30秒让你有效的使用天池实验室资源
天池实验室云服务器存在的问题?
- 在安装其他的库时候,虽然说使用的是阿里自己的资源,其下载速度也是相当感人。
- 在使用
keras
时候,远程的数据资源本来下载一次都很费劲,在只有两个小时的free
资源下,下载数据的过程在这漫长的等待和你共舞,这该如何是好?
解决方案
替换镜像源
清华大学 https://pypi.tuna.tsinghua.edu.cn/simple/
阿里云 http://mirrors.aliyun.com/pypi/simple/
中国科技大学 https://pypi.mirrors.ustc.edu.cn/simple/
中国科学技术大学 http://pypi.mirrors.ustc.edu.cn/simple/
这些使用起来都很香。临时使用的话,就按照临时使用的方式:
!pip install opencv-python==3.4.3.18 -i https://pypi.mirrors.ustc.edu.cn/simple/
以上只是一个```demo``,至于选择哪个,根据实际情况,哪个香用哪个。
提前后台下载数据资源,在下载资源的这段时间,可以搞其他工作
出于好奇的原因,我们先找一下keras/dataset
在阿里云实验室服务器的位置:
!ls /opt/conda/pkgs/keras-2.1.6-py36_0/lib/python3.6/site-packages/keras/datasets/
我们再来看下我们关系的cifar-10
是如何load_data
的:
"""CIFAR10 small images classification dataset.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from .cifar import load_batch
from ..utils.data_utils import get_file
from .. import backend as K
import numpy as np
import os
def load_data():
"""Loads CIFAR10 dataset.
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
dirname = 'cifar-10-batches-py'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
path = get_file(dirname, origin=origin, untar=True)
num_train_samples = 50000
x_train = np.empty((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.empty((num_train_samples,), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path, 'data_batch_' + str(i))
(x_train[(i - 1) * 10000: i * 10000, :, :, :],
y_train[(i - 1) * 10000: i * 10000]) = load_batch(fpath)
fpath = os.path.join(path, 'test_batch')
x_test, y_test = load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
return (x_train, y_train), (x_test, y_test)
我们再来看,get_file
根据头引入的from ..utils.data_utils import get_file
"""Utilities for file download and caching."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import hashlib
import multiprocessing
import os
import random
import shutil
import sys
import tarfile
import threading
import time
import traceback
import zipfile
from abc import abstractmethod
from contextlib import closing
from multiprocessing.pool import ThreadPool
import numpy as np
import six
from six.moves.urllib.error import HTTPError
from six.moves.urllib.error import URLError
from six.moves.urllib.request import urlopen
try:
import queue
except ImportError:
import Queue as queue
from ..utils.generic_utils import Progbar
if sys.version_info[0] == 2:
def urlretrieve(url, filename, reporthook=None, data=None):
"""Replacement for `urlretrive` for Python 2.
Under Python 2, `urlretrieve` relies on `FancyURLopener` from legacy
`urllib` module, known to have issues with proxy management.
# Arguments
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`.
"""
def chunk_read(response, chunk_size=8192, reporthook=None):
content_type = response.info().get('Content-Length')
total_size = -1
if content_type is not None:
total_size = int(content_type.strip())
count = 0
while True:
chunk = response.read(chunk_size)
count += 1
if reporthook is not None:
reporthook(count, chunk_size, total_size)
if chunk:
yield chunk
else:
break
with closing(urlopen(url, data)) as response, open(filename, 'wb') as fd:
for chunk in chunk_read(response, reporthook=reporthook):
fd.write(chunk)
else:
from six.moves.urllib.request import urlretrieve
def _extract_archive(file_path, path='.', archive_format='auto'):
"""Extracts an archive if it matches tar, tar.gz, tar.bz, or zip formats.
# Arguments
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.
