tensorflow
https://github.com/tensorflow/tensorflow
C++
An Open Source Machine Learning Framework for Everyone
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
C++ not yet supported471 Subscribers
View all SubscribersAdd a CodeTriage badge to tensorflow
Help out
- Issues
- deserialize pb stream to feature is too slow.
- [TFLite] Quantized int8/16 support for TILE operator
- tf.profiler.experimental.Trace only works with name is "TraceContext"
- TensorRT Converter *Core Dumped*
- Issue with custom metrics with model class inheritance and using GPU’s with mirrored strategy with TF version 2.4.1 and TFP version 0.12.1 (Also tested and found same issue on TF 2.5.0/TFP 0.12.1).
- Support input of temporal sample_weights for model training on ragged tensors
- “Cloud TPU” console spam on every TensorFlow import
- A name conflict bug caused by LoweringFunctionalOps pass
- support CSR (data, indices, indptr), [shape=(M, N)] format in tf.sparse
- NaNs/Infs in gradient of tf.image.ssim_multiscale
- Docs
- C++ not yet supported