§ ~Wêh–Iãób—dZddlmcmZddlmZejjjZ ejjj Z ejjj Z ejjjZejjjZejjjjZejjjZejjjZeddgd¬¦«e ¦«edd gd¬¦«e ¦«ed d gd¬¦«e ¦«ed gd¬¦«e¦«ed dgd¬¦«e¦«eddgd¬¦«e¦«edgd¬¦«e¦«edgd¬¦«e¦«egd¢¬¦«Gd„dejjj¦«¦«Zegd¢¬¦«Gd„dejjj¦«¦«Zeddg¬¦«Gd„dejjj¦«¦«Zedg¬¦«Gd„d ejjj¦«¦«Zed!g¬¦«Gd"„d#ejjj¦«¦«Z ed$g¬¦«Gd%„d&ejjj¦«¦«Z!ed'g¬¦«Gd(„d)ejjj¦«¦«Z"dS)*zKeras initializers for TF 1.éN)Ú keras_exportzkeras.initializers.Zeroszkeras.initializers.zerosT)Úv1Úallow_multiple_exportszkeras.initializers.Oneszkeras.initializers.oneszkeras.initializers.Constantzkeras.initializers.constantz"keras.initializers.VarianceScalingzkeras.initializers.Orthogonalzkeras.initializers.orthogonalzkeras.initializers.Identityzkeras.initializers.identityz!keras.initializers.glorot_uniformz keras.initializers.glorot_normal)zkeras.initializers.RandomNormalz keras.initializers.random_normalzkeras.initializers.normal)rcó6‡—eZdZdZdddejfˆfd„ ZˆxZS)Ú RandomNormalaýInitializer that generates a normal distribution. Args: mean: a python scalar or a scalar tensor. Mean of the random values to generate. stddev: a python scalar or a scalar tensor. Standard deviation of the random values to generate. seed: A Python integer. Used to create random seeds. See `tf.compat.v1.set_random_seed` for behavior. dtype: Default data type, used if no `dtype` argument is provided when calling the initializer. Only floating point types are supported. @compatibility(TF2) Although it is a legacy compat.v1 api, `tf.compat.v1.keras.initializers.RandomNormal` is compatible with eager execution and `tf.function`. To switch to native TF2, switch to using `tf.keras.initializers.RandomNormal` (not from `compat.v1`) and if you need to change the default dtype use `tf.keras.backend.set_floatx(float_dtype)` or pass the dtype when calling the initializer, rather than passing it when constructing the initializer. Random seed behavior: Also be aware that if you pass a seed to the TF2 initializer API it will reuse that same seed for every single initialization (unlike the TF1 initializer) #### Structural Mapping to Native TF2 Before: ```python initializer = tf.compat.v1.keras.initializers.RandomNormal( mean=mean, stddev=stddev, seed=seed, dtype=dtype) weight_one = tf.Variable(initializer(shape_one)) weight_two = tf.Variable(initializer(shape_two)) ``` After: ```python initializer = tf.keras.initializers.RandomNormal( mean=mean, # seed=seed, # Setting a seed in the native TF2 API # causes it to produce the same initializations # across multiple calls of the same initializer. stddev=stddev) weight_one = tf.Variable(initializer(shape_one, dtype=dtype)) weight_two = tf.Variable(initializer(shape_two, dtype=dtype)) ``` #### How to Map Arguments | TF1 Arg Name | TF2 Arg Name | Note | | :---------------- | :-------------- | :------------------------- | | `mean` | `mean` | No change to defaults | | `stddev` | `stddev` | No change to defaults | | `seed` | `seed` | Different random number generation | : : : semantics (to change in a : : : : future version). If set, the TF2 version : : : : will use stateless random number : : : : generation which will produce the exact : : : : same initialization even across multiple : : : : calls of the initializer instance. the : : : : `compat.v1` version will generate new : : : : initializations each time. Do not set : : : : a seed if you need different : : : : initializations each time. Instead : : : : either set a global tf seed with : : : : `tf.random.set_seed` if you need : : : : determinism, or initialize each weight: : : : with a separate initializer instance : : : : and a different seed. : | `dtype` | `dtype` | The TF2 native api only takes it | : : : as