o Neg@s\dZddlZddlZddlZddlZddlZddlZddlZddl Z ddl Z ddl Z ddl Z ddl Z ddlZddlZddlZddlmZddlmZddlZddlmmZddlmZddlmZddlmZddl m!Z!dd l"m#Z#dd l$m%Z% dKd d Z&ddZ(dLddZ)e#d          dMddZ*ddZ+dNddZ,dOd d!Z-dPd"d#Z.Gd$d%d%Z/d&d'Z0e#d(Gd)d*d*Z1d+d,Z2ia3da4e5Z6da7e8Z9da:e ;Zd1d2Z?d3d4Z@d5d6ZAe#d7Gd8d9d9ZBe#d:Gd;d<dZDd?d@ZEe#dAGdBdCdCeBZFe#dDdE  F G G HdQdIdJZGdS)Rz(Utilities for file download and caching.N)abstractmethod)closing)urlsplit)io_utils) tf_inspect)Progbar) keras_export)urlopenTcCs`ddd}t||}t|d}|||dD]}||qWddS1s)wYdS)aReplacement for `urlretrieve` for Python 2. Under Python 2, `urlretrieve` relies on `FancyURLopener` from legacy `urllib` module, known to have issues with proxy management. Args: url: url to retrieve. filename: where to store the retrieved data locally. reporthook: a hook function that will be called once on establishment of the network connection and once after each block read thereafter. The hook will be passed three arguments; a count of blocks transferred so far, a block size in bytes, and the total size of the file. data: `data` argument passed to `urlopen`. Ncssf|d}d}|durt|}d} ||}|d7}|dur*|||||r0|VndSq)NzContent-LengthrT)infogetintstripread)response chunk_size reporthook content_type total_sizecountchunkrFD:\Projects\ConvertPro\env\Lib\site-packages\keras/utils/data_utils.py chunk_readDs   zurlretrieve..chunk_readwb)r)r N)r openwrite)urlfilenamerdatarrfdrrrr urlretrieve3s    "r#)r#cCsJttttttf}t|tjt j f|rdSt |p$t|t p$t|tjS)z'Check if `x` is a Keras generator type.F)strlisttupledictset frozenset isinstancetfZTensornpZndarrayr isgeneratorSequencetypingIterator)xZbuiltin_iteratorsrrris_generator_or_sequence]s  r2.autoc Cs|durdS|dkrddg}t|tr|g}t|}t|}|D]^}|dkr.tj}tj}|dkr8tj}tj }||r||5}z| |Wn#tj t t fyktj|rjtj|ret|t|wWddS1sxwYdSq"dS)aNExtracts an archive if it matches tar, tar.gz, tar.bz, or zip formats. Args: file_path: path to the archive file path: path to extract the archive file archive_format: Archive format to try for extracting the file. Options are 'auto', 'tar', 'zip', and None. 'tar' includes tar, tar.gz, and tar.bz files. The default 'auto' is ['tar', 'zip']. None or an empty list will return no matches found. Returns: True if a match was found and an archive extraction was completed, False otherwise. NFr4tarzipT)r*r$rpath_to_stringtarfiler is_tarfilezipfileZipFile is_zipfile extractallTarError RuntimeErrorKeyboardInterruptospathexistsisfileremoveshutilrmtree) file_pathrBarchive_formatZ archive_typeZopen_fnZ is_match_fnarchiverrr_extract_archiveisD            rKzkeras.utils.get_fileFdatasetsc  Cs|durtd| durtjtjdd} |dur#|dur#|}d}tj| } t| tjs7tjdd} tj| |} t| t |}|s\tj t |j}|s\td|d|r| d rtt |}|d d }t|}tj| |} | d } ntj| |} d }tj| r|durt| ||d std |d|dd}nd}|r3td|Gddd}d}z=z t|| |Wn1tjjy}z t|||j|jd}~wtjjy}z t|||j|jd}~wwWnttfytj| rt | wtj| r3|dur3t| ||d s3td|d|d|rFtj| sDt!| | dd| S|rOt!