MCPcopy Create free account

hub / github.com/keras-team/keras / functions

Functions12,633 in github.com/keras-team/keras

↓ 3 callersFunctionblock
An inverted residual block. Args: inputs: input tensor. activation: activation function. drop_rate: float between 0 and 1
keras/src/applications/efficientnet.py:440
↓ 3 callersMethodbuild
(self, input_shape)
guides/functional_api.py:601
↓ 3 callersMethodbuild
(self, input_shape)
keras/src/layers/core/dense_test.py:309
↓ 3 callersMethodbuild
(self, sequences_shape, initial_state_shape=None)
keras/src/layers/rnn/rnn.py:270
↓ 3 callersMethodcompile_from_config
Compiles the model with the information given in config. This method uses the information in the config (optimizer, loss, metrics, et
keras/src/trainers/trainer.py:958
↓ 3 callersFunctioncompute_conv_transpose_padding_args_for_torch
( input_shape, kernel_shape, strides, padding, output_padding, dilation_rate, )
keras/src/backend/common/backend_utils.py:149
↓ 3 callersMethodcompute_mask
(self, inputs, mask=None)
keras/src/layers/merging/dot.py:348
↓ 3 callersMethodcompute_output_shape
(self, input_shape)
keras/src/layers/preprocessing/category_encoding.py:129
↓ 3 callersMethodcompute_output_spec
(self, x)
keras/src/ops/linalg.py:413
↓ 3 callersMethodcompute_output_spec
(self, x)
keras/src/ops/math.py:819
↓ 3 callersFunctionconvert_spec_to_tensor
(spec, replace_none_number=None)
keras/src/export/export_utils.py:100
↓ 3 callersFunctionconvert_to_numpy
(x)
keras/src/backend/openvino/core.py:677
↓ 3 callersFunctiondeserialize_keras_object
Retrieve the object by deserializing the config dict. The config dict is a Python dictionary that consists of a set of key-value pairs, and r
keras/src/saving/serialization_lib.py:433
↓ 3 callersMethoddtype_policy_string
Returns the dtype policy string for this configuration. Returns: A string representing the dtype policy, e.g. "gptq_4bit".
keras/src/quantizers/gptq_config.py:178
↓ 3 callersFunctionexpand_dims
(x, axis)
keras/src/backend/torch/numpy.py:794
↓ 3 callersMethodfinalize_state
(self)
keras/src/layers/preprocessing/normalization.py:291
↓ 3 callersMethodfinalize_variable_values
Set the final value of model's trainable variables. Sometimes there are some extra steps before ending the variable updates, such as
keras/src/optimizers/base_optimizer.py:1016
↓ 3 callersMethodfloat_discretized
( cls, num_bins, bin_boundaries=None, output_mode="one_hot", name=None )
keras/src/layers/preprocessing/feature_space.py:315
↓ 3 callersMethodfloat_normalized
(cls, name=None)
keras/src/layers/preprocessing/feature_space.py:305
↓ 3 callersFunctionget_autocast_scope
()
keras/src/backend/common/variables.py:651
↓ 3 callersMethodget_compile_config
Returns a serialized config with information for compiling the model. This method returns a config dictionary containing all the information
keras/src/trainers/trainer.py:945
↓ 3 callersMethodget_config
(self)
keras/src/legacy/layers.py:205
↓ 3 callersMethodget_config
Gets a `SharedObjectConfig` if one has already been seen for `obj`. Args: obj: The object for which to retrieve the `SharedObjectCo
keras/src/legacy/saving/serialization.py:187
↓ 3 callersMethodget_config
(self)
keras/src/saving/saving_lib_test.py:930
↓ 3 callersMethodget_config
(self)
keras/src/dtype_policies/dtype_policy.py:177
↓ 3 callersMethodget_config
(self)
keras/src/models/sequential.py:335
↓ 3 callersFunctionget_example_array
()
keras/src/constraints/constraints_test.py:8
↓ 3 callersFunctionget_functional_model
(keras)
keras/src/legacy/saving/legacy_h5_format_test.py:38
↓ 3 callersFunctionget_input_signature
(model)
keras/src/export/export_utils.py:9
↓ 3 callersMethodget_jax_iterator
(self)
keras/src/trainers/data_adapters/torch_data_loader_adapter.py:43
↓ 3 callersMethodget_jax_iterator
(self)
keras/src/trainers/data_adapters/grain_dataset_adapter.py:100
↓ 3 callersMethodget_jax_iterator
(self)
keras/src/trainers/data_adapters/generator_data_adapter.py:28
↓ 3 callersMethodget_jax_iterator
(self)
keras/src/trainers/data_adapters/tf_dataset_adapter.py:45
↓ 3 callersFunctionget_mlp_functional_model
(shared_layers=False)
keras/src/models/cloning_test.py:13
↓ 3 callersMethodget_model
(self, dtype=None)
keras/src/saving/saving_api_test.py:121
↓ 3 callersMethodget_numpy_iterator
(self)
keras/src/trainers/data_adapters/array_data_adapter.py:95
↓ 3 callersMethodget_numpy_iterator
(self)
keras/src/trainers/data_adapters/grain_dataset_adapter.py:59
↓ 3 callersMethodget_random_transform
Generates random parameters for a transformation. Args: img_shape: Tuple of integers. Shape of the image that is
keras/src/legacy/preprocessing/image.py:1292
↓ 3 callersFunctionget_temp_dir
()
keras/src/saving/saving_lib.py:1840
↓ 3 callersMethodget_tf_dataset
(self)
keras/src/trainers/data_adapters/torch_data_loader_adapter.py:47
↓ 3 callersMethodget_tf_dataset
(self)
keras/src/trainers/data_adapters/grain_dataset_adapter.py:132
↓ 3 callersMethodget_torch_dataloader
(self)
keras/src/trainers/data_adapters/torch_data_loader_adapter.py:65
↓ 3 callersMethodget_torch_dataloader
(self)
keras/src/trainers/data_adapters/grain_dataset_adapter.py:180
↓ 3 callersMethodget_value
Get the context value for `arg_name`, or `default` if unset.
