error while running encode.py

[SrikarNamburu]

Facing this error

Traceback (most recent call last):
File "encode_images.py", line 80, in
main()
File "encode_images.py", line 53, in main
generator = Generator(Gs_network, args.batch_size, randomize_noise=args.randomize_noise)
File "/content/gdrive/My Drive/RI/stylegan-encoder/encoder/generator_model.py", line 35, in init
self.generator_output = self.graph.get_tensor_by_name('G_synthesis_1/_Run/concat:0')
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3783, in get_tensor_by_name
return self.as_graph_element(name, allow_tensor=True, allow_operation=False)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3607, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3649, in _as_graph_element_locked
"graph." % (repr(name), repr(op_name)))
KeyError: "The name 'G_synthesis_1/_Run/concat:0' refers to a Tensor which does not exist. The operation, 'G_synthesis_1/_Run/concat', does not exist in the graph."

[GuillaumeMMM]

I could fix this issue by going back to using tensorflow-gpu==1.14

[Radeeswar]

Hi, After installing tensorflow-gpu==1.14 I am getting error as follows. I am executing in Google Colab.

InvalidArgumentError: Cannot assign a device for operation learnable_dlatents/read: node learnable_dlatents/read (defined at /content/stylegan-encoder/encoder/generator_model.py:15) was explicitly assigned to /device:GPU:0 but available devices are [ /job:localhost/replica:0/task:0/device:CPU:0, /job:localhost/replica:0/task:0/device:XLA_CPU:0, /job:localhost/replica:0/task:0/device:XLA_GPU:0 ]. Make sure the device specification refers to a valid device.
[[learnable_dlatents/read]]

Any suggestions Please. Ty!

[taniyaghosh29]

Hi, After installing tensorflow-gpu==1.14 I am getting error as follows. I am executing in Google Colab.

InvalidArgumentError: Cannot assign a device for operation learnable_dlatents/read: node learnable_dlatents/read (defined at /content/stylegan-encoder/encoder/generator_model.py:15) was explicitly assigned to /device:GPU:0 but available devices are [ /job:localhost/replica:0/task:0/device:CPU:0, /job:localhost/replica:0/task:0/device:XLA_CPU:0, /job:localhost/replica:0/task:0/device:XLA_GPU:0 ]. Make sure the device specification refers to a valid device.
[[learnable_dlatents/read]]

Any suggestions Please. Ty!

I am getting the same error in Colab. Were you able to fix the issue?

[Radeeswar]

I am getting the same error in Colab. Were you able to fix the issue?

No. It seems like problem with colab GPU. It's working in other GPU by installing tenforflow-gpu==1.14 at start without importing any libraries.

I hope it helps.

[mr555ru]

Seems working for me with tensorflow-gpu==1.14 in Colab GPU runtime.

[oyvindhg]

Seems working for me with tensorflow-gpu==1.14 in Colab GPU runtime.

Like Radeeswar and taniyaghosh29 I cannot make it work in Colab either. Did you do anything extra to make it work in Colab with tensorflow-gpu==1.14?

Edit: Made it work. My error was to use tensorflow==1.14, instead of tensorflow-gpu==1.14

[danielkaifeng]

I remove all tensorflow pkg and do pip3 install tensorflow-gpu==1.14 --user
this problem still exists.

I add allow_soft_placement to gpu config and didn't solve this problem.