| | || S)aM Downloads a file from a URL if it not already in the cache. By default the file at the url `origin` is downloaded to the cache_dir `~/.keras`, placed in the cache_subdir `datasets`, and given the filename `fname`. The final location of a file `example.txt` would therefore be `~/.keras/datasets/example.txt`. Files in tar, tar.gz, tar.bz, and zip formats can also be extracted. Passing a hash will verify the file after download. The command line programs `shasum` and `sha256sum` can compute the hash. Example: ```python path_to_downloaded_file = tf.keras.utils.get_file( "flower_photos", "https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz", untar=True) ``` Args: fname: Name of the file. If an absolute path `/path/to/file.txt` is specified the file will be saved at that location. If `None`, the name of the file at `origin` will be used. origin: Original URL of the file. untar: Deprecated in favor of `extract` argument. boolean, whether the file should be decompressed md5_hash: Deprecated in favor of `file_hash` argument. md5 hash of the file for verification file_hash: The expected hash string of the file after download. The sha256 and md5 hash algorithms are both supported. cache_subdir: Subdirectory under the Keras cache dir where the file is saved. If an absolute path `/path/to/folder` is specified the file will be saved at that location. hash_algorithm: Select the hash algorithm to verify the file. options are `'md5'`, `'sha256'`, and `'auto'`. The default 'auto' detects the hash algorithm in use. extract: True tries extracting the file as an Archive, like tar or zip. archive_format: Archive format to try for extracting the file. Options are `'auto'`, `'tar'`, `'zip'`, and `None`. `'tar'` includes tar, tar.gz, and tar.bz files. The default `'auto'` corresponds to `['tar', 'zip']`. None or an empty list will return no matches found. cache_dir: Location to store cached files, when None it defaults to the default directory `~/.keras/`. Returns: Path to the downloaded file NzCPlease specify the "origin" argument (URL of the file to download).~z.kerasmd5z/tmpz5Can't parse the file name from the origin provided: 'z0'.Please specify the `fname` as the input param.z.tar.gzF) algorithmzNA local file was found, but it seems to be incomplete or outdated because the z0 file hash does not match the original value of z! so we will re-download the data.TzDownloading data from c@s eZdZdZddZddZdS)zget_file..DLProgbarz1Manage progress bar state for use in urlretrieve.cSsd|_d|_dSNF)progbarfinishedselfrrr__init__s z$get_file..DLProgbar.__init__cSsx|js|dkr d}t||_||}|dur|j|dS||kr*|j|dS|js:|j|jjd|_dSdS)Nr T)rRrupdaterStarget)rUZ block_num block_sizercurrentrrr__call__s  z$get_file..DLProgbar.__call__N)__name__ __module__ __qualname____doc__rVr[rrrr DLProgbars r`z!URL fetch failure on {}: {} -- {}z+Incomplete or corrupted file detected. The z0 file hash does not match the provided value of r3r5)rI)" ValueErrorrArBjoin expanduseraccessW_OK_makedirs_exist_okrr7basenamerendswithpathlibPath with_suffixr$rC validate_fileZ print_msgr#urlliberror HTTPError ExceptionformatcodemsgURLErrorerrnoreasonr@rErK)fnameoriginZuntarZmd5_hash file_hashZ cache_subdirZhash_algorithmextractrI cache_dirZ datadir_basedatadirZ untar_fpathfpathdownloadr` error_msgerrrget_files>        rcCstj|dddS)NT)exist_ok)rAmakedirs)r|rrrrfMsrfcCs<|dkrtS|dkr|durt|dkrtStS)z+Returns hash algorithm as hashlib function.sha256r4N@)hashlibrlenrN)rPryrrr_resolve_hasherQs rrcstt|tr t|}n|}t|dtfdddD]}||qWd|S1s1wY|S)aCalculates a file sha256 or md5 hash. Example: ```python _hash_file('/path/to/file.zip') 