Hello, Wang. I'm very interested in your job. I have two questions. Could you help me?

• Q1: I tried the training with λ1=1, λ2=10, λ3=λ4=2000, λ5=10000 as your paper suggests. But the result is not that good. I'm not sure it's the question of dataset or hyper-parameters?

• Q2: What's more, the hyper-parameters in the selective search is not sure. I tried seg_num=200, power=1.2, γ1=20, γ2=40 and the output of image was very black, as the following: The result of simple search: After that, I tried seg_num=1500, power=0.35, γ1=20, γ2=40 and the output of image was not that bad:

I know the value of pixel must be too large with power=1.2. So I just want to make sure that the parameters is suitable?

Thanks very much.

Hi, An interesting topic and a great model! Thanks for sharing. Here is an issue about surface representation after I read the paper: How do you define the surface representation F_dgf? I didn't find the definition in section3.1 and after.

I'm not quite expert with tf v1, if my understand corrects, L_total in the section 3.4 paper is related to "g_loss_total = 1e4tv_loss + 1e-1g_loss_blur + g_loss_gray + 2e2*recon_loss" line 77, train.py, Right? Well, how to map the four items to the section 3.4?

One more general question, I think this model contributes a combination of losses functions. So my question is why you design these 5 items or 3 parts: structure, texture, and surface? Is there any reference supporting, because I always confused with these terminologies.

Thanks.

Hi, experts That's a nice work and I finished to rewrite your code using pytorch and the training result as attached file. I found out network try transfer to more "smooth area" on trees especially fluff May you give me some suggestion about whether to decrease surface weight or superpixel weight? I have eamail you last week, please check if you are free, thanks

作者你好，按照论文里面的描述的结构损失和纹理损失中，输入的生成图像应该是没有进行guided filter的，但是train.py中，生成器生成的图像都被替换成了滤波后的图像，这样后面只要用到G(I_p)的地方都被改成了F_dgf(G(I_p))，这是本来所期望的吗？

    output = network.unet_generator(input_photo)
    output = guided_filter(input_photo, output, r=1)

hello, i`m trying to run cartoonize.py or pretrain.py and everytime i have same error:

python cartoonize.py 2020-07-30 13:32:57.785610: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudart64_101.dll Traceback (most recent call last): File "cartoonize.py", line 5, in import network File "C:\Users\Admin\Desktop\dfl\White-box-Cartoonization-master\White-box-Cartoonization-master\test_code\network.py", line 3, in import tensorflow.contrib.slim as slim File "C:\Users\Admin\Anaconda3\lib\site-packages\tensorflow\contrib_init_.py", line 40, in from tensorflow.contrib import coder File "C:\Users\Admin\Anaconda3\lib\site-packages\tensorflow\contrib\coder_init_.py", line 22, in from tensorflow.contrib.coder.python.ops.coder_ops import * File "C:\Users\Admin\Anaconda3\lib\site-packages\tensorflow\contrib\coder\python\ops\coder_ops.py", line 22, in from tensorflow.contrib.coder.python.ops import gen_coder_ops File "C:\Users\Admin\Anaconda3\lib\site-packages\tensorflow\contrib\coder\python\ops\gen_coder_ops.py", line 99, in _ops.RegisterShape("PmfToQuantizedCdf")(None) AttributeError: module 'tensorflow.python.framework.ops' has no attribute 'RegisterShape'

more info: cuda is 10.1 scikit-image==0.14.5 tensorflow-gpu==1.12.0

raceback (most recent call last): File "train.py", line 11, in import utils File "E:\White-box-Cartoonization\train_code\utils.py", line 11, in from selective_search.util import switch_color_space File "E:\White-box-Cartoonization\train_code\selective_search_init_.py", line 1, in from .core import selective_search, box_filter File "E:\White-box-Cartoonization\train_code\selective_search\core.py", line 3, in from util import oversegmentation, switch_color_space, load_strategy ModuleNotFoundError: No module named 'util'

Windows10 2004，i7-9750H+1660TI python3.6.8 TensorFlow1.12.0/1.13.0均报此错误 但是可以正常使用预训练模型进行推理

Very interesting work and results. I have a couple of questions. From the paper:

For cartoon images, we collect 10000 images from animations for the human face and 10000 images for landscape. Producers of collected animations include Kyoto animation, P.A.Works, Shinkai Makoto, Hosoda Mamoru, and Miyazaki Hayao.

