Can't compress own file with pretrained model or self trained model

[gullibleretorted]

Hi there,

first of all, thanks a lot for your reimplementation on the paper!

I wanted to see how it works on compressing an image of mine. I downloaded the pretrained model and wanted to use the compress.py script as mentioned in the read.me. This didn't work, so I saw a closed issue here, that for using the compression it needed the checkpoint file. So I trained the model to get such a checkpoint file. Now I tried to run the command with compress.py again:

python compress.py -r ./checkpoints/best/my_network_epoch34.ckpt-34 -i ./pic.jpeg -o ./pic_out.jpeg

I get the following error message:

Traceback (most recent call last): File "compress.py", line 85, in <module> main() File "compress.py", line 82, in main single_compress(config_test, args) File "compress.py", line 53, in single_compress new_saver = tf.train.import_meta_graph('{}.meta'.format(args.restore_path)) File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 1453, in import_meta_graph **kwargs)[0] File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 1477, in _import_meta_graph_with_return_elements **kwargs)) File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/framework/meta_graph.py", line 810, in import_scoped_meta_graph_with_return_elements return_elements=return_elements) File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs) File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/framework/importer.py", line 405, in import_graph_def producer_op_list=producer_op_list) File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/framework/importer.py", line 505, in _import_graph_def_internal raise ValueError(str(e)) ValueError: Cannot add function '__inference_Dataset_map__parser_56' because a different function with the same name already exists.

My venv:
Package Version

---

absl-py 0.12.0
appnope 0.1.2
astor 0.8.1
backports-abc 0.5
backports.functools-lru-cache 1.6.4
backports.shutil-get-terminal-size 1.0.0
backports.weakref 1.0.post1
bleach 1.5.0
cachetools 3.1.1
certifi 2020.12.5
chardet 4.0.0
cycler 0.10.0
decorator 4.4.2
enum34 1.1.10
funcsigs 1.0.2
functools32 3.2.3.post2
futures 3.3.0
gast 0.2.2
google-auth 1.30.0
google-auth-oauthlib 0.4.1
google-pasta 0.2.0
grpcio 1.37.1
h5py 2.10.0
html5lib 0.9999999
idna 2.10
ipykernel 4.10.1
ipython 5.10.0
ipython-genutils 0.2.0
jupyter-client 5.3.5
jupyter-core 4.6.3
Keras-Applications 1.0.8
Keras-Preprocessing 1.1.2
kiwisolver 1.1.0
Markdown 3.1.1
matplotlib 2.2.5
mock 3.0.5
numexpr 2.7.3
numpy 1.16.6
oauthlib 3.1.0
opt-einsum 2.3.2
pandas 0.24.2
pathlib2 2.3.5
pexpect 4.8.0
pickleshare 0.7.5
pip 20.3.4
prompt-toolkit 1.0.18
protobuf 3.17.0
ptyprocess 0.7.0
pyasn1 0.4.8
pyasn1-modules 0.2.8
Pygments 2.5.2
pyparsing 2.4.7
python-dateutil 2.8.1
pytz 2021.1
pyzmq 19.0.2
requests 2.25.1
requests-oauthlib 1.3.0
rsa 4.5
scandir 1.10.0
scipy 1.2.2
seaborn 0.9.1
setuptools 44.1.1
simplegeneric 0.8.1
singledispatch 3.6.1
six 1.16.0
subprocess32 3.5.4
tables 3.5.2
tensorboard 1.15.0
tensorflow 1.8.0
tensorflow-cpu 1.15.0
tensorflow-cpu-estimator 1.15.1
tensorflow-estimator 2.1.0
termcolor 1.1.0
tornado 5.1.1
traitlets 4.3.3
urllib3 1.26.4
wcwidth 0.2.5
Werkzeug 1.0.1
wheel 0.36.2
wrapt 1.12.1

---

I also tried to just add the checkpoint file to the checkpoints folder where the pretrained model is and got the following error:

`Sampling noise...
('Real image shape:', [None, None, None, 3])
('Reconstruction shape:', [None, 512, 1024, 3])
2021-05-20 11:55:08.755659: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2021-05-20 11:55:08.790379: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f911c318720 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-05-20 11:55:08.790421: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2021-05-20 11:55:13.008342: W tensorflow/core/graph/graph_constructor.cc:1491] Importing a graph with a lower producer version 24 into an existing graph with producer version 134. Shape inference will have run different parts of the graph with different producer versions.
2021-05-20 11:55:25.044370: W tensorflow/core/framework/op_kernel.cc:1651] OP_REQUIRES failed at save_restore_v2_ops.cc:184 : Not found: Key generator/encoder_image/batch_normalization/beta not found in checkpoint
Traceback (most recent call last):
File "compress.py", line 85, in
main()
File "compress.py", line 82, in main
single_compress(config_test, args)
File "compress.py", line 54, in single_compress
new_saver.restore(sess, args.restore_path)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 1306, 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 generator/encoder_image/batch_normalization/beta not found in checkpoint
[[node save/RestoreV2 (defined at /Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]

Original stack trace for u'save/RestoreV2':
File "compress.py", line 85, in
main()
File "compress.py", line 82, in main
single_compress(config_test, args)
File "compress.py", line 34, in single_compress
saver = tf.train.Saver()
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 828, in init
self.build()
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 840, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 878, in _build
build_restore=build_restore)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 508, in _build_internal
restore_sequentially, reshape)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 328, in _AddRestoreOps
restore_sequentially)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 575, in bulk_restore
return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/ops/gen_io_ops.py", line 1696, in restore_v2
name=name)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op
attrs, op_def, compute_device)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal
op_def=op_def)
File "/Users/python_envs/gan/lib/python2.7/site-packages/tensorflow_core/python/framework/ops.py", line 1748, in init
self._traceback = tf_stack.extract_stack()`

---

Any help would be highly appreciated!! Thanks a lot in advance!