-
Notifications
You must be signed in to change notification settings - Fork 19.4k
Insights: keras-team/keras
September 13, 2024 – September 20, 2024
Overview
Could not load contribution data
Please try again later
3 Pull requests merged by 3 people
-
Updated Complex dtype input support for layers
#19872 merged
Sep 20, 2024 -
Allow AREA resize interpolation for TF backend
#20264 merged
Sep 17, 2024 -
Fix typo in documentation for the extract_patches function.
#20262 merged
Sep 16, 2024
2 Pull requests opened by 2 people
-
Modified example in depthwise_conv1d file
#20268 opened
Sep 18, 2024 -
Fix "same" padding torch issue
#20270 opened
Sep 18, 2024
6 Issues closed by 4 people
-
[Feature request] Complex dtype input support for layers
#19860 closed
Sep 20, 2024 -
"replication_pad1d" not implemented for 'Half'
#20236 closed
Sep 18, 2024 -
Accessing the current training iteration step in a custom Layer class
#20261 closed
Sep 18, 2024 -
Would Keras support unique function?
#20140 closed
Sep 18, 2024 -
Add AdEMAMix Optimizer
#20258 closed
Sep 16, 2024
6 Issues opened by 6 people
-
Incompatibility in 'tf.GradientTape.watch' of TensorFlow 2.17 in Keras 3.4.1
#20274 opened
Sep 20, 2024 -
Error: ValueError: Cannot get result() since the metric has not yet been built during model.fit()
#20273 opened
Sep 20, 2024 -
Keras v3 equivalent for `get_output_at(num)`
#20267 opened
Sep 18, 2024 -
Model weights not saved if a custom layer class contains a list of layers named self._layers
#20260 opened
Sep 16, 2024
26 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
add list_layer_paths method for KerasFileEditor
#20239 commented on
Sep 14, 2024 • 4 new comments -
ValueError: Passed in object <KerasVariable shape=(1, 64), dtype=float64, path=dense_15/kernel> of type 'Variable', not tf.Tensor or tf.Variable or ExtensionType.
#19874 commented on
Sep 20, 2024 • 0 new comments -
Early-stopping does not work properly in Keras 3 when used in a for loop
#20256 commented on
Sep 19, 2024 • 0 new comments -
Rescaling layer defaults to "float32" if dtype not specified - input is uint8
#18464 commented on
Sep 19, 2024 • 0 new comments -
Embedding Projector using TensorBoard callback
#20210 commented on
Sep 19, 2024 • 0 new comments -
Conv1D on custom shaped data
#19900 commented on
Sep 19, 2024 • 0 new comments -
Unexpected behaviour training custom Siamese Network
#20133 commented on
Sep 19, 2024 • 0 new comments -
mul got incompatible shapes for broadcasting
#20219 commented on
Sep 18, 2024 • 0 new comments -
Inconsistent execution results by the PyTorch backend
#20235 commented on
Sep 18, 2024 • 0 new comments -
🗺️ Keras Development Roadmap
#19519 commented on
Sep 18, 2024 • 0 new comments -
Invalid reduction dimension (2 for input with 2 dimension(s) [Op:Sum]
#20221 commented on
Sep 18, 2024 • 0 new comments -
Failure running a SavedModel exported from a tf.Module with a Keras model as an instance variable
#20095 commented on
Sep 18, 2024 • 0 new comments -
Memory leak when using custom DataGenerator
#19907 commented on
Sep 18, 2024 • 0 new comments -
How to create custom metric with more inputs than y_true, y_pred in Keras 3
#20127 commented on
Sep 18, 2024 • 0 new comments -
ops.image.affine_transform() does not work as a layer in GPU
#20191 commented on
Sep 18, 2024 • 0 new comments -
More Customisation in utils.ProgBar
#19684 commented on
Sep 18, 2024 • 0 new comments -
This works in keras 2.15 with TensorFlow 2.15 but does not 3.5 with TensorFlow 2.17: multiple lookup layer types in inputs
#20166 commented on
Sep 17, 2024 • 0 new comments -
Unexpected Behavior when Replacing Layers in CustomModel built with Subclass API
#19268 commented on
Sep 17, 2024 • 0 new comments -
TokenAndPositionEmbedding layer warning---Respecting padding mask or destroying it?
#19794 commented on
Sep 17, 2024 • 0 new comments -
RFC: Keras Recommenders (Keras-RS)
#20080 commented on
Sep 17, 2024 • 0 new comments -
TImeDistributed + Add Layers Error
#20093 commented on
Sep 17, 2024 • 0 new comments -
The .fit() method passes unsized batches to a custom loss function.
#19732 commented on
Sep 17, 2024 • 0 new comments -
PyDataset Documentation and Best Practices
#20142 commented on
Sep 16, 2024 • 0 new comments -
Layer does not have a default tensorflow namespace; requires passing `initial_value` in lambda function
#18461 commented on
Sep 16, 2024 • 0 new comments -
Return and arguments type information for layers.
#19836 commented on
Sep 15, 2024 • 0 new comments -
AttributeError: 'Functional' object has no attribute '_get_save_spec'
#18430 commented on
Sep 13, 2024 • 0 new comments