Pre-trained Model Exploration

Course Q&A Generative Adversarial Networks (GANS) Build Basic Generative Adversarial Networks
1

When running this cell:

fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)

images = Gs.run(noise_vectors, None, truncation_psi=Truncation, randomize_noise=False, output_transform=fmt)

print(f'Successfully sampled {batch_size} images from the model.')

I get this error:

InvalidArgumentError: Cannot assign a device for operation Gs/_Run/Gs/latents_in: {{node Gs/_Run/Gs/latents_in}} 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.
	 [[Gs/_Run/Gs/latents_in]]

During handling of the above exception, another exception occurred:

I have used !pip install tensorflow-gpu==1.15.2

2

Uh oh. I’m seeing the same issue now, too.
I’ll ping the developers to see how they’re coming on the update to this assignment.

3

Same issue for notebook C1W1_8: (Colab) Inputs to a pre-trained GAN.ipynb :frowning:

4

:grimacing: Sure enough! I’m seeing it, too. Thanks for the update. I’ll add it to the list for the developers to fix

5

Any update about the fix @Wendy ?

6

@Hasan_Resul_Cesur,
Unfortunately, it’s going to take a little while to get it fixed, so they’re going to hide the labs in the meantime so students won’t keep running into this issue.