a `__call__` arg, not a constructor arg. : | `partition_info` | - | (`__call__` arg in TF1) Not supported | #### Example of fixed-seed behavior differences `compat.v1` Fixed seed behavior: >>> initializer = tf.compat.v1.keras.initializers.RandomNormal(seed=10) >>> a = initializer(shape=(2, 2)) >>> b = initializer(shape=(2, 2)) >>> tf.reduce_sum(a - b) == 0 After: >>> initializer = tf.keras.initializers.RandomNormal(seed=10) >>> a = initializer(shape=(2, 2)) >>> b = initializer(shape=(2, 2)) >>> tf.reduce_sum(a - b) == 0 @end_compatibility ççš™™™™™©?NcóR•—t¦« ||||¬¦«dS)N©ÚmeanÚstddevÚseedÚdtype©ÚsuperÚ__init__©Úselfr r rrÚ __class__s €úh/var/www/html/movieo_spanner_bot/venv/lib/python3.11/site-packages/keras/initializers/initializers_v1.pyrzRandomNormal.__init__°s*ø€Ý ‰Œ×Ò˜d¨6¸ÀEÐÑJÔJÐJÐJÐJó©Ú__name__Ú __module__Ú __qualname__Ú__doc__ÚtfÚfloat32rÚ __classcell__©rs@rrr?saø€€€€€ðgðgðR ¨°4¸r¼zðKðKðKðKðKðKðKðKðKðKrr)z keras.initializers.RandomUniformz!keras.initializers.random_uniformzkeras.initializers.uniformcó6‡—eZdZdZdddejfˆfd„ ZˆxZS)Ú RandomUniforma6Initializer that generates tensors with a uniform distribution. Args: minval: A python scalar or a scalar tensor. Lower bound of the range of random values to generate. maxval: A python scalar or a scalar tensor. Upper bound of the range of random values to generate. Defaults to 1 for float types. seed: A Python integer. Used to create random seeds. See `tf.compat.v1.set_random_seed` for behavior. dtype: Default data type, used if no `dtype` argument is provided when calling the initializer. @compatibility(TF2) Although it is a legacy `compat.v1` api, `tf.compat.v1.keras.initializers.RandomUniform` is compatible with eager execution and `tf.function`. To switch to native TF2, switch to using `tf.keras.initializers.RandomUniform` (not from `compat.v1`) and if you need to change the default dtype use `tf.keras.backend.set_floatx(float_dtype)` or pass the dtype when calling the initializer, rather than passing it when constructing the initializer. Random seed behavior: Also be aware that if you pass a seed to the TF2 initializer API it will reuse that same seed for every single initialization (unlike the TF1 initializer) #### Structural Mapping to Native TF2 Before: ```python initializer = tf.compat.v1.keras.initializers.RandomUniform( minval=minval, maxval=maxval, seed=seed, dtype=dtype) weight_one = tf.Variable(initializer(shape_one)) weight_two = tf.Variable(initializer(shape_two)) ``` After: ```python initializer = tf.keras.initializers.RandomUniform( minval=minval, maxval=maxval, # seed=seed, # Setting a seed in the native TF2 API # causes it to produce the same initializations # across multiple calls of the same initializer. ) weight_one = tf.Variable(initializer(shape_one, dtype=dtype)) weight_two = tf.Variable(initializer(shape_two, dtype=dtype)) ``` #### How to Map Arguments | TF1 Arg Name | TF2 Arg Name | Note | | :---------------- | :-------------- | :------------------------- | | `minval` | `minval` | No change to defaults | | `maxval` | `maxval` | No change to defaults | | `seed` | `seed` | Different random number generation | : : : semantics (to change in a : : : : future version). If set, the TF2 version : : : : will use stateless random number : : : : generation which will produce the exact : : : : same initialization even across multiple : : : : calls of the initializer instance. the : : : : `compat.v1` version will generate new : : : : initializations each time. Do not set : : : : a seed if you need different : : : : initializations each time. Instead : : : : either set a global tf seed with : : : `tf.random.set_seed` if