"""
if archive_format is None:
return False
if archive_format is 'auto':
archive_format = ['tar', 'zip']
if isinstance(archive_format, six.string_types):
archive_format = [archive_format]
for archive_type in archive_format:
if archive_type is 'tar':
open_fn = tarfile.open
is_match_fn = tarfile.is_tarfile
if archive_type is 'zip':
open_fn = zipfile.ZipFile
is_match_fn = zipfile.is_zipfile
if is_match_fn(file_path):
with open_fn(file_path) as archive:
try:
archive.extractall(path)
except (tarfile.TarError, RuntimeError,
KeyboardInterrupt):
if os.path.exists(path):
if os.path.isfile(path):
os.remove(path)
else:
shutil.rmtree(path)
raise
return True
return False
def get_file(fname,
origin,
untar=False,
md5_hash=None,
file_hash=None,
cache_subdir='datasets',
hash_algorithm='auto',
extract=False,
archive_format='auto',
cache_dir=None):
"""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.
# Arguments
fname: Name of the file. If an absolute path `/path/to/file.txt` is
specified the file will be saved at that location.
origin: Original URL of the file.
untar: Deprecated in favor of 'extract'.
boolean, whether the file should be decompressed
md5_hash: Deprecated in favor of 'file_hash'.
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' is ['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 [Keras Directory](/faq/#where-is-the-keras-configuration-filed-stored).
# Returns
Path to the downloaded file
"""
if cache_dir is None:
cache_dir = os.path.join(os.path.expanduser('~'), '.keras')
if md5_hash is not None and file_hash is None:
file_hash = md5_hash
hash_algorithm = 'md5'
datadir_base = os.path.expanduser(cache_dir)
if not os.access(datadir_base, os.W_OK):
datadir_base = os.path.join('/tmp', '.keras')
datadir = os.path.join(datadir_base, cache_subdir)
if not os.path.exists(datadir):
os.makedirs(datadir)
if untar:
untar_fpath = os.path.join(datadir, fname)
fpath = untar_fpath + '.tar.gz'
else:
fpath = os.path.join(datadir, fname)
download = False
if os.path.exists(fpath):
# File found; verify integrity if a hash was provided.
if file_hash is not None:
if not validate_file(fpath, file_hash, algorithm=hash_algorithm):
print('A local file was found, but it seems to be '
'incomplete or outdated because the ' + hash_algorithm +
' file hash does not match the original value of ' +
file_hash + ' so we will re-download the data.')
download = True
else:
download = True
if download:
print('Downloading data from', origin)
class ProgressTracker(object):
# Maintain progbar for the lifetime of download.
# This design was chosen for Python 2.7 compatibility.
progbar = None
def dl_progress(count, block_size, total_size):
if ProgressTracker.progbar is None:
if total_size is -1:
total_size = None
ProgressTracker.progbar = Progbar(total_size)
else:
ProgressTracker.progbar.update(count * block_size)
error_msg = 'URL fetch failure on {}: {} -- {}'
try:
try:
urlretrieve(origin, fpath, dl_progress)
except URLError as e:
raise Exception(error_msg.format(origin, e.errno, e.reason))
except HTTPError as e:
raise Exception(error_msg.format(origin, e.code, e.msg))
except (Exception, KeyboardInterrupt) as e:
if os.path.exists(fpath):
os.remove(fpath)
raise
ProgressTracker.progbar = None
if untar:
if not os.path.exists(untar_fpath):
_extract_archive(fpath, datadir, archive_format='tar')
return untar_fpath
if extract:
_extract_archive(fpath, datadir, archive_format)
return fpath
def _hash_file(fpath, algorithm='sha256', chunk_size=65535):
"""Calculates a file sha256 or md5 hash.
# Example
```python
>>> from keras.data_utils import _hash_file
>>> _hash_file('/path/to/file.zip')
'e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855'
```
# Arguments
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
"""
if (algorithm is 'sha256') or (algorithm is 'auto' and len(hash) is 64):
hasher = hashlib.sha256()
else:
hasher = hashlib.md5()
with open(fpath, 'rb') as fpath_file:
for chunk in iter(lambda: fpath_file.read(chunk_size), b''):
hasher.update(chunk)
return hasher.hexdigest()
def validate_file(fpath, file_hash, algorithm='auto', chunk_size=65535):
"""Validates a file against a sha256 or md5 hash.