keras/src/layers/layer.py:1993
↓ 3 callersMethodget_weights
(self)
keras/src/callbacks/early_stopping_test.py:157
↓ 3 callersFunctionin_safe_mode
()
keras/src/saving/serialization_lib.py:96
↓ 3 callersFunctionin_symbolic_scope
()
keras/src/backend/common/symbolic_scope.py:18
↓ 3 callersFunctionis_batched
Check if the `tf.data.Dataset` is batched.
keras/src/utils/dataset_utils.py:646
↓ 3 callersFunctionis_sparse
DEPRECATED.
keras/src/legacy/backend.py:956
↓ 3 callersMethodmake
Make a new H5 entry group. This method is only available in write mode. It defers the creation of the H5 entry group until `__setitem
keras/src/saving/saving_lib.py:1492
↓ 3 callersFunctionmap
(f, xs)
keras/src/backend/jax/core.py:406
↓ 3 callersFunctionmap_coordinates
( inputs, coordinates, order, fill_mode="constant", fill_value=0.0 )
keras/src/backend/torch/image.py:763
↓ 3 callersFunctionmap_coordinates
( inputs, coordinates, order, fill_mode="constant", fill_value=0.0 )
keras/src/backend/numpy/image.py:910
↓ 3 callersFunctionmax
(x, axis=None, keepdims=False, initial=None)
keras/src/backend/tensorflow/numpy.py:722
↓ 3 callersMethodmodel
(self)
keras/src/callbacks/callback.py:78
↓ 3 callersFunctionmodel_from_json
Parses a JSON model configuration string and returns a model instance. Example: >>> model = keras.Sequential([ ... keras.layers.Dens
keras/src/models/model.py:897
↓ 3 callersFunctionnp_conv1d
( x, kernel_weights, bias_weights, strides, padding, data_format, dilation_rate,
keras/src/layers/convolutional/conv_test.py:25
↓ 3 callersFunctionnp_conv1d_transpose
( x, kernel_weights, bias_weights, strides, padding, output_padding, data_format,
keras/src/layers/convolutional/conv_transpose_test.py:19
↓ 3 callersMethodon_epoch_end
(self, epoch, logs=None)
keras/src/callbacks/remote_monitor.py:54
↓ 3 callersMethodon_epoch_end
(self, epoch, logs=None)
keras/src/trainers/trainer_test.py:335
↓ 3 callersFunctionone_hot
(x, num_classes, axis=-1, dtype=None, sparse=False)
keras/src/backend/numpy/nn.py:545
↓ 3 callersMethodpermutation
(_)
keras/src/trainers/data_adapters/array_data_adapter.py:128
↓ 3 callersMethodquantize_and_correct_layer
Performs GPTQ quantization and correction on the layer's weights. This method implements the core logic of the "Optimal Brain Quant"
keras/src/quantizers/gptq.py:393
↓ 3 callersMethodquantized_build
(self, kernel_shape, mode, config=None)
keras/src/layers/core/einsum_dense.py:445
↓ 3 callersMethodquantized_build
(self, kernel_shape, mode, config=None)
keras/src/layers/core/dense.py:371
↓ 3 callersMethodquantized_build
(self, embeddings_shape, mode)
keras/src/layers/core/embedding.py:318
↓ 3 callersMethodreset_state
(self)
keras/src/trainers/compile_utils.py:357
↓ 3 callersFunctionresolve_sub_path
Verify that a relative path stays within the base directory. Args: base_dir: The base directory to check against, must be resolved via
keras/src/utils/file_utils.py:48
↓ 3 callersFunctionresult_type
Returns the type from applying the Keras type promotion rules. In general, each argument is first parsed by `backend.standardize_dtype`, and
keras/src/backend/common/dtypes.py:281
↓ 3 callersFunctionsafe_get_h5_dataset
Retrieve a Dataset within a given Group. Args: group: the parent h5py.Group. name: the name of the Dataset to retrieve. Retu
keras/src/saving/saving_lib.py:1174
↓ 3 callersFunctionsave_attributes_to_hdf5_group
Saves attributes (data) of the specified name into the HDF5 group. This method deals with an inherent problem of HDF5 file which is not able
keras/src/legacy/saving/legacy_h5_format.py:288
↓ 3 callersFunctionsave_model_to_hdf5
(model, filepath, overwrite=True, include_optimizer=True)
keras/src/legacy/saving/legacy_h5_format.py:28
↓ 3 callersFunctionserialize
