When using a generator for validation data, you must specify a value for `validation_steps` about noise2noise HOT 7 OPEN

You might using Keras < 2.1.2.
Please use Keras >= 2.1.2.

from noise2noise.

yes，after i update to 2.2.0，it can work now。
thank you very much！
by the way，"train model using (noise, noise) pairs", does it mean use two noised image of one image？one image occured twice with different noise，rght？

from noise2noise.

in fact，l want to know，what does it mean ： (noise, noise) or (noise, clean)

from noise2noise.

I don't understand why each image of your train dataset is clean？if all of my dataset are noise image，some of them are the same image with different noise，can i train a general model？

from noise2noise.

@yu4u hope your answer，thanks a lot

from noise2noise.

by the way，"train model using (noise, noise) pairs", does it mean use two noised image of one image？one image occured twice with different noise，rght？

Yes.
clean image -> noisy image1
-> noisy image2

(noise, noise) or (noise, clean) means (input, target) pair.
(noise, clean) is a standard training setting.

from noise2noise.

---python
clean_patch = image[i:i + image_size, j:j + image_size]
x[sample_id] = self.source_noise_model(clean_patch)
y[sample_id] = self.target_noise_model(clean_patch)

this means you train with input clean data + noise and output is org clean data + noise ?

from noise2noise.