# Arguments
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
"""
if ((algorithm is 'sha256') or
(algorithm is 'auto' and len(file_hash) is 64)):
hasher = 'sha256'
else:
hasher = 'md5'
if str(_hash_file(fpath, hasher, chunk_size)) == str(file_hash):
return True
else:
return False
class Sequence(object):
"""Base object for fitting to a sequence of data, such as a dataset.
Every `Sequence` must implements 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
# Here, `x_set` is list of path to the images
# and `y_set` are the associated classes.
class CIFAR10Sequence(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 int(np.ceil(len(self.x) / float(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)
```
"""
@abstractmethod
def __getitem__(self, index):
"""Gets batch at position `index`.
# Arguments
index: position of the batch in the Sequence.
# Returns
A batch
"""
raise NotImplementedError
@abstractmethod
def __len__(self):
"""Number of batch in the Sequence.
# Returns
The number of batches in the Sequence.
"""
raise NotImplementedError
def on_epoch_end(self):
"""Method called at the end of every epoch.
"""
pass
def __iter__(self):
"""Create an infinite generator that iterate over the Sequence."""
while True:
for item in (self[i] for i in range(len(self))):
yield item
# Global variables to be shared across processes
_SHARED_SEQUENCES = {}
# We use a Value to provide unique id to different processes.
_SEQUENCE_COUNTER = None
def init_pool(seqs):
global _SHARED_SEQUENCES
_SHARED_SEQUENCES = seqs
def get_index(uid, i):
"""Get 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.
# Arguments
uid: int, Sequence identifier
i: index
# Returns
The value at index `i`.
"""
return _SHARED_SEQUENCES[uid][i]
class SequenceEnqueuer(object):
"""Base class to enqueue inputs.
The task of an Enqueuer is to use parallelism to speed up preprocessing.
This is done with processes or threads.
# Examples
```python
enqueuer = SequenceEnqueuer(...)
enqueuer.start()
datas = enqueuer.get()
for data in datas:
# Use the inputs; training, evaluating, predicting.
# ... stop sometime.
enqueuer.close()
```
The `enqueuer.get()` should be an infinite stream of datas.
"""
@abstractmethod
def is_running(self):
raise NotImplementedError
@abstractmethod
def start(self, workers=1, max_queue_size=10):
"""Starts the handler's workers.
# Arguments
workers: number of worker threads
max_queue_size: queue size
(when full, threads could block on `put()`).
"""
raise NotImplementedError
@abstractmethod
def stop(self, timeout=None):
"""Stop running threads and wait for them to exit, if necessary.
Should be called by the same thread which called start().
# Arguments
timeout: maximum time to wait on thread.join()
"""
raise NotImplementedError
@abstractmethod
def get(self):
"""Creates 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)`.
"""
raise NotImplementedError
class OrderedEnqueuer(SequenceEnqueuer):
"""Builds a Enqueuer from a Sequence.
Used in `fit_generator`, `evaluate_generator`, `predict_generator`.
# Arguments
sequence: A `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
"""
def __init__(self, sequence,
use_multiprocessing=False,
shuffle=False):
self.sequence = sequence
self.use_multiprocessing = use_multiprocessing
global _SEQUENCE_COUNTER
if _SEQUENCE_COUNTER is None:
try:
_SEQUENCE_COUNTER = multiprocessing.Value('i', 0)
except OSError:
# In this case the OS does not allow us to use
# multiprocessing. We resort to an int
# for enqueuer indexing.
_SEQUENCE_COUNTER = 0
if isinstance(_SEQUENCE_COUNTER, int):
self.uid = _SEQUENCE_COUNTER
_SEQUENCE_COUNTER += 1
else:
# Doing Multiprocessing.Value += x is not process-safe.
with _SEQUENCE_COUNTER.get_lock():
self.uid = _SEQUENCE_COUNTER.value
_SEQUENCE_COUNTER.value += 1
self.shuffle = shuffle
self.workers = 0
self.executor_fn = None
self.queue = None
self.run_thread = None
self.stop_signal = None
def is_running(self):
return self.stop_signal is not None and not self.stop_signal.is_set()
def start(self, workers=1, max_queue_size=10):
"""Start the handler's workers.
