Comments (5)
Ok this is fixed - 64e2836
from coral-ordinal.
Hello,
Thanks for letting me know about this issue! It appears that changes in Tensorflow 2.3 break the package right now, so I've updated the colab notebook to run on TF 2.2 in the short term. I will leave this issue open until I fix the package for TF 2.3.
Appreciate it,
Chris
from coral-ordinal.
I actually fixed it by just changing the following line in loss.py to
y_pred = ops.convert_to_tensor_v2(y_pred)
to
y_pred = tf.convert_to_tensor(y_pred)
Hope this helps
from coral-ordinal.
Yep, I followed that such a change would fix it for TF 2.3, but does it also work in TF 2.2? That's the other check before making the change, otherwise it will be more of a pain to maintain TF 2.2 compatibility.
from coral-ordinal.
Sorry for the late reply
tf.convert_to_tensor()
does work in TF 2.2 cause its base is derived from TF 1.0, therefore i think you can make the change and close this issue
from coral-ordinal.
Related Issues (19)
- MeanAbsoluteErrorLabels metric causes TypeError Exception HOT 3
- OrdinalCrossEntropy should not require `num_classes`; can be inferred from `y_pred`
- OrdinalCrossEntropy does not use `reduction` argument
- Implement CORN loss for logit outputs
- Add option to pass kernel_* and bias_* regularizers to Coral layer HOT 3
- Drop 'units' from get_config() in CornLayer to enable serialization
- Can you provide an example for functional API? HOT 2
- How to have an output of the CoralOrdinal layer to be a single integer of predicted class? HOT 1
- Turning a multi-class classification into ordinal regression HOT 2
- coral-ordinal consistently predicts only 0 in classification task
- Using corn loss with existing ordinal regression task.
- Class weights and coral.OrdinalCrossEntropy()
- InvalidArgumentError: Dimension -1 must be >=0
- Unsupported upperand error when using OrdinalCrossEntropy HOT 4
- bug in Colab notebook's MNIST example HOT 1
- Usage for segmentation HOT 1
- What is the recommended way to handle imbalanced data? HOT 1
- Loss function pug 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 coral-ordinal.