版塊導(dǎo)航: 正在加載中...

應(yīng)《網(wǎng)絡(luò)安全法》要求，自2017年10月1日起，未進(jìn)行實(shí)名認(rèn)證將不得使用互聯(lián)網(wǎng)跟帖服務(wù)。為保障您的帳號(hào)能夠正常使用，請(qǐng)盡快對(duì)帳號(hào)進(jìn)行手機(jī)號(hào)驗(yàn)證，感謝您的理解與支持！

24小時(shí)熱門版塊排行榜

返回列表

HZSte1204

新蟲 (初入文壇)

應(yīng)助: 0 (幼兒園)
金幣: 44.6
帖子: 26
在線: 2.2小時(shí)
蟲號(hào): 20042637
注冊(cè): 2019-12-06
專業(yè): 自動(dòng)化

[求助] 求助AttributeError: module ' ' has no attribute ''

求助各位，運(yùn)行代碼時(shí)出現(xiàn)AttributeError: module 'cs_gan.utils' has no attribute 'get_train_dataset'，代碼中有from cs_gan import utils，查看utils.py中也有Function:get_train_dataset ，出現(xiàn)此問題該如何解決呢？

發(fā)自小木蟲Android客戶端

回復(fù)此樓

» 猜你喜歡

0817找調(diào)劑已經(jīng)有3人回復(fù)
調(diào)劑的同學(xué)，走過路過，不要錯(cuò)過已經(jīng)有14人回復(fù)
288求調(diào)劑085600材料與化工已經(jīng)有14人回復(fù)
【求調(diào)劑】293分環(huán)境工程求調(diào)劑材料/化工，服從調(diào)劑，抗壓能力強(qiáng)！已經(jīng)有11人回復(fù)
0701-322 求調(diào)劑已經(jīng)有5人回復(fù)
材料與化工求調(diào)劑已經(jīng)有3人回復(fù)
298求調(diào)劑已經(jīng)有7人回復(fù)
288求調(diào)劑已經(jīng)有4人回復(fù)
0856材料與化工290求調(diào)劑已經(jīng)有4人回復(fù)
286求調(diào)劑已經(jīng)有13人回復(fù)

1樓 2020-04-15 18:50:36

已閱回復(fù)此樓關(guān)注TA 給TA發(fā)消息送TA紅花 TA的回帖

HZSte1204

新蟲 (初入文壇)

應(yīng)助: 0 (幼兒園)
金幣: 44.6
帖子: 26
在線: 2.2小時(shí)
蟲號(hào): 20042637
注冊(cè): 2019-12-06
專業(yè): 自動(dòng)化

大佬你好，請(qǐng)問運(yùn)行代碼時(shí)出現(xiàn)AttributeError: module 'cs_gan.utils' has no attribute 'get_train_dataset'，代碼中有from cs_gan import utils，查看utils.py中也有Function:get_train_dataset ，出現(xiàn)此問題該如何解決呢？謝謝

發(fā)自小木蟲Android客戶端

贊一下

回復(fù)此樓

2樓2020-04-15 18:52:52

已閱回復(fù)此樓關(guān)注TA 給TA發(fā)消息送TA紅花 TA的回帖

天天進(jìn)步啊

木蟲 (著名寫手)

應(yīng)助: 87 (初中生)
金幣: 6058.7
散金: 101
紅花: 42
沙發(fā): 9
帖子: 1793
在線: 1005.5小時(shí)
蟲號(hào): 3689648
注冊(cè): 2015-02-15
性別: GG
專業(yè): 理論和計(jì)算化學(xué)

引用回帖:

2樓: Originally posted by HZSte1204 at 2020-04-15 18:52:52
大佬你好，請(qǐng)問運(yùn)行代碼時(shí)出現(xiàn)AttributeError: module 'cs_gan.utils' has no attribute 'get_train_dataset'，代碼中有from cs_gan import utils，查看utils.py中也有Function:get_train_dataset ，出現(xiàn)此問題該如 ...