'e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855' ``` Args: fpath: path to the file being validated algorithm: hash algorithm, one of `'auto'`, `'sha256'`, or `'md5'`. The default `'auto'` detects the hash algorithm in use. chunk_size: Bytes to read at a time, important for large files. Returns: The file hash rbcs SN)rrrZ fpath_filerrvs z_hash_file..N)r*r$rriterrW hexdigest)r}rPrhasherrrrr _hash_file]s     rcCs*t||}tt|||t|krdSdS)aValidates a file against a sha256 or md5 hash. Args: fpath: path to the file being validated file_hash: The expected hash string of the file. The sha256 and md5 hash algorithms are both supported. algorithm: Hash algorithm, one of 'auto', 'sha256', or 'md5'. The default 'auto' detects the hash algorithm in use. chunk_size: Bytes to read at a time, important for large files. Returns: Whether the file is valid TF)rr$r)r}ryrPrrrrrrl|s rlc@s0eZdZdZddZddZddZdd Zd S) ThreadsafeIterzEWrap an iterator with a lock and propagate exceptions to all threads.cCs||_t|_d|_dSr)it threadingLocklock _exception)rUrrrrrVs  zThreadsafeIter.__init__cCs|SrrrTrrr__iter__szThreadsafeIter.__iter__cCs|Sr)__next__rTrrrnextszThreadsafeIter.nextc Csd|j%|jr |jz t|jWWdSty'}z||_d}~ww1s+wYdSr)rrrrrp)rUrrrrrs zThreadsafeIter.__next__N)r\r]r^r_rVrrrrrrrrs  rctfdd}|S)Ncst|i|Sr)r)akwfrrgszthreadsafe_generator..g functoolswraps)rrrrrthreadsafe_generatorsrzkeras.utils.Sequencec@s8eZdZdZeddZeddZddZdd Zd S) r.aBase object for fitting to a sequence of data, such as a dataset. Every `Sequence` must implement the `__getitem__` and the `__len__` methods. If you want to modify your dataset between epochs you may implement `on_epoch_end`. The method `__getitem__` should return a complete batch. Notes: `Sequence` are a safer way to do multiprocessing. This structure guarantees that the network will only train once on each sample per epoch which is not the case with generators. Examples: ```python from skimage.io import imread from skimage.transform import resize import numpy as np import math # Here, `x_set` is list of path to the images # and `y_set` are the associated classes. class CIFAR10Sequence(tf.keras.utils.Sequence): def __init__(self, x_set, y_set, batch_size): self.x, self.y = x_set, y_set self.batch_size = batch_size def __len__(self): return math.ceil(len(self.x) / self.batch_size) def __getitem__(self, idx): batch_x = self.x[idx * self.batch_size:(idx + 1) * self.batch_size] batch_y = self.y[idx * self.batch_size:(idx + 1) * self.batch_size] return np.array([ resize(imread(file_name), (200, 200)) for file_name in batch_x]), np.array(batch_y) ``` cCt)zGets batch at position `index`. Args: index: position of the batch in the Sequence. Returns: A batch NotImplementedError)rUindexrrr __getitem__ zSequence.__getitem__cCr)znNumber of batch in the Sequence. Returns: The number of batches in the Sequence. rrTrrr__len__szSequence.__len__cCsdS)z(Method called at the end of every epoch.NrrTrrr on_epoch_endszSequence.on_epoch_endc#s,fddttDD]}|VqdS)z2Create a generator that iterate over the Sequence.c3s|]}|VqdSrr).0irTrr sz$Sequence.__iter__..N)ranger)rUitemrrTrrszSequence.