# Arguments
workers: number of worker threads
max_queue_size: queue size
(when full, workers could block on `put()`)
"""
if self.use_multiprocessing:
self.executor_fn = lambda seqs: multiprocessing.Pool(workers,
initializer=init_pool,
initargs=(seqs,))
else:
# We do not need the init since it's threads.
self.executor_fn = lambda _: ThreadPool(workers)
self.workers = workers
self.queue = queue.Queue(max_queue_size)
self.stop_signal = threading.Event()
self.run_thread = threading.Thread(target=self._run)
self.run_thread.daemon = True
self.run_thread.start()
def _wait_queue(self):
"""Wait for the queue to be empty."""
while True:
time.sleep(0.1)
if self.queue.unfinished_tasks == 0 or self.stop_signal.is_set():
return
def _run(self):
"""Submits request to the executor and queue the `Future` objects."""
sequence = list(range(len(self.sequence)))
self._send_sequence() # Share the initial sequence
while True:
if self.shuffle:
random.shuffle(sequence)
with closing(self.executor_fn(_SHARED_SEQUENCES)) as executor:
for i in sequence:
if self.stop_signal.is_set():
return
self.queue.put(
executor.apply_async(get_index, (self.uid, i)), block=True)
# Done with the current epoch, waiting for the final batches
self._wait_queue()
if self.stop_signal.is_set():
# We're done
return
# Call the internal on epoch end.
self.sequence.on_epoch_end()
self._send_sequence() # Update the pool
def get(self):
"""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)`.
"""
try:
while self.is_running():
inputs = self.queue.get(block=True).get()
self.queue.task_done()
if inputs is not None:
yield inputs
except Exception as e:
self.stop()
six.raise_from(StopIteration(e), e)
def _send_sequence(self):
"""Send current Sequence to all workers."""
# For new processes that may spawn
_SHARED_SEQUENCES[self.uid] = self.sequence
def stop(self, timeout=None):
"""Stops running threads and wait for them to exit, if necessary.
Should be called by the same thread which called `start()`.
# Arguments
timeout: maximum time to wait on `thread.join()`
"""
self.stop_signal.set()
with self.queue.mutex:
self.queue.queue.clear()
self.queue.unfinished_tasks = 0
self.queue.not_full.notify()
self.run_thread.join(timeout)
_SHARED_SEQUENCES[self.uid] = None
class GeneratorEnqueuer(SequenceEnqueuer):
"""Builds a queue out of a data generator.
The provided generator can be finite in which case the class will throw
a `StopIteration` exception.
Used in `fit_generator`, `evaluate_generator`, `predict_generator`.
# Arguments
generator: a generator function which yields data
use_multiprocessing: use multiprocessing if True, otherwise threading
wait_time: time to sleep in-between calls to `put()`
random_seed: Initial seed for workers,
will be incremented by one for each worker.
"""
def __init__(self, generator,
use_multiprocessing=False,
wait_time=0.05,
seed=None):
self.wait_time = wait_time
self._generator = generator
if os.name is 'nt' and use_multiprocessing is True:
# On Windows, avoid **SYSTEMATIC** error in `multiprocessing`:
# `TypeError: can't pickle generator objects`
# => Suggest multithreading instead of multiprocessing on Windows
raise ValueError('Using a generator with `use_multiprocessing=True`'
' is not supported on Windows (no marshalling of'
' generators across process boundaries). Instead,'
' use single thread/process or multithreading.')
