B ӻd`@sdZddlZddlmZddlmZddlmZddlm Z ddlm Z ddl m Z dd lmZdd lmZdd lmZed gd GdddeZedgd GdddeZdaeddgd ddZddZeddgd ddZejddZdd Zd!d"Zd#d$Zd'd%d&Z dS)(z7Contains the Policy class for mixed precision training.N)dtypes)backend)base_layer_utils)device_compatibility_check) loss_scale) generic_utils) tf_logging)mixed_precision_global_state) keras_exportzkeras.mixed_precision.Policy)Zv1c@sbeZdZdZddZddZeddZedd Zed d Z d d Z ddZ e dddZ dS)PolicyaA dtype policy for a Keras layer. A dtype policy determines a layer's computation and variable dtypes. Each layer has a policy. Policies can be passed to the `dtype` argument of layer constructors, or a global policy can be set with `tf.keras.mixed_precision.set_global_policy`. Args: name: The policy name, which determines the compute and variable dtypes. Can be any dtype name, such as `'float32'` or `'float64'`, which causes both the compute and variable dtypes will be that dtype. Can also be the string `'mixed_float16'` or `'mixed_bfloat16'`, which causes the compute dtype to be float16 or bfloat16 and the variable dtype to be float32. Typically you only need to interact with dtype policies when using mixed precision, which is the use of float16 or bfloat16 for computations and float32 for variables. This is why the term `mixed_precision` appears in the API name. Mixed precision can be enabled by passing `'mixed_float16'` or `'mixed_bfloat16'` to `tf.keras.mixed_precision.set_global_policy`. See [the mixed precision guide](https://www.tensorflow.org/guide/keras/mixed_precision) for more information on how to use mixed precision. >>> tf.keras.mixed_precision.set_global_policy('mixed_float16') >>> layer1 = tf.keras.layers.Dense(10) >>> layer1.dtype_policy # `layer1` will automatically use mixed precision >>> # Can optionally override layer to use float32 instead of mixed precision. >>> layer2 = tf.keras.layers.Dense(10, dtype='float32') >>> layer2.dtype_policy >>> # Set policy back to initial float32 for future examples. >>> tf.keras.mixed_precision.set_global_policy('float32') In the example above, passing `dtype='float32'` to the layer is equivalent to passing `dtype=tf.keras.mixed_precision.Policy('float32')`. In general, passing a dtype policy name to a layer is equivalent to passing the corresponding policy, so it is never necessary to explicitly construct a `Policy` object. Note: `Model.compile` will automatically wrap an optimizer with a `tf.keras.mixed_precision.LossScaleOptimizer` if you use the `'mixed_float16'` policy. If you use a custom training loop instead of calling `Model.compile`, you should explicitly use a `tf.keras.mixed_precision.LossScaleOptimizer` to avoid numeric underflow with float16. ### How a layer uses its policy's compute dtype A layer casts its inputs to its compute dtype. This causes the layer's computations and output to also be in the compute dtype. For example: >>> x = tf.ones((4, 4, 4, 4), dtype='float64') >>> # `layer`'s policy defaults to float32. >>> layer = tf.keras.layers.Conv2D(filters=4, kernel_size=2) >>> layer.compute_dtype # Equivalent to layer.dtype_policy.compute_dtype 'float32' >>> # `layer` casts its inputs to its compute dtype and does computations in >>> # that dtype. >>> y = layer(x) >>> y.dtype tf.float32 Note that the base `tf.keras.layers.Layer` class inserts the casts. If subclassing your own layer, you do not have to insert any casts. Currently, only tensors in the first argument to the layer's `call` method are casted (although this will likely be changed in a future minor release). For example: >>> class MyLayer(tf.keras.layers.Layer): ... # Bug! `b` will not be casted. ... def call(self, a, b): ... return