keras-team/tf-keras
The TensorFlow-specific implementation of the Keras API, which was the default Keras from 2019 to 2023.
PythonApache-2.0
Issues
- 1
- 5
- 5
ValueError: (F1Score|FBetaScore) expects 2D inputs with shape (batch_size, output_dim).
#771 opened by msusol - 2
RetinaNet with custom backbone and custom dataset
#773 opened by adityaroy10 - 0
- 3
IntegerLookup with XLA Compilation Fails to Enable JIT in TensorFlow 2.16.1 and Keras 3.2.1
#774 opened by jacob-talroo - 9
- 1
conda-forge release
#775 opened by jonas-eschle - 3
LSTM - different outputs for same weights across CPU and GPU, when using float32 + tf-keras + NVIDIA A100
#772 opened by lbortolotti - 3
- 12
- 2
Addition of Reflect Padding Functionality for tf.keras Convolutional Layers
#766 opened by thesahibnanda - 4
- 9
L1 penalty set small weights to 0
#16 opened by coco90417 - 5
Calling a model and using model.predict yields different results for the same input
#135 opened by tobiasarndt - 3
- 5
- 2
Mirrored strategy model.load_weights() failure
#731 opened by SamKnightGit - 5
- 3
Fail to load model with == op (operator.eq)
#31 opened by Chizkiyahu - 8
- 6
- 7
Adam (and other) optimizers miscalculate the momentum update for complex variables
#30 opened by Hihaatje - 10
Error importing model with both load_model (.keras) and load_weights (.h5)
#664 opened by lllllllllaa - 3
UNIMPLEMENTED: Cast string to float is not supported; CANCELLED: Function was cancelled before it was started
#706 opened by Staddl - 0
TextVectorization: output_mode={multi_hot, count} promise int arrays but output floats
#711 opened by divyashreepathihalli - 11
Error while importing tf_keras
#676 opened by othakkar - 6
tf.keras.metrics.F1Score produces ValueError: Tensor conversion requested dtype float32 for Tensor with dtype int32
#33 opened by meekus-fischer - 3
- 2
- 4
- 6
Reduce Root Mean Square Error and Mean Square Error in dataset which use LSTM Model
#143 opened by LasandiThennakoon - 0
- 5
Using Lambda layers to take different slices of a prevous layer's output causes earlier Lambda layers to be overwritten
#671 opened by sachinprasadhs - 2
- 4
class_weight in .fit fails with InvalidArgumentError: Graph execution error:
#28 opened by Satori1313 - 14
- 3
NotFoundError could not find registered transfer manager for platform Host -- check target linkage [Op:__inference__jit_compiled_convolution_op_26169]
#655 opened by innat - 0
Feature: Flops calculation
#6 opened by innat - 2
Feature: Flops calculation
#138 opened by innat - 6
Add SECURITY.md
#145 opened by psmoros - 3
cannot import name 'np_utils'
#144 opened by faithful-dragon - 9
- 2
- 1
Add a dedicated file for Keras' security policy
#137 opened by pnacht - 3
StringLookup layer never releases memory on load
#136 opened by cjmcgraw - 6
keras_nlp RuntimeError: Exception encountered when calling MultiSegmentPacker.call().
#38 opened by dsbyprateekg - 6
Feature request: Add a "pandas field selection layer" to allow saving a specification of what inputs are needed in what order / what the output of the model corresponds to
#34 opened by jerabaul29 - 2
The model does not save and load correctly when containing `tf.keras.layers.experimental.preprocessing.StringLookup` layer
#29 opened by oawxkw - 4