you need : : : : determinism, or initialize each weight : : : : with a separate initializer instance : : : : and a different seed. : | `dtype` | `dtype` | The TF2 native api only takes it | : : : as a `__call__` arg, not a constructor arg. : | `partition_info` | - | (`__call__` arg in TF1) Not supported | #### Example of fixed-seed behavior differences `compat.v1` Fixed seed behavior: >>> initializer = tf.compat.v1.keras.initializers.RandomUniform(seed=10) >>> a = initializer(shape=(2, 2)) >>> b = initializer(shape=(2, 2)) >>> tf.reduce_sum(a - b) == 0 After: >>> initializer = tf.keras.initializers.RandomUniform(seed=10) >>> a = initializer(shape=(2, 2)) >>> b = initializer(shape=(2, 2)) >>> tf.reduce_sum(a - b) == 0 @end_compatibility gš™™™™™©¿r NcóR•—t¦« ||||¬¦«dS)N)ÚminvalÚmaxvalrrr)rr$r%rrrs €rrzRandomUniform.__init__(s*ø€Ý ‰Œ×Ò ¨v¸DÈÐÑNÔNÐNÐNÐNrrr s@rr"r"´saø€€€€€ðjðjðX$¨D°tÀ2Ä:ðOðOðOðOðOðOðOðOðOðOrr"z"keras.initializers.TruncatedNormalz#keras.initializers.truncated_normalcó6‡—eZdZdZdddejfˆfd„ ZˆxZS)ÚTruncatedNormalaInitializer that generates a truncated normal distribution. These values are similar to values from a `random_normal_initializer` except that values more than two standard deviations from the mean are discarded and re-drawn. This is the recommended initializer for neural network weights and filters. Args: mean: a python scalar or a scalar tensor. Mean of the random values to generate. stddev: a python scalar or a scalar tensor. Standard deviation of the random values to generate. seed: A Python integer. Used to create random seeds. See `tf.compat.v1.set_random_seed` for behavior. dtype: Default data type, used if no `dtype` argument is provided when calling the initializer. Only floating point types are supported. @compatibility(TF2) Although it is a legacy compat.v1 api, `tf.compat.v1.keras.initializers.TruncatedNormal` is compatible with eager execution and `tf.function`. To switch to native TF2, switch to using `tf.keras.initializers.TruncatedNormal` (not from `compat.v1`) and if you need to change the default dtype use `tf.keras.backend.set_floatx(float_dtype)` or pass the dtype when calling the initializer, rather than passing it when constructing the initializer. Random seed behavior: Also be aware that if you pass a seed to the TF2 initializer API it will reuse that same seed for every single initialization (unlike the TF1 initializer) #### Structural Mapping to Native TF2 Before: ```python initializer = tf.compat.v1.keras.initializers.TruncatedNormal( mean=mean, stddev=stddev, seed=seed, dtype=dtype) weight_one = tf.Variable(initializer(shape_one)) weight_two = tf.Variable(initializer(shape_two)) ``` After: ```python initializer = tf.keras.initializers.TruncatedNormal( mean=mean, # seed=seed, # Setting a seed in the native TF2 API # causes it to produce the same initializations # across multiple calls of the same initializer. stddev=stddev) weight_one = tf.Variable(initializer(shape_one, dtype=dtype)) weight_two = tf.Variable(initializer(shape_two, dtype=dtype)) ``` #### How to Map Arguments | TF1 Arg Name | TF2 Arg Name | Note | | :---------------- | :-------------- | :------------------------- | | `mean` | `mean` | No change to defaults | | `stddev` | `stddev` | No change to defaults | | `seed` | `seed` | Different random number generation | : : : semantics (to change in a : : : : future version). If set, the TF2 version : : : : will use stateless random number : : : : generation which will produce the exact : : : : same initialization even across multiple : : : : calls of the initializer instance. the : : : : `compat.v1` version will generate