a + 1., b + 1. >>> a = tf.constant(1., dtype="float32") >>> b = tf.constant(1., dtype="float32") >>> layer = MyLayer(dtype="float64") >>> x, y = layer(a, b) >>> x.dtype tf.float64 >>> y.dtype tf.float32 If writing your own layer with multiple inputs, you should either explicitly cast other tensors to `self.compute_dtype` in `call` or accept all tensors in the first argument as a list. The casting only occurs in TensorFlow 2. If `tf.compat.v1.disable_v2_behavior()` has been called, you can enable the casting behavior with `tf.compat.v1.keras.layers.enable_v2_dtype_behavior()`. ### How a layer uses its policy's variable dtype The default dtype of variables created by `tf.keras.layers.Layer.add_weight` is the layer's policy's variable dtype. If a layer's compute and variable dtypes differ, `add_weight` will wrap floating-point variables with a special wrapper called an `AutoCastVariable`. `AutoCastVariable` is identical to the original variable except it casts itself to the layer's compute dtype when used within `Layer.call`. This means if you are writing a layer, you do not have to explicitly cast the variables to the layer's compute dtype. For example: >>> class SimpleDense(tf.keras.layers.Layer): ... ... def build(self, input_shape): ... # With mixed precision, self.kernel is a float32 AutoCastVariable ... self.kernel = self.add_weight('kernel', (input_shape[-1], 10)) ... ... def call(self, inputs): ... # With mixed precision, self.kernel will be casted to float16 ... return tf.linalg.matmul(inputs, self.kernel) ... >>> layer = SimpleDense(dtype='mixed_float16') >>> y = layer(tf.ones((10, 10))) >>> y.dtype tf.float16 >>> layer.kernel.dtype tf.float32 A layer author can prevent a variable from being wrapped with an `AutoCastVariable` by passing `experimental_autocast=False` to `add_weight`, which is useful if the float32 value of the variable must be accessed within the layer. ### How to write a layer that supports mixed precision and float64. For the most part, layers will automatically support mixed precision and float64 without any additional work, due to the fact the base layer automatically casts inputs, creates variables of the correct type, and in the case of mixed precision, wraps variables with `AutoCastVariables`. The primary case where you need extra work to support mixed precision or float64 is when you create a new tensor, such as with `tf.ones` or `tf.random.normal`, In such cases, you must create the tensor of the correct dtype. For example, if you call `tf.random.normal`, you must pass the compute dtype, which is the dtype the inputs have been casted to: >>> class AddRandom(tf.keras.layers.Layer): ... ... def call(self, inputs): ... # We must pass `dtype=inputs.dtype`, otherwise a TypeError may ... # occur when adding `inputs` to `rand`. ... rand = tf.random.normal(shape=inputs.shape, dtype=inputs.dtype) ... return inputs + rand >>> layer = AddRandom(dtype='mixed_float16') >>> y = layer(x) >>> y.dtype tf.float16 If you did not pass `dtype=inputs.dtype` to `tf.random.normal`, a `TypeError` would have occurred. This is because the `tf.random.normal`'s dtype defaults to `"float32"`, but the input dtype is float16. You cannot add a float32 tensor with a float16 tensor. cCsdt|tjrtd|jfnt|ts6td|f||_||\|_|_ |dkr`t |dS)NzG'name' must be a string, not a DType. Instead, pass DType.name. Got: %sz$'name' must be a string, but got: %s) mixed_float16Z mixed_bloat16) isinstancerZDType TypeErrornamestr_name _parse_name_compute_dtype_variable_dtyperZlog_device_compatibility_check)selfrr`/var/www/html/venv/lib/python3.7/site-packages/tensorflow/python/keras/mixed_precision/policy.py__init__s  zPolicy.