else:
self._use_multiprocessing = use_multiprocessing
self._threads = []
self._stop_event = None
self._manager = None
self.queue = None
self.seed = seed
def _data_generator_task(self):
if self._use_multiprocessing is False:
while not self._stop_event.is_set():
with self.genlock:
try:
if (self.queue is not None and
self.queue.qsize() < self.max_queue_size):
# On all OSes, avoid **SYSTEMATIC** error
# in multithreading mode:
# `ValueError: generator already executing`
# => Serialize calls to
# infinite iterator/generator's next() function
generator_output = next(self._generator)
self.queue.put((True, generator_output))
else:
time.sleep(self.wait_time)
except StopIteration:
break
except Exception as e:
# Can't pickle tracebacks.
# As a compromise, print the traceback and pickle None instead.
if not hasattr(e, '__traceback__'):
setattr(e, '__traceback__', sys.exc_info()[2])
self.queue.put((False, e))
self._stop_event.set()
break
else:
while not self._stop_event.is_set():
try:
if (self.queue is not None and
self.queue.qsize() < self.max_queue_size):
generator_output = next(self._generator)
self.queue.put((True, generator_output))
else:
time.sleep(self.wait_time)
except StopIteration:
break
except Exception as e:
# Can't pickle tracebacks.
# As a compromise, print the traceback and pickle None instead.
traceback.print_exc()
setattr(e, '__traceback__', None)
self.queue.put((False, e))
self._stop_event.set()
break
def start(self, workers=1, max_queue_size=10):
"""Kicks off threads which add data from the generator into the queue.
# Arguments
workers: number of worker threads
max_queue_size: queue size
(when full, threads could block on `put()`)
"""
try:
self.max_queue_size = max_queue_size
if self._use_multiprocessing:
self._manager = multiprocessing.Manager()
self.queue = self._manager.Queue(maxsize=max_queue_size)
self._stop_event = multiprocessing.Event()
else:
# On all OSes, avoid **SYSTEMATIC** error in multithreading mode:
# `ValueError: generator already executing`
# => Serialize calls to infinite iterator/generator's next() function
self.genlock = threading.Lock()
self.queue = queue.Queue(maxsize=max_queue_size)
self._stop_event = threading.Event()
for _ in range(workers):
if self._use_multiprocessing:
# Reset random seed else all children processes
# share the same seed
np.random.seed(self.seed)
thread = multiprocessing.Process(target=self._data_generator_task)
thread.daemon = True
if self.seed is not None:
self.seed += 1
else:
thread = threading.Thread(target=self._data_generator_task)
self._threads.append(thread)
thread.start()
except:
self.stop()
raise
def is_running(self):
return self._stop_event is not None and not self._stop_event.is_set()
def stop(self, timeout=None):
"""Stops running threads and wait for them to exit, if necessary.
Should be called by the same thread which called `start()`.
# Arguments
timeout: maximum time to wait on `thread.join()`.
"""
if self.is_running():
self._stop_event.set()
for thread in self._threads:
if self._use_multiprocessing:
if thread.is_alive():
thread.terminate()
else:
# The thread.is_alive() test is subject to a race condition:
# the thread could terminate right after the test and before the
# join, rendering this test meaningless -> Call thread.join()
# always, which is ok no matter what the status of the thread.
thread.join(timeout)
if self._manager:
self._manager.shutdown()
self._threads = []
self._stop_event = None
self.queue = None
def get(self):
"""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)`.
"""
while self.is_running():
if not self.queue.empty():
success, value = self.queue.get()
# Rethrow any exceptions found in the queue
if not success:
six.reraise(value.__class__, value, value.__traceback__)
# Yield regular values
if value is not None:
yield value
else:
all_finished = all([not thread.is_alive() for thread in self._threads])
if all_finished and self.queue.empty():
raise StopIteration()
else:
time.sleep(self.wait_time)
# Make sure to rethrow the first exception in the queue, if any
while not self.queue.empty():
success, value = self.queue.get()
if not success:
six.reraise(value.__class__, value, value.__traceback__)
然后看代码逻辑和注释就一目了然了。
如何查看后台下载情况
# 查看日志
!cat wget-log.2
# 断点续传
!wget -c https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz
完事,收工!
云服务器在哪?
https://tianchi.aliyun.com/notebook-ai/