The results seems not good. about image_completion_tf2 HOT 15 OPEN

Hello, where did you training the module, CPU or GPU? I can train it on CPU, but maybe my 2 8G Kingston RAMs can't offer enough storage capacity，only can train the module in Tc+Td epochs. So the result seems not good because my computer did not complete the training of the entire model.

from image_completion_tf2.

Ooh,I just run the master branch code on my gpu.I ignored the tc and the td stage.I would try to run the animi branch today.

from image_completion_tf2.

Yeah, the master branch code does not involve the tc and the td stage. I am looking forward to your new result on the animi branch.
Could you please tell me the version of your GPU, CUDA, Tensorflow-gpu and Keras , My computer is nvidia GTX1080, CUDA8.0 Tensorflow-gpu(1.6.0) and Keras (2.1.5) ,but it doesn't work for the anim and separate_c_d branch.

from image_completion_tf2.

I use M40,cuda8.0,Tensorflow-gpu（1.6.0）and Keras（2.0.8）and it run 100 epochs about 2.5 hours.

from image_completion_tf2.

Oh, thanks, maybe my GPU is only 8G, I‘ll try to change the code for solving the problems.

from image_completion_tf2.

@dongdong092 when you finished the training, how do you load the trained weight to predict the test sets. Please give me some advice, thanks!

from image_completion_tf2.

I run the other branch .In the 20th opoches,it stops by the following error:
print("%d [D loss: %e] [G mse: %e]" % (n, d_loss, g_loss))
TypeError: must be real number, not list

from image_completion_tf2.

I also met this error，because the g_loss is not a real number, I print g_loss separately by the following code, which show g_loss is a list such as 'G mse: [0.0028160308, 0.0028160308, 1.1920933e-07]':
print('%d G mse:' % n),
print(g_loss),
print("[D loss: %e]" %d_loss)

from image_completion_tf2.

And could you please tell me your email address?

from image_completion_tf2.

Hi.
I will check the "TypeError" and fix it.
Thanks.

from image_completion_tf2.

I fixed the "TypeError" and merged to master branch.

from image_completion_tf2.

I train this model on Street View dataset,my result doesn't good as well. Do anybody achieve good result?

from image_completion_tf2.

@xieenze I train the model on place2 dataset, the result looks good. But when I test images with arbitrary mask shape, the results are too bad. Do you test any images and how to do it ?

from image_completion_tf2.

@Alex-toto , which branch did you use? the master or animi?

from image_completion_tf2.

@dongdong092 im running very slow compared to your 100Ep @ 2.5Hours.
I use batch size 16 on a TitanV GPU (and dual xeon cpus to spare) and Im getting around 20mins per Epoch... Im also only using the 35000 validation images from places...

from image_completion_tf2.