quolc / neural-collage Goto Github PK

Hi!
First, type your code
python3 demo_spatial_translation.py --config ./configs/sn_projection_dog_and_cat_256_scbn.yml --gen_model ./sn_projection_dog_and_cat_256/ResNetGenerator_450000.npz --gpu 0

Then, I use GPU clusters, so that I only can open browser use command line.
For example,
user@user:opera,
Then X11 will open.

But how to load image in that page?
Thanks.

argument = "--config_path ./configs/sn_projection_dog_and_cat_256_auxab.yml \
--gpu 0 \
--gen_model ./sn_projection_dog_and_cat_256_large/ResNetAuxABGenerator_75000.npz \
--dis_model ./sn_projection_dog_and_cat_256_large/SNResNetProjectionDiscriminator_450000.npz \
--enc_model ./sn_projection_dog_and_cat_256_large/ResNetEncoder_450000.npz \
--src_class {} \
--input patch_src.png \
--iter_opt 200 \
--mode aux".format(src_class)

This line can't run because zsh: number expected on oh-my-zsh and bash: 未预期的符号 (' 附近有语法错误` on bash

你好，在我运行 python demo_spatial_translation.py --config ./configs/sn_projection_dog_and_cat_256_scbn.yml --gen_model ./sn_projection_dog_and_cat_256/ResNetGenerator_450000.npz --gpu 0 之后，程序运行出现了卡顿，一直再没有输出也没有下一步的显示，控制台如下，请问你是否知道是什么原因？

python 3.5

File "demo_feature_blending.py", line 6, in
import secrets
ImportError: No module named 'secrets'

你好，我想请问是否可以使用你的代码对celeba人脸数据集进行训练？因为我看datasets里有imagenet和dog_and_cat的.py文件

Thank you for sharing.
In your paper you said you explored to enable the semantic modification of real images in "real time". So how fast did you get for optimization in your environment? In my try, it seems to be difficult to achieve real-time speed with 1 RTX 2080.

And did you try projection via a feedforward network?

Thanks.

Hello, I run NeuralCollage_demo.ipynb in colab. It show TypeError. How can it work pretty?

# perform blending
arguments = "--gpu 0 \
--config ./configs/sn_projection_dog_and_cat_256_scbn.yml \
--snapshot sn_projection_dog_and_cat_256_large/ResNetGenerator_450000.npz \
--results_dir log/log/gen_spatially_interpolated_images_with_feature_blend  \
--z1 ./src.npy \
--z2 ./ref.npy \
--class_mask ./examples/mask_1.png \
--classes {} {}".format(target_class, src_class)

!python evaluations/gen_spatially_interpolated_images_with_feature_blend.py $arguments

Output

(45, 99)
Traceback (most recent call last):
  File "evaluations/gen_spatially_interpolated_images_with_feature_blend.py", line 141, in <module>
    main()
  File "evaluations/gen_spatially_interpolated_images_with_feature_blend.py", line 124, in main
    x = gen.spatial_interpolation(zs=[z1, z2], weights=ws, blends=blends)
  File "gen_models/resnet_256_scbn.py", line 77, in spatial_interpolation
    hs.append(chainer.Variable(self.xp.zeros_like(hs[0]))) # dummy
  File "/usr/local/lib/python3.7/dist-packages/cupy/creation/basic.py", line 238, in zeros_like
    shape)
  File "/usr/local/lib/python3.7/dist-packages/cupy/creation/basic.py", line 42, in _new_like_order_and_strides
    order = chr(_update_order_char(a, ord(order)))
TypeError: Argument 'x' has incorrect type (expected cupy.core.core.ndarray, got Variable)

RuntimeError Traceback (most recent call last)
in ()
1 import chainer
----> 2 chainer.cuda.get_device(0).use()

/usr/local/lib/python3.6/dist-packages/chainer/backends/cuda.py in get_device(*args)
224 warnings.warn('get_device is deprecated. Please use get_device_from_id or'
225 ' get_device_from_array instead.', DeprecationWarning)
--> 226 return _get_device(*args)
227
228

/usr/local/lib/python3.6/dist-packages/chainer/backends/cuda.py in _get_device(*args)
230 for arg in args:
231 if type(arg) is not bool and isinstance(arg, _integer_types):
--> 232 check_cuda_available()
233 return Device(arg)
234 if isinstance(arg, ndarray):

/usr/local/lib/python3.6/dist-packages/chainer/backends/cuda.py in check_cuda_available()
91 '(see https://github.com/chainer/chainer#installation).')
92 msg += str(_resolution_error)
---> 93 raise RuntimeError(msg)
94 if (not cudnn_enabled and
95 not _cudnn_disabled_by_user and

RuntimeError: CUDA environment is not correctly set up
(see https://github.com/chainer/chainer#installation).CuPy is not correctly installed.

If you are using wheel distribution (cupy-cudaXX), make sure that the version of CuPy you installed matches with the version of CUDA on your host.
Also, confirm that only one CuPy package is installed:
$ pip freeze

If you are building CuPy from source, please check your environment, uninstall CuPy and reinstall it with:
$ pip install cupy --no-cache-dir -vvvv

Check the Installation Guide for details:
https://docs-cupy.chainer.org/en/latest/install.html

original error: libcublas.so.9.2: cannot open shared object file: No such file or directory

get this error in the google colab notebook

Hi~ Thank you for your excellent work! I am wondering if you could also upload a demo for human face images as well. I'd really appreciate that!

Thank you for greate paper!

I have a question about a manifold projection method for StyleGAN generator.
Did you use the same way where the loss function is described in Equation (4) in paper to obtain the corresponding latent/style representation of a given image?

Thanks in advance!