TomatoBoy90

how to train a i2i use instance maps?

1

hello,I read your work find that your paper say work better in cityscapes when use instance maps. however,if I train general A to B task，can I use instance maps? for...

Can someone share the weight?

4

I didn't reply after filling in the form

ModuleNotFoundError: No module named 'clean_ch'

1

ModuleNotFoundError: No module named 'clean_ch'

What is the ILN network layer? I searched a large circle and didn't see the relevant information

1

What is the ILN network layer? I searched a large circle and didn't see the relevant information

How is your web version background deployed?

4

I use flask for deployment, and the infer time is very slow, one second at a time

Memory-Usage used full wen code running,and drawing is slow

1

+-----------------------------------------------------------------------------+ | NVIDIA-SMI 410.104 Driver Version: 410.104 CUDA Version: 10.0 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage |...

The results before and after running are different

1

 code as follow: from PIL import Image img=Image.open('XX.jpg').resize((256,256)) image=np.array(img) ih=torch.tensor(np.transpose(image,(2,0,1)))/255.0 ih=ih.unsqueeze(0) imoutput,immask,imwatermark= model(ih.cuda()) imcoarser,imrefine,imwatermark = imoutput[1]*immask + im*(1-immask),imoutput[0]*immask + im*(1-immask),imwatermark*immask torchvision.utils.save_image(imcoarser,'imrefine.jpg')

where is images and keypoints for DATA_FOLDER?

11

hi, your job so great .however,how to download those data?

stack expects a non-empty TensorList

2

我在运行你的测试代码的时候，出错了： Network [ModulateGenerator] was created. Total number of parameters: 89.6 million. To see the architecture, do print(network). Embedding size is 512, encoder SAP. Network [ResSESyncEncoder] was created. Total number of...