一看就知道是python代碼，先把你代碼貼出來，再講你的報(bào)錯(cuò)

贊一下(1人)

回復(fù)此樓

» 本帖已獲得的紅花（最新10朵）

HZSte1204

分子篩、分子動(dòng)力學(xué)模擬，有問題可咨詢我的知乎主頁 https://www.zhihu.com/people/rao777

3樓2020-04-15 20:41:22

已閱回復(fù)此樓關(guān)注TA 給TA發(fā)消息送TA紅花 TA的回帖

HZSte1204

新蟲 (初入文壇)

應(yīng)助: 0 (幼兒園)
金幣: 44.6
帖子: 26
在線: 2.2小時(shí)
蟲號(hào): 20042637
注冊(cè): 2019-12-06
專業(yè): 自動(dòng)化

送紅花一朵

引用回帖:

3樓: Originally posted by 天天進(jìn)步啊 at 2020-04-15 20:41:22
一看就知道是python代碼，先把你代碼貼出來，再講你的報(bào)錯(cuò)...

您好，這個(gè)代碼是Yan Wu, Mihaela Rosca, Timothy Lillicrap Deep Compressed Sensing. ICML 2019的開源代碼（This is the example code for the following ICML 2019 paper. If you use the code here please cite this paper），網(wǎng)址https://github.com/deepmind/deepmind-research/tree/master/cs_gan
下面是報(bào)錯(cuò)，運(yùn)行后報(bào)錯(cuò)的main_cs.py文件以及utils.py文件代碼
  File "D:\deep compressed sensing\main_cs.py", line 76, in main
images = utils.get_train_dataset(data_processor, FLAGS.dataset,

AttributeError: module 'cs_gan.utils' has no attribute 'get_train_dataset'

#main_cs.py
"""Training script."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os

from absl import app
from absl import flags
from absl import logging

import tensorflow.compat.v1 as tf
import tensorflow_probability as tfp

from cs_gan import cs
from cs_gan import file_utils
from cs_gan import utils

tfd = tfp.distributions

flags.DEFINE_string(
'mode', 'recons', 'Model mode.')
flags.DEFINE_integer(
'num_training_iterations', 10000000,
'Number of training iterations.')
flags.DEFINE_integer(
'batch_size', 64, 'Training batch size.')
flags.DEFINE_integer(
'num_measurements', 25, 'The number of measurements')
flags.DEFINE_integer(
'num_latents', 100, 'The number of latents')
flags.DEFINE_integer(
'num_z_iters', 3, 'The number of latent optimisation steps.')
flags.DEFINE_float(
'z_step_size', 0.01, 'Step size for latent optimisation.')
flags.DEFINE_string(
'z_project_method', 'norm', 'The method to project z.')
flags.DEFINE_integer(
'summary_every_step', 1000,
'The interval at which to log debug ops.')
flags.DEFINE_integer(
'export_every', 10,
'The interval at which to export samples.')
flags.DEFINE_string(
'dataset', 'mnist', 'The dataset used for learning (cifar|mnist.')
flags.DEFINE_float('learning_rate', 1e-4, 'Learning rate.')
flags.DEFINE_string(
'output_dir', '/tmp/cs_gan/cs', 'Location where to save output files.')

FLAGS = flags.FLAGS

# Log info level (for Hooks).
tf.logging.set_verbosity(tf.logging.INFO)

def main(argv):
  del argv

  utils.make_output_dir(FLAGS.output_dir)
  data_processor = utils.DataProcessor()
  images = utils.get_train_dataset(data_processor, FLAGS.dataset,
                                 FLAGS.batch_size)

  logging.info('Learning rate: %d', FLAGS.learning_rate)