__init__cCs|drVd}|dkr |d7}n"|dkr2|d7}n|dkrB|d7}|d |7}t||d krbd S|d krnd S|dkrzdSyt|j}Wn&tk rd|f}t|YnX||fS)zParses a Policy name into a compute and variable dtype. Args: name: The name of the policy: Returns: The (compute_dtype, variable_dtype) pair. Z _float32_varszEPolicies ending in '_float32_vars' have been removed from TensorFlow.)Zinfer_float32_varsZinfer_with_float32_varszC Please use the 'mixed_float16' or 'mixed_bfloat16' policy instead.Zfloat16_with_float32_varsz/ Please use the 'mixed_float16' policy instead.Zbfloat16_with_float32_varsz0 Please use the 'mixed_bfloat16' policy instead.z Got policy name: '%s'r )float16float32Zmixed_bfloat16)Zbfloat16r_infer)NNzCannot convert value %s to a mixed precision Policy. Valid policies include 'mixed_float16', 'mixed_bfloat16', and the name of any dtype such as 'float32'.)endswith ValueErrorras_dtyperr)rr error_msgdtypeerrorrrrrs.     zPolicy._parse_namecCs|jS)aThe variable dtype of this policy. This is the dtype layers will create their variables in, unless a layer explicitly chooses a different dtype. If this is different than `Policy.compute_dtype`, Layers will cast variables to the compute dtype to avoid type errors. Variable regularizers are run in the variable dtype, not the compute dtype. Returns: The variable dtype of this policy, as a string. )r)rrrrvariable_dtypeszPolicy.variable_dtypecCs|jS)aThe compute dtype of this policy. This is the dtype layers will do their computations in. Typically layers output tensors with the compute dtype as well. Note that even if the compute dtype is float16 or bfloat16, hardware devices may not do individual adds, multiplies, and other fundamental operations in float16 or bfloat16, but instead may do some of them in float32 for numeric stability. The compute dtype is the dtype of the inputs and outputs of the TensorFlow ops that the layer executes. Internally, many TensorFlow ops will do certain internal calculations in float32 or some other device-internal intermediate format with higher precision than float16/bfloat16, to increase numeric stability. For example, a `tf.keras.layers.Dense` layer, when run on a GPU with a float16 compute dtype, will pass float16 inputs to `tf.linalg.matmul`. But, `tf.linalg.matmul` will do use float32 intermediate math. The performance benefit of float16 is still apparent, due to increased memory bandwidth and the fact modern GPUs have specialized hardware for computing matmuls on float16 inputs while still keeping intermediate computations in float32. Returns: The compute dtype of this policy, as a string. )r)rrrr compute_dtypeszPolicy.compute_dtypecCs|jS)z Returns the name of this policy.)r)rrrrr"sz Policy.namecCs d|jS)Nz )r)rrrr__repr__'szPolicy.__repr__cCs d|jiS)Nr)r)rrrr get_config*szPolicy.get_configNcCs"~d|kr|}|d=|f|S)Nr)copy)clsconfigcustom_objectsrrr from_config-s zPolicy.from_config)N)__name__ __module__ __qualname____doc__rrpropertyr"r#rr$r% classmethodr*rrrrr s 0   r z)keras.mixed_precision.experimental.PolicycsLeZdZdZdfdd ZeddZddZd d Ze dd d Z Z S)PolicyV1aDA deprecated dtype policy for a Keras layer. Warning: This class is now deprecated and will be removed soon. Please use the non-experimental class `tf.keras.mixed_precision.Policy` instead. The difference between this class and the non-experimental class is that this class has a `loss_scale` field and the non-experimental class does not. The loss scale is only used by `tf.keras.Model.compile`, which automatically wraps the optimizer with a `LossScaleOptimizer` if the optimizer is not already a `LossScaleOptimizer`. For the non-experimental Policy class, `Model.compile` instead wraps the optimizer with a `LossScaleOptimizer` if `Policy.name` is "mixed_float16". When deserializing objects with an experimental policy using functions like `tf.keras.utils.deserialize_keras_object`, the policy will be deserialized as the non-experimental `tf.keras.mixed_precision.Policy`, and the loss scale will silently be dropped. This is so that SavedModels that are generated with an experimental policy can be restored after the experimental policy is removed. autocsftt|||dkr0|dkr$dnd}d|_nd|_|rV|jdkrVtd||ft||_ dS) aConstructs the policy. The `name` argument determines the compute and variable dtype, the default loss scale, and has no additional effect on the Policy. The compute and variable dtypes can only be specified through `name`, and cannot be specified directly. Args: name: A string. Can be one of the following values: * Any dtype name, such as 'float32' or 'float64'. Both the variable and compute dtypes will be that dtype. * 'mixed_float16' or 'mixed_bfloat16': The compute dtype is float16 or bfloat16, while the variable dtype is float32. With 'mixed_float16', a dynamic loss scale is used. These policies are used for mixed precision training. loss_scale: A `tf.compat.v1.mixed_precision.LossScale`, an int (which uses a `FixedLossScale`), the string "dynamic" (which uses a `DynamicLossScale`), or None (which uses no loss scale). Defaults to `"auto"`. In the `"auto"` case: 1) if `name` is `"mixed_float16"`, then use `loss_scale="dynamic"`. 2) otherwise, do not use a loss scale. Only `tf.keras.Model`s, not layers, use the loss scale, and it is only used during `Model.fit`, `Model.train_on_batch`, and other similar methods. r2r ZdynamicNTF)NrzCreating a Policy with a loss scale is only useful for float16 policies. You passed loss_scale=%r for policy %s. Consider not passing any loss_scale instead.) superr1r_using_default_loss_scalerrwarningkeras_loss_scale_moduleget _loss_scale)rrr) __class__rrrOs zPolicyV1.__init__cCs|jS)zReturns the loss scale of this Policy. Returns: A `tf.compat.v1.mixed_precision.experimental.LossScale`, or None. )r8)rrrrruszPolicyV1.loss_scalecCsd|j|jfS)Nz)rr)rrrrr$~szPolicyV1.__repr__cCs$d|ji}|js t|j|d<|S)Nrr)rr4r6 serializer)rr(rrrr%s zPolicyV1.get_configNcCs>d|kr4t|dtr4|}tj|d|d|d<|f|S)Nr)r))r dictr&r6 deserialize)r'r(r)rrrr*s zPolicyV1.from_config)r2)N) r+r,r-r.rr/rr$r%r0r* __classcell__rr)r9rr18s&  r1z#keras.mixed_precision.global_policyz0keras.mixed_precision.experimental.global_policycCs(tdkr$trttStdStS)aReturns the global dtype policy. The global policy is the default `tf.keras.mixed_precision.Policy` used for layers, if no policy is passed to the layer constructor. If no policy has been set with `keras.mixed_precision.set_global_policy`, this will return a policy constructed from `tf.keras.backend.floatx()` (floatx defaults to float32). >>> tf.keras.mixed_precision.global_policy() >>> tf.keras.layers.Dense(10).dtype_policy # Defaults to the global policy If TensorFlow 2 behavior has been disabled with `tf.compat.v1.disable_v2_behavior()`, this will instead return a special "_infer" policy which infers the dtype from the dtype of the first input the first time the layer is called. This behavior matches the behavior that existed in TensorFlow 1. See `tf.keras.mixed_precision.Policy` for more information on policies. Returns: The global Policy. Nr)_global_policyrv2_dtype_behavior_enabledr rZfloatxrrrr global_policys  r@cCstrtdj|ddS)NaMThe global dtype policy cannot be set to "{policy.name}", because the mixed precision graph rewrite has already been enabled. At most, one of the following can be called: 1. tf.compat.v1.train.enable_mixed_precision_graph_rewrite() (You called this first) 