Comments (7)
And the shape of X_ins is (?, 128, 128, 1), the shape of y_ins is (?, 128, 128, 3), and the shape of tensor is (?, 128, 128, 3).
from multiplanarunet.
from multiplanarunet.
Hi!
Your y_ins should be of shape (?, 128, 128, 1) with each entry giving an integer-valued label. That is, values in {0, 1, 2} in your case for a 3-class problem. I would expect that you have your label maps stored in one-hot encoding (which would be normal, but not what is used here).
I am, however, surprised that you did not get a more appropriate error message - so perhaps this is not the error. I will look into it later this week as soon as I have more time.
If this does solve your issue let me know.
from multiplanarunet.
Hi! Thank you for your reply! One thing I did not mention. I changed slightly your code in the callbacks.py
(y_ins = {in_tens: in_ for in_tens, in_ in zip(self.model.targets, y)} --> y_ins = {in_tens: in_ for in_tens, in_ in zip(self.model.output, y)}),
due to the error "Unet object has no attribute 'targets' "
from multiplanarunet.
Hi! I think I understand it. The problem is the code of callbacks.py:
'y_ins = {in_tens: in_ for in_tens, in_ in zip(self.model.targets, y)}', because I changed 'targets'(,,,1) to 'outputs'(,,,2) for binary segmentation.
However, I still do not know the placeholder variable name of y_ins due to the error "Unet object has no attribute 'targets' ".
Best Wishes,
Tao H
from multiplanarunet.
Hi! Maybe I solved the problem. I replaced 'targets' with '_targets' and it works. However, I do not known if it is true.
Best Wishes,
Tao H
from multiplanarunet.
Hi,
Please update to the latest version (0.2.4) with TensorFlow >=2.0. If you still receive this error, please raise a new issue.
Cheers,
Mathias
from multiplanarunet.
Related Issues (20)
- [urgent] Inputs to operation AddN_7 of type AddN must have the same size and shape.
- AttributeError: 'UNet' object has no attribute 'loss_functions' HOT 4
- Does it support multi-channel input images? HOT 1
- ValueError: 'bg_value' should be a list of length 'n_channels'. Got [4.0] for n_channels=2 HOT 1
- Input volume is sampled on 2D HOT 2
- Error when trying to train HOT 1
- Does MPU have to install "tensorflow-gpu==2.3.2"? The readme file says that GPU is not required. HOT 1
- Why do we need 'predict_single' in predict.py? HOT 2
- No available GPUs... Sleeping 120 seconds HOT 1
- What is real_space_span? HOT 1
- nan weights, nan validation losses HOT 3
- dataset folder structure
- Could you please provide the pdf of your paper? HOT 1
- my system restarts automatically whenever I start training HOT 1
- Getting ValueError in new environment HOT 1
- Memory Error and Lack of GPU Usage HOT 4
- When training on toy_data, TypeError: can only concatenate list (not "dict") to list HOT 1
- weights can not be broadcast to values. values.rank=3. weights.rank=1. values.shape=(2, 448, 448). weights.shape=(2,). HOT 12
- xla_gup not compatible to newest tensorflow version HOT 2
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 multiplanarunet.