Serializes `DTypePolicy` instance. Args: dtype_policy: A Keras `DTypePolicy` instance. Returns: `DTypePolicy` configuration
keras/src/dtype_policies/__init__.py:24
↓ 3 callersFunctionserialize_dict
(obj)
keras/src/saving/serialization_lib.py:423
↓ 3 callersMethodsetUp
(self)
keras/src/distribution/distribution_lib_test.py:366
↓ 3 callersFunctionset_global_attribute
(name, value)
keras/src/backend/common/global_state.py:11
↓ 3 callersMethodset_model
(self, model)
keras/src/callbacks/callback.py:74
↓ 3 callersFunctionset_random_seed
Sets all random seeds (Python, NumPy, and backend framework, e.g. TF). You can use this utility to make almost any Keras program fully determ
keras/src/utils/rng_utils.py:14
↓ 3 callersMethodsetup
(self, axis=1)
keras/src/metrics/regression_metrics_test.py:46
↓ 3 callersMethodshape
(self)
keras/src/trainers/data_adapters/array_slicing.py:162
↓ 3 callersFunctionsigmoid
(x)
keras/src/backend/numpy/nn.py:29
↓ 3 callersFunctionslice
Return a slice of an input tensor. At a high level, this operation is an explicit replacement for array slicing e.g. `inputs[start_indices: s
keras/src/ops/core.py:421
↓ 3 callersFunctionsparse_generator
(generator_type)
keras/src/trainers/trainer_test.py:259
↓ 3 callersFunctionsparse_to_dense
(x, default_value=None)
keras/src/backend/tensorflow/sparse.py:12
↓ 3 callersMethodstatic_call
(x, negative_slope=0.0, max_value=None, threshold=0.0)
keras/src/activations/activations.py:76
↓ 3 callersMethodstring_categorical
( cls, max_tokens=None, num_oov_indices=1, output_mode="one_hot", name
keras/src/layers/preprocessing/feature_space.py:347
↓ 3 callersMethodstring_hashed
(cls, num_bins, output_mode="one_hot", name=None)
keras/src/layers/preprocessing/feature_space.py:365
↓ 3 callersMethodtest_on_batch
Test the model on a single batch of samples. Args: x: Input data. Must be array-like. y: Target data. Must be array-l
keras/src/trainers/trainer.py:905
↓ 3 callersFunctiontext_to_word_sequence
DEPRECATED.
keras/src/legacy/preprocessing/text.py:14
↓ 3 callersMethodto_json
Returns a JSON string containing the network configuration. To load a network from a JSON save file, use `keras.models.model_from_jso
keras/src/models/model.py:540
↓ 3 callersFunctionto_list
Normalizes a list/tensor into a list. If a tensor is passed, we return a list of size 1 containing the tensor. Args: x: target o
keras/src/utils/python_utils.py:109
↓ 3 callersMethodtokenize
(self, text)
keras/src/quantizers/gptq_core_test.py:18
↓ 3 callersMethodtrain_on_batch
Runs a single gradient update on a single batch of data. Args: x: Input data. Must be array-like. y: Target data. Mus
keras/src/trainers/trainer.py:867
↓ 3 callersFunctiontrain_step
(train_state, x, y)
examples/demo_jax_distributed.py:268
↓ 3 callersFunctiontraverse
(func, structure, top_down=True)
keras/src/tree/dmtree_impl.py:94
↓ 3 callersMethodupdate_state
Accumulates root mean squared error statistics. Args: y_true: The ground truth values. y_pred: The predicted values.
keras/src/metrics/regression_metrics.py:480
↓ 3 callersFunctionuses_cpu
()
keras/src/testing/test_case.py:624
↓ 3 callersMethodvalidate_outputs
Validate that teacher and student outputs are compatible. Arguments: teacher_outputs: Outputs from the teacher model.
keras/src/distillation/distillation_loss.py:62
↓ 2 callersFunctionMobileNetV3
( stack_fn, last_point_ch, input_shape=None, alpha=1.0, model_type="large", minimalist
keras/src/applications/mobilenet_v3.py:153
↓ 2 callersFunctionNASNet
Instantiates a NASNet model. Reference: - [Learning Transferable Architectures for Scalable Image Recognition]( https://arxiv.org/abs
keras/src/applications/nasnet.py:20
← previousnext →601–700 of 12,633, ranked by callers