Comments (5)
Hi, Excuse me,
when I just Run the Face_Restoration function with aligned image(512*512), it occured to a question :
"################ Error in enhancing this image: input and output sizes should be greater than 0, but got input (H: 16, W: 0) output (H: 40, W: 40)"
I checked the class UNetDictFace in network.py carefully, i find:
cur_feature is the shape of [1, 128, 256, 256];
mo_location is the shape of [4],and its value is [205, 288, 242, 325];
then ;
MO_feature = cur_feature[:,:,mo_location[1]:mo_location[3],mo_location[0]:mo_location[2]].clone();
it didn't work that the value would cross the border of cur_feature.some pics work, but some pics didn't work.
Could u tell me the reason?
thx very much!!
Can you send me the pics that did not work? I think I should debug it to find the reason.
from dfdnet.
Hi, Excuse me,
when I just Run the Face_Restoration function with aligned image(512*512), it occured to a question :
"################ Error in enhancing this image: input and output sizes should be greater than 0, but got input (H: 16, W: 0) output (H: 40, W: 40)"
I checked the class UNetDictFace in network.py carefully, i find:
cur_feature is the shape of [1, 128, 256, 256];
mo_location is the shape of [4],and its value is [205, 288, 242, 325];
then ;
MO_feature = cur_feature[:,:,mo_location[1]:mo_location[3],mo_location[0]:mo_location[2]].clone();
it didn't work that the value would cross the border of cur_feature.
some pics work, but some pics didn't work.
Could u tell me the reason?
thx very much!!Can you send me the pics that did not work? I think I should debug it to find the reason.
emm..sorry, I find my pics are not aligned.
I put the pic(the size is (102, 112, 3)) and the landmark to Face_Restoration function, it works.results are as follows.
------>
But the same pic(resize it to (2693, 4096, 3)) didn't work.
from dfdnet.
Hi, Excuse me,
when I just Run the Face_Restoration function with aligned image(512*512), it occured to a question :
"################ Error in enhancing this image: input and output sizes should be greater than 0, but got input (H: 16, W: 0) output (H: 40, W: 40)"
I checked the class UNetDictFace in network.py carefully, i find:
cur_feature is the shape of [1, 128, 256, 256];
mo_location is the shape of [4],and its value is [205, 288, 242, 325];
then ;
MO_feature = cur_feature[:,:,mo_location[1]:mo_location[3],mo_location[0]:mo_location[2]].clone();
it didn't work that the value would cross the border of cur_feature.
some pics work, but some pics didn't work.
Could u tell me the reason?
thx very much!!Can you send me the pics that did not work? I think I should debug it to find the reason.
emm..sorry, I find my pics are not aligned.
I put the pic(the size is (102, 112, 3)) and the landmark to Face_Restoration function, it works.results are as follows.
------>
But the same pic(resize it to (2693, 4096, 3)) didn't work.
Very strange. Both images ( (102, 112, 3), (2693, 4096, 3)) work well in my computer. Do you use our new code? Or did you change our code (except these four parameters in command)? With the released code, I didn't reproduce your problem.
from dfdnet.
Hi, Excuse me,
when I just Run the Face_Restoration function with aligned image(512*512), it occured to a question :
"################ Error in enhancing this image: input and output sizes should be greater than 0, but got input (H: 16, W: 0) output (H: 40, W: 40)"
I checked the class UNetDictFace in network.py carefully, i find:
cur_feature is the shape of [1, 128, 256, 256];
mo_location is the shape of [4],and its value is [205, 288, 242, 325];
then ;
MO_feature = cur_feature[:,:,mo_location[1]:mo_location[3],mo_location[0]:mo_location[2]].clone();
it didn't work that the value would cross the border of cur_feature.
some pics work, but some pics didn't work.
Could u tell me the reason?
thx very much!!Can you send me the pics that did not work? I think I should debug it to find the reason.
emm..sorry, I find my pics are not aligned.
I put the pic(the size is (102, 112, 3)) and the landmark to Face_Restoration function, it works.results are as follows.
------>
But the same pic(resize it to (2693, 4096, 3)) didn't work.
Very strange. Both images ( (102, 112, 3), (2693, 4096, 3)) work well in my computer. Do you use our new code? Or did you change our code (except these four parameters in command)? With the released code, I didn't reproduce your problem.
thank u very much.
I will check my code and try ur new code.
Thanks again.
from dfdnet.
Hi, Excuse me,
when I just Run the Face_Restoration function with aligned image(512*512), it occured to a question :
"################ Error in enhancing this image: input and output sizes should be greater than 0, but got input (H: 16, W: 0) output (H: 40, W: 40)"
I checked the class UNetDictFace in network.py carefully, i find:
cur_feature is the shape of [1, 128, 256, 256];
mo_location is the shape of [4],and its value is [205, 288, 242, 325];
then ;
MO_feature = cur_feature[:,:,mo_location[1]:mo_location[3],mo_location[0]:mo_location[2]].clone();
it didn't work that the value would cross the border of cur_feature.
some pics work, but some pics didn't work.
Could u tell me the reason?
thx very much!!Can you send me the pics that did not work? I think I should debug it to find the reason.
emm..sorry, I find my pics are not aligned.
I put the pic(the size is (102, 112, 3)) and the landmark to Face_Restoration function, it works.results are as follows.
------>
But the same pic(resize it to (2693, 4096, 3)) didn't work.
Very strange. Both images ( (102, 112, 3), (2693, 4096, 3)) work well in my computer. Do you use our new code?
Hi, Excuse me,
when I just Run the Face_Restoration function with aligned image(512*512), it occured to a question :
"################ Error in enhancing this image: input and output sizes should be greater than 0, but got input (H: 16, W: 0) output (H: 40, W: 40)"
I checked the class UNetDictFace in network.py carefully, i find:
cur_feature is the shape of [1, 128, 256, 256];
mo_location is the shape of [4],and its value is [205, 288, 242, 325];
then ;
MO_feature = cur_feature[:,:,mo_location[1]:mo_location[3],mo_location[0]:mo_location[2]].clone();
it didn't work that the value would cross the border of cur_feature.
some pics work, but some pics didn't work.
Could u tell me the reason?
thx very much!!Can you send me the pics that did not work? I think I should debug it to find the reason.
emm..sorry, I find my pics are not aligned.
Very strange. Both images ( (102, 112, 3), (2693, 4096, 3)) work well in my computer. Do you use our new code? Or did you change our code (except these four parameters in command)? With the released code, I didn't reproduce your problem.
thank u very much.
I will check my code and try ur new code.
Thanks again.
This is the result that takes the input with 2693*4096.
from dfdnet.
Related Issues (20)
- Training HOT 2
- Can the cropped area of the face be larger? Long-haired ones are not fully displayed HOT 1
- Cuda alocating too much on 4gb card, come on, gpen does it fine. 1024 models ?
- Pasting upscaled face back to original image is offset/wrong size
- Can someone set it up for huggingface or replicate websites to run ?
- Got it working, but won't work the second time
- CUDA running out of memory (3gb card) on the face restoration step
- all faces enhance along with background
- the face channel or some step went wrong? HOT 1
- No output
- onnx export
- error step2:I changed the test picture, the size is 16x16, and I made an error in the second step.
- somebody can help me HOT 1
- Multiple gpus?
- VGGFace loss details.
- Discriminator architecture
- Weird results on side face input
- weird results, what's wrong.
- weird results, what's wrong? HOT 2
- Which file to edit in order to use cpu when using it as mve plugin?
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 dfdnet.