  # Construct optimizers.
  optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate)

  # Create the networks and models.
  generator = utils.get_generator(FLAGS.dataset)
  metric_net = utils.get_metric_net(FLAGS.dataset, FLAGS.num_measurements)
  model = cs.CS(metric_net, generator,
            FLAGS.num_z_iters, FLAGS.z_step_size, FLAGS.z_project_method)
  prior = utils.make_prior(FLAGS.num_latents)
  generator_inputs = prior.sample(FLAGS.batch_size)

  model_output = model.connect(images, generator_inputs)
  optimization_components = model_output.optimization_components
  debug_ops = model_output.debug_ops
  reconstructions, _ = utils.optimise_and_sample(
   generator_inputs, model, images, is_training=False)

  global_step = tf.train.get_or_create_global_step()
  update_op = optimizer.minimize(
   optimization_components.loss,
   var_list=optimization_components.vars,
   global_step=global_step)

  sample_exporter = file_utils.FileExporter(
   os.path.join(FLAGS.output_dir, 'reconstructions'))

  # Hooks.
  debug_ops['it'] = global_step
  # Abort training on Nans.
  nan_hook = tf.train.NanTensorHook(optimization_components.loss)
  # Step counter.
  step_conter_hook = tf.train.StepCounterHook()

  checkpoint_saver_hook = tf.train.CheckpointSaverHook(
   checkpoint_dir=utils.get_ckpt_dir(FLAGS.output_dir), save_secs=10 * 60)

  loss_summary_saver_hook = tf.train.SummarySaverHook(
   save_steps=FLAGS.summary_every_step,
   output_dir=os.path.join(FLAGS.output_dir, 'summaries'),
   summary_op=utils.get_summaries(debug_ops))

  hooks = [checkpoint_saver_hook, nan_hook, step_conter_hook,
         loss_summary_saver_hook]

  # Start training.
  with tf.train.MonitoredSession(hooks=hooks) as sess:
logging.info('starting training')

for i in range(FLAGS.num_training_iterations):
   sess.run(update_op)

   if i % FLAGS.export_every == 0:
      reconstructions_np, data_np = sess.run([reconstructions, images])
      # Create an object which gets data and does the processing.
      data_np = data_processor.postprocess(data_np)
      reconstructions_np = data_processor.postprocess(reconstructions_np)
      sample_exporter.save(reconstructions_np, 'reconstructions')
      sample_exporter.save(data_np, 'data')

if __name__ == '__main__':
  app.run(main)

#utils.py
"""Tools for latent optimisation."""
import collections
import os

from absl import logging
import numpy as np
import tensorflow.compat.v1 as tf
import tensorflow_probability as tfp

from cs_gan import nets

tfd = tfp.distributions

class ModelOutputs(
collections.namedtuple('AdversarialModelOutputs',
                        ['optimization_components', 'debug_ops'])):
  """All the information produced by the adversarial module.
  Fields:
* `optimization_components`: A dictionary. Each entry in this dictionary
   corresponds to a module to train using their own optimizer. The keys are
   names of the components, and the values are `common.OptimizationComponent`
   instances. The keys of this dict can be made keys of the configuration
   used by the main train loop, to define the configuration of the
   optimization details for each module.
* `debug_ops`: A dictionary, from string to a scalar `tf.Tensor`. Quantities
   used for tracking training.
  """

class OptimizationComponent(
collections.namedtuple('OptimizationComponent', ['loss', 'vars'])):
  """Information needed by the optimizer to train modules.
  Usage:
   `optimizer.minimize(
      opt_compoment.loss, var_list=opt_component.vars)`
  Fields:
* `loss`: A `tf.Tensor` the loss of the module.
* `vars`: A list of variables, the ones which will be used to minimize the
   loss.
  """

def cross_entropy_loss(logits, expected):
  """The cross entropy classification loss between logits and expected values.
  The loss proposed by the original GAN paper: https://arxiv.org/abs/1406.2661.
  Args:
logits: a `tf.Tensor`, the model produced logits.
expected: a `tf.Tensor`, the expected output.
  Returns:
A scalar `tf.Tensor`, the average loss obtained on the given inputs.
  Raises:
ValueError: if the logits do not have shape [batch_size, 2].
  """

  num_logits = logits.get_shape()[1]
  if num_logits != 2:
raise ValueError(('Invalid number of logits for cross_entropy_loss! '
                  'cross_entropy_loss supports only 2 output logits!'))
  return tf.reduce_mean(
   tf.nn.sparse_softmax_cross_entropy_with_logits(
      logits=logits, labels=expected))

def optimise_and_sample(init_z, module, data, is_training):
  """Optimising generator latent variables and sample."""