__iter__N) r\r]r^r_rrrrrrrrrr.s-   r.ccs |D]}|Vqq)zIterates indefinitely over a Sequence. Args: seq: `Sequence` instance. Yields: Batches of data from the `Sequence`. r)seqrrrriter_sequence_infinite s  rcr)NcsHttd}a|i|}|a|WdS1swYdS)NT)_FORCE_THREADPOOL_LOCK_FORCE_THREADPOOL)argskwargsZold_force_threadpooloutrrrwrapped*s  $z.dont_use_multiprocessing_pool..wrappedr)rrrrrdont_use_multiprocessing_pool)srcCs|rtrtjjStjSr)rmultiprocessingdummyZPool)use_multiprocessingrrrget_pool_class6srcCstdurtatS)z,Lazily create the queue to track worker ids.N)_WORKER_ID_QUEUErQueuerrrrget_worker_id_queue=srcCs|adSr_SHARED_SEQUENCES)seqsrrr init_poolEsrcCs t||S)acGet the value from the Sequence `uid` at index `i`. To allow multiple Sequences to be used at the same time, we use `uid` to get a specific one. A single Sequence would cause the validation to overwrite the training Sequence. Args: uid: int, Sequence identifier i: index Returns: The value at index `i`. r)uidrrrr get_indexJs rzkeras.utils.SequenceEnqueuerc@sjeZdZdZdddZddZdd d Zd d ZdddZddZ e ddZ e ddZ e ddZ d S)SequenceEnqueueraBase class to enqueue inputs. The task of an Enqueuer is to use parallelism to speed up preprocessing. This is done with processes or threads. Example: ```python enqueuer = SequenceEnqueuer(...) enqueuer.start() datas = enqueuer.get() for data in datas: # Use the inputs; training, evaluating, predicting. # ... stop sometime. enqueuer.stop() ``` The `enqueuer.get()` should be an infinite stream of data. FcCs||_||_tdurztddaWn tydaYnwtttr+t|_td7ant tj |_tj d7_ Wdn1sEwYd|_ d|_ d|_ d|_d|_dS)Nrrr )sequencer_SEQUENCE_COUNTERrValueOSErrorr*rrZget_lockvalueworkers executor_fnqueue run_thread stop_signal)rUrrrrrrVqs(     zSequenceEnqueuer.__init__cCs|jduo |j Sr)ris_setrTrrr is_runningszSequenceEnqueuer.is_runningr csd|jr ||_nfdd|_|_t||_t|_tj |j d|_ d|j _ |j dS)zStarts the handler's workers. Args: workers: Number of workers. max_queue_size: queue size (when full, workers could block on `put()`) cs tdSrQ)r)_rrrrs z(SequenceEnqueuer.start..)rXTN)r_get_executor_initrrrrrEventrThread_runrdaemonstart)rUrZmax_queue_sizerrrrs  zSequenceEnqueuer.startcCs|jt|j<dS)z&Sends current Iterable to all workers.N)rrrrTrrr_send_sequenceszSequenceEnqueuer._send_sequenceNcCsl|j|jj|jjd|j_|jjWdn1s$wY|j |dt |j <dS)zStops running threads and wait for them to exit, if necessary. Should be called by the same thread which called `start()`. Args: timeout: maximum time to wait on `thread.join()` rN) rr(rmutexclearunfinished_tasksnot_fullnotifyrrbrr)rUtimeoutrrrstops    zSequenceEnqueuer.stopcCs|r |dSdSr)rrrTrrr__del__s zSequenceEnqueuer.__del__cCr)?Submits request to the executor and queue the `Future` objects.rrTrrrrszSequenceEnqueuer._runcCr)Gets the Pool initializer for multiprocessing. Args: workers: Number of workers. Returns: Function, a Function to initialize the pool rrUrrrrrrz#SequenceEnqueuer._get_executor_initcCr)zCreates a generator to extract data from the queue. Skip the data if it is `None`. # Returns Generator yielding tuples `(inputs, targets)` or `(inputs, targets, sample_weights)`. rrTrrrrs zSequenceEnqueuer.get)F)r rr)r\r]r^r_rVrrrrrrrrrrrrrr[s      rzkeras.utils.OrderedEnqueuercsBeZdZdZd fdd ZddZddZd d Zd d ZZ S)OrderedEnqueuera Builds a Enqueuer from a Sequence. Args: sequence: A `tf.keras.utils.data_utils.Sequence` object. use_multiprocessing: use multiprocessing if True, otherwise threading shuffle: whether to shuffle the data at the beginning of each epoch Fct||||_dSr)superrVshuffle)rUrrr __class__rrrV zOrderedEnqueuer.