NotImplementedError: Cannot convert a symbolic Tensor (Cast_80:0) to a numpy array. about super-resolution HOT 7 CLOSED

I cannot reproduce that. Please provide more details:

• which notebook have you used for running the example? If you have used a custom notebook/script please attach it (wonder if you have disabled eager execution).
• list of installed packages in your environment.

from super-resolution.

Thank Mr. Krasser for your response. I ran the EDSR example with pre-trained weights by using Google Colab. I followed your given codes:

from model import resolve_single
from model.edsr import edsr
from utils import load_image, plot_sample

model = edsr(scale=4, num_res_blocks=16)
model.load_weights('weights/edsr-16-x4/weights.h5')

lr = load_image('demo/0851x4-crop.png')
sr = resolve_single(model, lr)

plot_sample(lr, sr)

When I ran the example, I got the errors as the following:
NotImplementedError Traceback (most recent call last)
in ()
10 #tf.dtypes.cast(sr, tf.float32)
11 sr = resolve_single(model, lr)
---> 12 plot_sample(lr,sr)
13

8 frames

/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py in array(self)
734 def array(self):
735 raise NotImplementedError("Cannot convert a symbolic Tensor ({}) to a numpy"
--> 736 " array.".format(self.name))
737
738 def len(self):

NotImplementedError: Cannot convert a symbolic Tensor (strided_slice_1:0) to a numpy array.

from super-resolution.

Do you mind sharing the Colab notebook here so that I can reproduce the error?

from super-resolution.

Thanks a lot!
This is my Colab notebook link:
https://colab.research.google.com/drive/1UtlpG8YCtIouwUT7_e-hNB8G2qg7HTpk

from super-resolution.

It seems you're using the default Tensorflow version in Colab which is 1.x. This project requires 2.0 though. You can enable Tensorflow 2.0 with %tensorflow_version 2.x in the notebook. I just tried that with your notebook (after some minor changes) and it works as expected.

from super-resolution.

Thank you so much!

from super-resolution.

Hi

I want some information on how to generate a model GAN network you save directly generator.h5, I am sending one image that much bad quality also I want clear image please can you help in this process, I want some information, it's important for me.

from super-resolution.