Bump keras from 2.4.3 to 2.13.1 in /object/detection/src

[dependabot[bot]]

Bumps keras from 2.4.3 to 2.13.1.

Release notes

Sourced from keras's releases.

Keras Release 2.13.1

What's Changed

• Fix timeseries_dataset_from_array counts when sequence_stride > 1 by @​basjacobs93 in keras-team/keras#17396
• Fix doc for MultiHeadAttention's output_shape arg by @​tsdeng in keras-team/keras#17432
• Added a link to the TextVectorization API Reference Page. by @​Neeshamraghav012 in keras-team/keras#17540
• Fix ConvNeXt classifier activation bug by @​Frightera in keras-team/keras#17544
• Activations clean up by @​joesho112358 in keras-team/keras#17545
• Perform all ops in apply_gradient in a given tf.name_scope. by @​foxik in keras-team/keras#17550
• Bugfix/normalization invert by @​jerabaul29 in keras-team/keras#17501
• OptimizerV2: Allow deepcopy by @​jschueller in keras-team/keras#17463
• keras.models.clone_model creates different weight names for RNN layers by @​mergian in keras-team/keras#17465
• Fix spelling error in Initializer warning by @​edknv in keras-team/keras#17568
• LayerScale fix to support pretrained ConvNeXt models with mixed precision by @​andreped in keras-team/keras#17547
• Softmax fix in Mixed Precision by @​dsr-lab in keras-team/keras#17571
• Less restrictive ROCm+GRU/LSTM fallback logic by @​ekuznetsov139 in keras-team/keras#17587
• Update security section. by @​sachinprasadhs in keras-team/keras#17522
• Fix serialization error with EfficientNet by @​RocketDelivery in keras-team/keras#17498
• grammar corrections by @​egurnick in keras-team/keras#17595
• Update documentation to keras reuters dataset by @​hxy9243 in keras-team/keras#17635
• Add Lion optimizer by @​drauh in keras-team/keras#17605
• Correct the docstring of Head func in convnext.py by @​Frightera in keras-team/keras#17667
• keras.layers.Bidirectional is missing argument "states", which is defined for keras.layers.RNN by @​mergian in keras-team/keras#17469
• fix a small bug in tf.keras.layer.Layer.compute_output_signature by @​yamanoko in keras-team/keras#17636
• Optimize mixed-precision finite check for sparse tensors. by @​nluehr in keras-team/keras#17638
• Typo Lion docstring by @​drauh in keras-team/keras#17726
• Raise ValueError if reducing axis dimension is 0 by @​old-school-kid in keras-team/keras#16755
• Add CategoricalFocalCrossentropy to Losses API by @​Frightera in keras-team/keras#17651
• Unifying interpolation selection by @​jpodivin in keras-team/keras#17742
• Add a missing space by @​sudoLife in keras-team/keras#17744
• [keras/initializers/initializers_v1.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17785
• [keras/layers/convolutional/conv3d_transpose.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17797
• [keras/engine/training.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17780
• [keras/feature_column/dense_features.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17783
• [keras/datasets/imdb.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17771
• [keras/backend.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17769
• [keras/engine/base_layer_utils.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17774
• [keras/layers/activation/leaky_relu.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17786
• [keras/engine/training_v1.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17781
• [keras/layers/activation/relu.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17787
• [keras/layers/convolutional/conv2d_transpose.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17795
• [keras/layers/convolutional/conv3d.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17796
• [keras/layers/activation/softmax.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17788
• [keras/layers/convolutional/depthwise_conv2d.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17799
• [keras/layers/convolutional/separable_conv2d.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17800
• [keras/layers/locally_connected/locally_connected2d.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17803
• [keras/layers/locally_connected/locally_connected1d.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17802
• Fix performance issue with sample weights in model.fit() by @​nershman in keras-team/keras#17357
• [keras/datasets/reuters.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17772
• [keras/applications/mobilenet.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17763
• [keras/applications/inception_v3.py] Standardise docstring usage of "Default to" by @​SamuelMarks in keras-team/keras#17762

... (truncated)

Commits

• See full diff in compare view

You can trigger a rebase of this PR by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the Security Alerts page.

Note Automatic rebases have been disabled on this pull request as it has been open for over 30 days.