  if module.num_z_iters == 0:
z_final = init_z
  else:
init_loop_vars = (0, _project_z(init_z, module.z_project_method))
loop_cond = lambda i, _: i < module.num_z_iters
def loop_body(i, z):
   loop_samples = module.generator(z, is_training)
   gen_loss = module.gen_loss_fn(data, loop_samples)
   z_grad = tf.gradients(gen_loss, z)[0]
   z -= module.z_step_size * z_grad
   z = _project_z(z, module.z_project_method)
   return i + 1, z

# Use the following static loop for debugging
# z = init_z
# for _ in xrange(num_z_iters):
# _, z = loop_body(0, z)
# z_final = z

_, z_final = tf.while_loop(loop_cond,
                           loop_body,
                           init_loop_vars)

  return module.generator(z_final, is_training), z_final

def get_optimisation_cost(initial_z, optimised_z):
  optimisation_cost = tf.reduce_mean(
   tf.reduce_sum((optimised_z - initial_z)**2, -1))
  return optimisation_cost

def _project_z(z, project_method='clip'):
  """To be used for projected gradient descent over z."""
  if project_method == 'norm':
z_p = tf.nn.l2_normalize(z, axis=-1)
  elif project_method == 'clip':
z_p = tf.clip_by_value(z, -1, 1)
  else:
raise ValueError('Unknown project_method: {}'.format(project_method))
  return z_p

class DataProcessor(object):

  def preprocess(self, x):
return x * 2 - 1

  def postprocess(self, x):
return (x + 1) / 2.

def _get_np_data(data_processor, dataset, split='train'):
  """Get the dataset as numpy arrays."""
  index = 0 if split == 'train' else 1
  if dataset == 'mnist':
# Construct the dataset.
x, _ = tf.keras.datasets.mnist.load_data()[index]
# Note: tf dataset is binary so we convert it to float.
x = x.astype(np.float32)
x = x / 255.
x = x.reshape((-1, 28, 28, 1))

  if dataset == 'cifar':
x, _ = tf.keras.datasets.cifar10.load_data()[index]
x = x.astype(np.float32)
x = x / 255.

  if data_processor:
# Normalize data if a processor is given.
x = data_processor.preprocess(x)
  return x

def make_output_dir(output_dir):
  logging.info('Creating output dir %s', output_dir)
  if not tf.gfile.IsDirectory(output_dir):
tf.gfile.MakeDirs(output_dir)

def get_ckpt_dir(output_dir):
  ckpt_dir = os.path.join(output_dir, 'ckpt')
  if not tf.gfile.IsDirectory(ckpt_dir):
tf.gfile.MakeDirs(ckpt_dir)
  return ckpt_dir

def get_real_data_for_eval(num_eval_samples, dataset, split='valid'):
  data = _get_np_data(data_processor=None, dataset=dataset, split=split)
  data = data[:num_eval_samples]
  return tf.constant(data)

def get_summaries(ops):
  summaries = []
  for name, op in ops.items():
# Ensure to log the value ops before writing them in the summary.
# We do this instead of a hook to ensure IS/FID are never computed twice.
print_op = tf.print(name, [op], output_stream=tf.logging.info)
with tf.control_dependencies([print_op]):
   summary = tf.summary.scalar(name, op)
   summaries.append(summary)
  return summaries

def get_train_dataset(data_processor, dataset, batch_size):
  """Creates the training data tensors."""
  x_train = _get_np_data(data_processor, dataset, split='train')
  # Create the TF dataset.
  dataset = tf.data.Dataset.from_tensor_slices(x_train)

  # Shuffle and repeat the dataset for training.
  # This is required because we want to do multiple passes through the entire
  # dataset when training.
  dataset = dataset.shuffle(100000).repeat()

