Comments (5)
Hi, you should modify the code from Line34
Line 34-36: Get UV texture image of imageA and imageB. If you want to directly input the UV texture, please comment L34-36.
from cpm.
@thaoshibe
Run according to your above operation, report the following error:
Traceback (most recent call last):
File "main.py", line 58, in
output = model.render_texture(new_txt)
File "/data/hjq/CPM/makeup.py", line 132, in render_texture
self.triangles.T,
AttributeError: 'Makeup' object has no attribute 'triangles'
from cpm.
Hi @seawater668 ,
I'm not sure what you're trying to get. As far as I understand, your inputs are UW-maps, and you want to get outputs as UV maps as well.
Then, please comment Line 47, 48 too.
Sorry I can't assist you further. But if you want to modify anything, starting debug from here is a good start.
Thank youu.
from cpm.
@thaoshibe
if name == "main":
args = get_args()
model = Makeup(args)
imgA = np.array(Image.open(args.input))
imgB = np.array(Image.open(args.style))
imgA = cv2.resize(imgA, (256, 256))
imgB = cv2.resize(imgB, (256, 256))
A_txt = imgA.copy()
B_txt = imgB.copy()
# model.prn_process(imgA)
# A_txt = model.get_texture()
# B_txt = model.prn_process_target(imgB)
if args.color_only:
output = color_makeup(A_txt, B_txt, args.alpha)
elif args.pattern_only:
output = pattern_makeup(A_txt, B_txt)
else:
color_txt = model.makeup(A_txt, B_txt) * 255
cv2.imwrite('./0929/color_txt.jpg', color_txt)
mask = model.get_mask(B_txt)
mask = (mask > 0.001).astype("uint8")
cv2.imwrite('./0929/mask.jpg', mask)
new_txt = color_txt * (1 - mask)[:, :, np.newaxis] + B_txt * mask[:, :, np.newaxis]
cv2.imwrite('./0929/new_txt.jpg', new_txt)
output = model.render_texture(new_txt)
output = model.blend_imgs(model.face, output, alpha=1)
x2, y2, x1, y1 = model.location_to_crop()
output = np.concatenate([imgB[x2:], model.face[x2:], output[x2:]], axis=1)
if not os.path.exists(args.savedir):
os.makedirs(args.savedir)
save_path = os.path.join(args.savedir, "result.png")
Image.fromarray((output).astype("uint8")).save(save_path)
print("Completed 👍 Please check result in: {}".format(save_path))
from cpm.
As mentioned above: Sorry I can't assist you further. But if you want to modify anything, starting debug from here is a good start.
Thank you!.
from cpm.
Related Issues (20)
- how to render uv map to normal image? HOT 2
- Setup throwing error HOT 3
- the code is too bad! waste my time!!! HOT 1
- It work so bad!!!!!!!!! HOT 1
- ValueError: The passed save_path is not a valid checkpoint: ./PRNet/net-data/256_256_resfcn256_weight HOT 2
- Suggest to loosen the dependency on albumentations HOT 2
- Training on new dataset HOT 3
- AttributeError: module 'segmentation_models_pytorch' has no attribute 'utils' HOT 1
- About the MT dataset HOT 2
- No module named 'blend_modes
- MT dataset HOT 1
- image-invariant region mask HOT 1
- No module named 'segmentation_models_pytorch.unet'
- No module named 'blend_modes'
- The corresponding package cannot be installed in colab and locally, because of the mac device? HOT 1
- Part of the face changes? HOT 1
- The performance of the code can not match the picture in README HOT 4
- RuntimeError: Unsupported image type, must be 8bit gray or RGB image. HOT 2
- The sticker order in the Stickers dataset is incorrect HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cpm.