the Answer as "Accept as solution" if the information provided is helpful.

Give Kudos to a post which you think is helpful and reply oriented.
-----------------------------------------------------------------------------------------------
0 Kudos