new : : : : initializations each time. Do not set : : : : a seed if you need different : : : : initializations each time. Instead : : : : either set a global tf seed with : : : `tf.random.set_seed` if you need : : : : determinism, or initialize each weight : : : : with a separate initializer instance : : : : and a different seed. : | `dtype` | `dtype` | The TF2 native api only takes it | : : : as a `__call__` arg, not a constructor arg. : | `partition_info` | - | (`__call__` arg in TF1) Not supported | #### Example of fixed-seed behavior differences `compat.v1` Fixed seed behavior: >>> initializer = tf.compat.v1.keras.initializers.TruncatedNormal(seed=10) >>> a = initializer(shape=(2, 2)) >>> b = initializer(shape=(2, 2)) >>> tf.reduce_sum(a - b) == 0 After: >>> initializer = tf.keras.initializers.TruncatedNormal(seed=10) >>> a = initializer(shape=(2, 2)) >>> b = initializer(shape=(2, 2)) >>> tf.reduce_sum(a - b) == 0 @end_compatibility rr NcóR•—t¦« ||||¬¦«dS)aMInitializer that generates a truncated normal distribution. Args: mean: a python scalar or a scalar tensor. Mean of the random values to generate. stddev: a python scalar or a scalar tensor. Standard deviation of the random values to generate. seed: A Python integer. Used to create random seeds. See `tf.compat.v1.set_random_seed` for behavior. dtype: Default data type, used if no `dtype` argument is provided when calling the initializer. Only floating point types are supported. r Nrrs €rrzTruncatedNormal.__init__¡s,ø€õ ‰Œ×Ò˜d¨6¸ÀEÐÑJÔJÐJÐJÐJrrr s@rr'r',saø€€€€€ðlðlð\ ¨°4¸r¼zðKðKðKðKðKðKðKðKðKðKrr'zkeras.initializers.lecun_normalcó&‡—eZdZdˆfd„ Zd„ZˆxZS)Ú LecunNormalNcóR•—t¦« ddd|¬¦«dS)Nçð?Úfan_inÚtruncated_normal©ÚscaleÚmodeÚ distributionrr©rrrs €rrzLecunNormal.__init__´ó8ø€Ý ‰Œ×ÒؘHÐ3EÈDð ñ ô ð ð ð rcó—d|jiS©Nr©r©rs rÚ get_configzLecunNormal.get_config¹ó€Ø˜œ Ð"Ð"r©N©rrrrr9rr s@rr*r*²óLø€€€€€ð ð ð ð ð ð ð #ð#ð#ð#ð#ð#ð#rr*z keras.initializers.lecun_uniformcó&‡—eZdZdˆfd„ Zd„ZˆxZS)Ú LecunUniformNcóR•—t¦« ddd|¬¦«dS)Nr,r-Úuniformr/rr3s €rrzLecunUniform.__init__¿ó7ø€Ý ‰Œ×ÒؘH°9À4ð ñ ô ð ð ð rcó—d|jiSr6r7r8s rr9zLecunUniform.get_configÄr:rr;r<r s@rr?r?½r=rr?zkeras.initializers.he_normalcó&‡—eZdZdˆfd„ Zd„ZˆxZS)ÚHeNormalNcóR•—t¦« ddd|¬¦«dS)Nç@r-r.r/rr3s €rrzHeNormal.__init__Êr4rcó—d|jiSr6r7r8s rr9zHeNormal.get_configÏr:rr;r<r s@rrErEÈr=rrEzkeras.initializers.he_uniformcó&‡—eZdZdˆfd„ Zd„ZˆxZS)Ú HeUniformNcóR•—t¦« ddd|¬¦«dS)NrGr-rAr/rr3s €rrzHeUniform.__init__ÕrBrcó—d|jiSr6r7r8s rr9zHeUniform.get_configÚr:rr;r<r s@rrJrJÓr=rrJ)#rÚtensorflow.compat.v2ÚcompatÚv2rÚ tensorflow.python.util.tf_exportrrÚzeros_initializerÚ_v1_zeros_initializerÚones_initializerÚ_v1_ones_initializerÚconstant_initializerÚ_v1_constant_initializerÚvariance_scaling_initializerÚ _v1_variance_scaling_initializerÚorthogonal_initializerÚ_v1_orthogonal_initializerÚ initializersÚidentityÚ _v1_identityÚglorot_uniform_initializerÚ_v1_glorot_uniform_initializerÚglorot_normal_initializerÚ_v1_glorot_normal_initializerÚrandom_normal_initializerrÚrandom_uniform_initializerr"Útruncated_normal_initializerr'r*r?rErJ©rrúrfsëðð#Ð"ð"Ð!Ð!Ð!Ð!Ð!Ð!Ð!Ð!ð:Ð9Ð9Ð9Ð9Ð9àœ œ Ô6ÐØ”y”|Ô4ÐØœ9œ<Ô<ÐØ#%¤9¤<Ô#LÐ ØœYœ\Ô@ÐØŒyŒ|Ô(Ô1€ Ø!#¤¤Ô!HÐØ "¤ ¤ Ô FÐð€ € Ø"Ð$>Ð?Øðñôðñôðð€ € Ø!Ð#<Ð=Øðñôðñôðð€ € Ø%Ð'DÐEØðñôðñôðð€ € Ø,Ð-Àdðñôà"ñ$ô$ð$ð€ € Ø'Ð)HÐIØðñôðñôðð€ € Ø%Ð'DÐEØðñôðñôðð€ € Ø+Ð,ÀTðñôà ñ"ô"ð"ð€ € Ø*Ð+ÀDðñôàñ!ô!ð!ð €ððððñôðkKðkKðkKðkKðkK2”9”<Ô9ñkKôkKñôðkKð\€ððððñôðnOðnOðnOðnOðnOB”I”LÔ;ñnOônOñôðnOðb€à,Ø-ððñôð }Kð}Kð}Kð}Kð}Kb”i”lÔ?ñ}Kô}Kñ ôð }Kð@€Ð3Ð4Ð5Ñ5Ô5ð#ð#ð#ð#ð#"”)”,Ô;ñ#ô#ñ6Ô5ð#ð€Ð4Ð5Ð6Ñ6Ô6ð#ð#ð#ð#ð#2”9”<Ô<ñ#ô#ñ7Ô6ð#ð€Ð0Ð1Ð2Ñ2Ô2ð#ð#ð#ð#ð#ˆrŒyŒ|Ô8ñ#ô#ñ3Ô2ð#ð€Ð1Ð2Ð3Ñ3Ô3ð#ð#ð#ð#ð#” ” Ô9ñ#ô#ñ4Ô3ð#ð#ð#r