-
Dear authors, could you please tell me what could be wrong, I use my own image and its generated mask for testing, I got the following error:
WARNING:tensorflow:
The TensorFlow contrib module wil…
-
how to split train/test
I downloaded CelebAMask-HQ.zip data. After unzip file, I saw the folder data below,
but I don't know how to split it to train/test. Could you help me how to split train/tes…
-
Hi! Thank you for your dataset and codes!
But if I have a face dataset such as FDDB or 300W, can I get the ground-true labels for these datasets and train their network? Thank you!
-
Hi,
I hope to use this project on ImageNet dataset. I am wondering to know:
1. Have you used ImageNet to train the model before? Any suggestions on hyperparameters? Do you have pre-trained model? …
-
I used pretrained models and the command from the documentation but nothing happened
`!python test.py --image examples/places2/case1_input.png --mask examples/places2/case1_mask.png --output results/…
-
I'm new to Python, I've been studying it for a while. I found your project by chance and it really impressed me, I want to figure out how everything works and test it myself, but using istruction noth…
BazzS updated
4 years ago
-
Hi! I ran the train.py with CelebAMask dataset but only get a 19.47 of PSNR. Did you use the landmark information of the CelebAMask dataset? Or made some special process with the dataset?
-
may I ask the training set of the Celeba you use is 18000, and the Validation set is 100?
Do you know how to obtain landmark use authors'network in the paper? Isn't the a priori network only able …
-
Hello,I was also using Celeba-HQ for training,the same size as you,16px and 128px.Is the 16px Celeba-HQ quite dataset quite low resolution?I think so,but a little doubt.I used SRResnet x8 to train it…
-
Hi, thanks for your work, i wonder what is the delta files for?
and have you get 1024x1024 images using h5tool.py?