Can you share more details about how were these images collected? 10000 images of what size? Any particular algorithm of what images are used and what images are discarded from the animations? Any kind of balance in the dataset? Buildings, nature, etc.

Another question, in different parts of the paper, the code and the readme VGG19 and VGG16 appears to be used interchangeably, but they are not the same. Which one was used VGG19 or VGG16? Was it fine-tuned in any way or only used the stock pretrained model to extract the high level features?

Lastly, where in the code is the style interpolation used? Or is it only for inference to interpolate models trained with different loss weights?

Dear wang, I really appreciate the work you have done.I run pretrain.py and got model in pretrain folder but got an error when i run train.py. The error is like this Traceback (most recent call last): File "train.py", line 206, in train(args)
File "train.py", line 193, in train str(total_iter)+'_face_result.jpg', 4) File "/content/drive/My Drive/cartoon/wbc_100/White-box-Cartoonization/train_code/utils.py", line 160, in write_batch_image image[k] = (image[k]+1) * 127.5 IndexError: index 1 is out of bounds for axis 0 with size 1]

Hi，thanks for your great work！ I wanted to use pretrained-model to run demo, but found the url (https://drive.google.com/open?id=1JfJzJbNjAWBIHGm9mc_R9dXv7DAw3tZc) is already not available. I want to ask whethre you can release a new url for pretrained model. Hope for your reply, thank you very much!

Hi, Thank you for uploading such a great work.

I am training the model with my custom dataset, only for portraits. I followed the steps mentioned, the pretrain.py runs properly and saves the model. But, on running train.py I am getting both discriminator and generator losses as NaN. The reconstruction loss does have some value, not sure why I am getting this.

Your help would mean a lot.

One more question. What should be the size of the dataset in order to get decent results. For instance, Paper mentioned use of 10000 cartoon faces, Is it possible to get great results with a smaller dataset?

Hello,

I successfully ported your tensorflow pretrained network to pure pytorch model. Check "pytorch_test" folder

JOB description:

• convert tf checkpoint files to a python dictionary like, {"generator.Conv.weight": weight_params(np.ndarray), ...}
• write a pytorch model with keeping its modules having the same name with the keys of the dictionary (ex. self.Conv = nn.Conv2d and so on ...)
• test model loading function & test on images...

https://master-white-box-cartoonization-psi1104.endpoint.ainize.ai/predict

API is showing "no healthy upstream"

Please solve it as soo as possible

I am very impressed with what you do. Let me ask a few questions about the material surface

What if I want to output an image whose texture doesn't look smooth? Its texture has a lot of detail, like in the movie Weathering with you. I'll leave the illustration below. Usually the result after training is complete, the output will look smooth. Is there a way to make it look like in the picture? I pay much attention to the interior of the house, the road, the trees and I don't pay much attention to the face and the pupils.

it gives me error ModuleNotFoundError: No module named 'tensorflow.contrib' is it because of tenserflow version? can anything be done for windows 10 users?

This is just FYI, feel free to close to the issue

Code: https://github.com/vladmandic/anime
Live demo (using WebCam): https://vladmandic.github.io/anime/public

Running in real-time at 10+ fps using 720x720 video with nVidia RTX3060
Model weights are quantized to F16 to reduce size

For some reason, I need to use more cartoonization that makes the images more unclear compared to input images. Is there any way to do this without retraining? For example by changing some parameters. I'm a novice in AI and I would be appreciated it if you guided me through doing this.