__init__csfdd}|S)rcs(tdt|dtfd}t||SNT)Z initializerZinitargs)rinit_pool_generatorr _DATA_POOLSaddrpoolrrrpool_fns  z3OrderedEnqueuer._get_executor_init..pool_fnrrUrrrrrrs  z"OrderedEnqueuer._get_executor_initcCs( td|jjdks|jrdSq)zWait for the queue to be empty.T皙?rN)timesleeprrrrrTrrr _wait_queues  zOrderedEnqueuer._wait_queuecCsttt|j}| |jrt|t|t <}|D]}|j r0WddS|j j |t|j|fddq ||j rR WddSWdn1s\wY|j|qrTNblock)r%rrrrrrandomrrrrrrput apply_asyncrrrr)rUrexecutorrrrrrs.     zOrderedEnqueuer._runc cs|rCz|jjddd}|r|j|dur |VWntjy+Ynty<}z||d}~ww|sdSdS)Creates a generator to extract data from the queue. Skip the data if it is `None`. Yields: The next element in the queue, i.e. a tuple `(inputs, targets)` or `(inputs, targets, sample_weights)`. TrrN)rrr task_doneEmptyrpr)rUinputsrrrrr"s"  zOrderedEnqueuer.get)FF) r\r]r^r_rVrrrr __classcell__rrrrrsrcCsV|at}d|j|_|durtj||j|dur)|j|jddddSdS)aInitializer function for pool workers. Args: gens: State which should be made available to worker processes. random_seed: An optional value with which to seed child processes. id_queue: A multiprocessing Queue of worker ids. This is used to indicate that a worker process was created by Keras and can be terminated using the cleanup_all_keras_forkpools utility. Z Keras_worker_NTrr) rrcurrent_processnamer,rseedidentr)Zgens random_seedZid_queueZ worker_procrrrr:s rcCs tt|S)a[Gets the next value from the generator `uid`. To allow multiple generators to be used at the same time, we use `uid` to get a specific one. A single generator would cause the validation to overwrite the training generator. Args: uid: int, generator identifier Returns: The next value of generator `uid`. )rr)rrrr next_sampleUs rzkeras.utils.GeneratorEnqueuercs:eZdZdZd fdd ZddZdd Zd d ZZS) GeneratorEnqueueraBuilds a queue out of a data generator. The provided generator can be finite in which case the class will throw a `StopIteration` exception. Args: generator: a generator function which yields data use_multiprocessing: use multiprocessing if True, otherwise threading random_seed: Initial seed for workers, will be incremented by one for each worker. FNcrr)rrVr)rU generatorrrrrrrVsrzGeneratorEnqueuer.__init__csfdd}|S)zGets the Pool initializer for multiprocessing. Args: workers: Number of works. Returns: A Function to initialize the pool cs*tdt|jtfd}t||Sr)rrrrrrrrrrrs  z5GeneratorEnqueuer._get_executor_init..pool_fnrrrrrrws  z$GeneratorEnqueuer._get_executor_initcCsh|t|t} |jr WddS|jj|t |j fddq 1s-wYdSr) rrrrrrrrrrr)rUrrrrrs zGeneratorEnqueuer._runc csz#|r"|jjdd}|j|dur|V|sWdSWdStydg}|jdkrE||jjdd|jdks4|D]}|qGdd|D}|D] }|dur`|VqWYdSty}z| dt |vryt d|d}~ww) rTrNrcSsg|] }|r|qSr)Z successfulr)rfuturerrr s z)GeneratorEnqueuer.get..zgenerator already executingzyYour generator is NOT thread-safe. Keras requires a thread-safe generator when `use_multiprocessing=False, workers > 1`. ) rrrr StopIterationqsizeappendwaitrprr$r?)rUr Z last_onesrrrrrrs@     zGeneratorEnqueuer.get)FN) r\r]r^r_rVrrrr rrrrres   rzkeras.utils.pad_sequencesz*keras.preprocessing.sequence.pad_sequencesint32prec Cst|ds tdt|}g}d}d} |D]3} z|t| | r1t| r1t| jdd}d} WqtyH} z tdt| | d} ~ ww|durRt |}t |tj p_t |tj } t |trx|tkrx| sxtd |d t|d tj||f|||d } t|D]p\} }t|sq|d kr|| d}n|dkr|d|}ntd|dtj||d }|jdd|krtd|jddd| d||dkr|| | dt|f<q|d kr|| | t| df<qtd|d| S)a Pads sequences to the same length. This function transforms a list (of length `num_samples`) of sequences (lists of integers) into a 2D Numpy array of shape `(num_samples, num_timesteps)`. `num_timesteps` is either the `maxlen` argument if provided, or the length of the longest sequence in the list. Sequences that are shorter than `num_timesteps` are padded with `value` until they are `num_timesteps` long. Sequences longer than `num_timesteps` are truncated so that they fit the desired length. The position where padding or truncation happens is determined by the arguments `padding` and `truncating`, respectively. Pre-padding or removing values from the beginning of the sequence is the default. >>> sequence = [[1], [2, 3], [4, 5, 6]] >>> tf.keras.preprocessing.sequence.pad_sequences(sequence) array([[0, 0, 1], [0, 2, 3], [4, 5, 6]], dtype=int32) >>> tf.keras.preprocessing.sequence.pad_sequences(sequence, value=-1) array([[-1, -1, 1], [-1, 2, 3], [ 4, 5, 6]], dtype=int32) >>> tf.keras.preprocessing.sequence.pad_sequences(sequence, padding='post') array([[1, 0, 0], [2, 3, 0], [4, 5, 6]], dtype=int32) >>> tf.keras.preprocessing.sequence.pad_sequences(sequence, maxlen=2) array([[0, 1], [2, 3], [5, 6]], dtype=int32) Args: sequences: List of sequences (each sequence is a list of integers). maxlen: Optional Int, maximum length of all sequences. If not provided, sequences will be padded to the length of the longest individual sequence. dtype: (Optional, defaults to `"int32"`). Type of the output sequences. To pad sequences with variable length strings, you can use `object`. padding: String, "pre" or "post" (optional, defaults to `"pre"`): pad either before or after each sequence. truncating: String, "pre" or "post" (optional, defaults to `"pre"`): remove values from sequences larger than `maxlen`, either at the beginning or at the end of the sequences. value: Float or String, padding value. (Optional, defaults to 0.) Returns: Numpy array with shape `(len(sequences), maxlen)` Raises: ValueError: In case of invalid values for `truncating` or `padding`, or in case of invalid shape for a `sequences` entry. rz`sequences` must be iterable.rTr NFz=`sequences` must be a list of iterables. Found non-iterable: z`dtype` z( is not compatible with `value`'s type: z; You should set `dtype=object` for variable length strings.)dtyperpostzTruncating type "z" not understoodzShape of sample z of sequence at position z" is different from expected shape zPadding type ")hasattrrarrr,Zasarrayshape TypeErrorr$maxZ issubdtypeZstr_Zunicode_r*objecttypefull enumerate) sequencesmaxlenrpaddingZ truncatingrZ num_sampleslengthsZ sample_shapeflagr1rZ is_dtype_stridxstruncrrr pad_sequencesst H  r/)NN)r3r4) NNFNNrLr4Fr4Nr)rr)r4r)Nrrrr)Hr_rrZmultiprocessing.dummyrrArirrrFr8rrr/rmweakrefr:abcr contextlibrnumpyr,Ztensorflow.compat.v2compatv2r+Zsix.moves.urllib.parserZ keras.utilsrrZkeras.utils.generic_utilsrZ tensorflow.python.util.tf_exportrZsix.moves.urllib.requestr r#urllib.requestr2rKrrfrrrlrrr.rrrWeakSetrrr(Z _WORKER_IDSrRLockrrrrrrrrrrrr/rrrrs         * 1 3  #M  ^\