B «»ˆd5&ã@sždZddlmmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z dd lmZdd lmZdd lmZed ƒGd d„deƒƒZdS)zEmbedding layer.éN)Úbackend)Ú constraints)Ú initializers)Ú regularizers)Úutils)Úbase_layer_utils)ÚLayer)Útf_utils)Ú keras_exportzkeras.layers.EmbeddingcsdeZdZdZejd‡fdd„ ƒZejddd„ƒZ dd d „Z ejd d „ƒZ d d„Z ‡fdd„Z ‡ZS)Ú Embeddinga± Turns positive integers (indexes) into dense vectors of fixed size. e.g. `[[4], [20]] -> [[0.25, 0.1], [0.6, -0.2]]` This layer can only be used on positive integer inputs of a fixed range. The `tf.keras.layers.TextVectorization`, `tf.keras.layers.StringLookup`, and `tf.keras.layers.IntegerLookup` preprocessing layers can help prepare inputs for an `Embedding` layer. This layer accepts `tf.Tensor` and `tf.RaggedTensor` inputs. It cannot be called with `tf.SparseTensor` input. Example: >>> model = tf.keras.Sequential() >>> model.add(tf.keras.layers.Embedding(1000, 64, input_length=10)) >>> # The model will take as input an integer matrix of size (batch, >>> # input_length), and the largest integer (i.e. word index) in the input >>> # should be no larger than 999 (vocabulary size). >>> # Now model.output_shape is (None, 10, 64), where `None` is the batch >>> # dimension. >>> input_array = np.random.randint(1000, size=(32, 10)) >>> model.compile('rmsprop', 'mse') >>> output_array = model.predict(input_array) >>> print(output_array.shape) (32, 10, 64) Args: input_dim: Integer. Size of the vocabulary, i.e. maximum integer index + 1. output_dim: Integer. Dimension of the dense embedding. embeddings_initializer: Initializer for the `embeddings` matrix (see `keras.initializers`). embeddings_regularizer: Regularizer function applied to the `embeddings` matrix (see `keras.regularizers`). embeddings_constraint: Constraint function applied to the `embeddings` matrix (see `keras.constraints`). mask_zero: Boolean, whether or not the input value 0 is a special "padding" value that should be masked out. This is useful when using recurrent layers which may take variable length input. If this is `True`, then all subsequent layers in the model need to support masking or an exception will be raised. If mask_zero is set to True, as a consequence, index 0 cannot be used in the vocabulary (input_dim should equal size of vocabulary + 1). input_length: Length of input sequences, when it is constant. This argument is required if you are going to connect `Flatten` then `Dense` layers upstream (without it, the shape of the dense outputs cannot be computed). Input shape: 2D tensor with shape: `(batch_size, input_length)`. Output shape: 3D tensor with shape: `(batch_size, input_length, output_dim)`. **Note on variable placement:** By default, if a GPU is available, the embedding matrix will be placed on the GPU. This achieves the best performance, but it might cause issues: - You may be using an optimizer that does not support sparse GPU kernels. In this case you will see an error upon training your model. - Your embedding matrix may be too large to fit on your GPU. In this case you will see an Out Of Memory (OOM) error. In such cases, you should place the embedding matrix on the CPU memory. You can do so with a device scope, as such: ```python with tf.device('cpu:0'): embedding_layer = Embedding(...) embedding_layer.build() ``` The pre-built `embedding_layer` instance can then be added to a `Sequential` model (e.g. `model.add(embedding_layer)`), called in a Functional model (e.g. `x = embedding_layer(x)`), or used in a subclassed model. ÚuniformNFc  sÈd| kr |r|f| d<nd| d<|dks0|dkrDtd|›d|›ƒ‚t ¡s`d| kr`t ¡| d<d| d<tƒjf| Ž||_||_t   |¡|_ t   |¡|_ t   |¡|_t  |¡|_||_||_||_dS) NÚ input_shape)NrzKBoth `input_dim` and `output_dim` should be positive, Received input_dim = z and output_dim = ÚdtypeFZautocast)Ú ValueErrorrZv2_dtype_behavior_enabledrZfloatxÚsuperÚ__init__Ú input_dimÚ output_dimrÚgetÚembeddings_initializerrÚembeddings_regularizerÚactivity_regularizerrÚembeddings_constraintÚ mask_zeroZsupports_maskingÚ input_length) ÚselfrrrrrrrrÚkwargs)Ú __class__©úM/var/www/html/venv/lib/python3.7/site-packages/keras/layers/core/embedding.pyrqs*       zEmbedding.__init__cCs0|j|j|jf|jd|j|jdd|_d|_dS)NÚ embeddingsF)ÚshapeZ initializerÚnameZ regularizerÚ constraintZexperimental_autocastT)Z add_weightrrrrrr Zbuilt)rr rrrÚbuild¡s  zEmbedding.buildcCs|js dSt |d¡S)Nr)rÚtfÚ not_equal)rÚinputsÚmaskrrrÚ compute_mask­szEmbedding.compute_maskcCsì|jdkr||jfSt|jttfƒr2t|jƒ}n|jg}t|ƒt|ƒdkrftd|j›d|›ƒ‚nhxftt||dd…ƒƒD]L\}\}}|dk rº|dk rº||krºtd|j›d|›ƒ‚q~|dkr~|||<q~W|dft|ƒ|jfSdS)Néz"input_length" is z, but received input has shape r) rrÚ isinstanceÚlistÚtupleÚlenrÚ enumerateÚzip)rr Zin_lensÚiÚs1Ús2rrrÚcompute_output_shape²s   $ zEmbedding.compute_output_shapecCsZt |¡}|dkr&|dkr&t |d¡}tj |j|¡}|jj|jj krVt ||jj¡}|S)NZint32Zint64) rrr%ÚcastÚnnZembedding_lookupr Z _dtype_policyZ compute_dtypeZvariable_dtype)rr'rÚoutrrrÚcallÌs   zEmbedding.callc sd|j|jt |j¡t |j¡t |j¡t |j ¡|j |j dœ}t ƒ  ¡}tt| ¡ƒt| ¡ƒƒS)N)rrrrrrrr)rrrÚ serializerrrrrrrrrÚ get_configÚdictr,Úitems)rÚconfigZ base_config)rrrr:Ús  zEmbedding.get_config)r NNNFN)N)N)Ú__name__Ú __module__Ú __qualname__Ú__doc__rZallow_initializer_layoutrr Zshape_type_conversionr$r)r4r8r:Ú __classcell__rr)rrr !sN& r )rAZtensorflow.compat.v2ÚcompatZv2r%ZkerasrrrrZ keras.dtensorrZ keras.enginerZkeras.engine.base_layerrZ keras.utilsr Z tensorflow.python.util.tf_exportr r rrrrÚs