2. tf.keras.mixed_precision.experimental.set_global_policy() with a mixed precision policy (You called this second) You called both functions, which is an error, because both functions enable you to use mixed precision. If in doubt which function to use, use the second, as it supports Eager execution and is more customizable.)policy)r Z(is_mixed_precision_graph_rewrite_enabledrformat)rArrr2_check_if_mixed_precision_graph_rewrite_is_enableds rCz'keras.mixed_precision.set_global_policyz4keras.mixed_precision.experimental.set_global_policycCststd|dk r*t|ts*t|}|dk o<|j|jk}|rJt||dk rz|jdk rzt |jj sztd|j f|a t |dS)aSets the global dtype policy. The global policy is the default `tf.keras.mixed_precision.Policy` used for layers, if no policy is passed to the layer constructor. >>> tf.keras.mixed_precision.set_global_policy('mixed_float16') >>> tf.keras.mixed_precision.global_policy() >>> tf.keras.layers.Dense(10).dtype_policy >>> # Global policy is not used if a policy is directly passed to constructor >>> tf.keras.layers.Dense(10, dtype='float64').dtype_policy >>> tf.keras.mixed_precision.set_global_policy('float32') If no global policy is set, layers will instead default to a Policy constructed from `tf.keras.backend.floatx()`. To use mixed precision, the global policy should be set to `'mixed_float16'` or `'mixed_bfloat16'`, so that every layer uses a 16-bit compute dtype and float32 variable dtype by default. Only floating point policies can be set as the global policy, such as `'float32'` and `'mixed_float16'`. Non-floating point policies such as `'int32'` and `'complex64'` cannot be set as the global policy because most layers do not support such policies. See `tf.keras.mixed_precision.Policy` for more information. Args: policy: A Policy, or a string that will be converted to a Policy. Can also be None, in which case the global policy will be constructed from `tf.keras.backend.floatx()` zThe global policy can only be set in TensorFlow 2 or if V2 dtype behavior has been set. To enable V2 dtype behavior, call "tf.compat.v1.keras.layers.enable_v2_dtype_behavior()"Nzset_global_policy can only be used to set the global policy to floating-point policies, such as "float32" and "mixed_float16", but got policy: %s)rr?rr r r#r"rCrrZ is_floatingrr>r Z set_using_mixed_precision_policy)rAZis_mixed_policyrrrset_global_policys&  rDccs&t}zt|dVWdt|XdS)zA context manager that sets the global Policy under it. Args: policy: A Policy, or a string that will be converted to a Policy.. Yields: Nothing. N)r>rD)rAZ old_policyrrr policy_scope s  rEcCs(yt|dStk r"dSXdS)NTF)rrr)r rrr_is_convertible_to_dtypes  rFcCs6t|tko4t|dgko4|jdkp4t|jS)aReturns True if the Policy is equivalent to a single dtype. A policy is equivalent to a single dtype if the policy's compute and variable dtypes are the same and the policy's type is Policy and not a subclass of Policy (such as PolicyV1). The "_infer" policy is considered equivalent to a single dtype. Args: policy: A Policy. Returns: True, if the policy is equivalent to a single dtype. rr)typer listr%keysrrF)rArrr_policy_equivalent_to_dtype$s rJcCs&t|r|jdkrdS|jSt|S)Nr)rJrrZserialize_keras_object)rArrrr::sr:cCsFt|trt|rt|S|dkr*tdSttd}tj|||ddS)Nr)r r1z dtype policy)module_objectsr)Zprintable_module_name)r rrFr rZdeserialize_keras_object)r(r)rKrrrr<Cs r<)N)!r. contextlibZtensorflow.python.frameworkrZtensorflow.python.kerasrZtensorflow.python.keras.enginerZ'tensorflow.python.keras.mixed_precisionrrr6Ztensorflow.python.keras.utilsrZtensorflow.python.platformrZ'tensorflow.python.training.experimentalr Z tensorflow.python.util.tf_exportr objectr r1r>r@rCrDcontextmanagerrErFrJr:r<rrrrs6         `!;