  # Batch the data and return the data batch.
  one_shot_iterator = dataset.batch(batch_size).make_one_shot_iterator()
  data_batch = one_shot_iterator.get_next()
  return data_batch

def get_generator(dataset):
  if dataset == 'mnist':
return nets.MLPGeneratorNet()
  if dataset == 'cifar':
return nets.SNGenNet()

def get_metric_net(dataset, num_outputs=2):
  if dataset == 'mnist':
return nets.MLPMetricNet(num_outputs)
  if dataset == 'cifar':
return nets.SNMetricNet(num_outputs)

def make_prior(num_latents):
  # Zero mean, unit variance prior.
  prior_mean = tf.zeros(shape=(num_latents), dtype=tf.float32)
  prior_scale = tf.ones(shape=(num_latents), dtype=tf.float32)

  return tfd.Normal(loc=prior_mean, scale=prior_scale)

贊一下

回復(fù)此樓

4樓2020-04-18 12:23:05

已閱回復(fù)此樓關(guān)注TA 給TA發(fā)消息送TA紅花 TA的回帖

天天進(jìn)步啊

木蟲 (著名寫手)

應(yīng)助: 87 (初中生)
金幣: 6058.7
散金: 101
紅花: 42
沙發(fā): 9
帖子: 1793
在線: 1005.5小時(shí)
蟲號(hào): 3689648
注冊(cè): 2015-02-15
性別: GG
專業(yè): 理論和計(jì)算化學(xué)

引用回帖:

4樓: Originally posted by HZSte1204 at 2020-04-18 12:23:05
您好，這個(gè)代碼是Yan Wu, Mihaela Rosca, Timothy Lillicrap Deep Compressed Sensing. ICML 2019的開源代碼（This is the example code for the following ICML 2019 paper. If you use the code here please cit ...

dir(utils)試試

回復(fù)此樓

分子篩、分子動(dòng)力學(xué)模擬，有問題可咨詢我的知乎主頁 https://www.zhihu.com/people/rao777

5樓2020-04-18 17:14:42

已閱回復(fù)此樓關(guān)注TA 給TA發(fā)消息送TA紅花 TA的回帖

HZSte1204

新蟲 (初入文壇)

應(yīng)助: 0 (幼兒園)
金幣: 44.6
帖子: 26
在線: 2.2小時(shí)
蟲號(hào): 20042637
注冊(cè): 2019-12-06
專業(yè): 自動(dòng)化

引用回帖:

5樓: Originally posted by 天天進(jìn)步啊 at 2020-04-18 17:14:42
dir(utils)試試...

您好，使用dir(utils)后看到utils的內(nèi)置屬性里有_get_np_data,_get_ckpt_dir等，但是沒有g(shù)et_train_data，但是utils.py里面是有def get_train_dataset(data_processor, dataset, batch_size):
  """Creates the training data tensors."""
  x_train = _get_np_data(data_processor, dataset, split='train')
  # Create the TF dataset.
  dataset = tf.data.Dataset.from_tensor_slices(x_train)的，此時(shí)還是報(bào)一樣的錯(cuò)誤應(yīng)該要怎么辦呢？謝謝您的幫助

贊一下

回復(fù)此樓

6樓2020-04-20 23:09:45

已閱回復(fù)此樓關(guān)注TA 給TA發(fā)消息送TA紅花 TA的回帖

HZSte1204

新蟲 (初入文壇)

應(yīng)助: 0 (幼兒園)
金幣: 44.6
帖子: 26
在線: 2.2小時(shí)
蟲號(hào): 20042637
注冊(cè): 2019-12-06
專業(yè): 自動(dòng)化

引用回帖:

6樓: Originally posted by HZSte1204 at 2020-04-20 23:09:45
您好，使用dir(utils)后看到utils的內(nèi)置屬性里有_get_np_data,_get_ckpt_dir等，但是沒有g(shù)et_train_data，但是utils.py里面是有def get_train_dataset(data_processor, dataset, batch_size):
"&q ...

已解決

發(fā)自小木蟲Android客戶端

回復(fù)此樓

7樓2020-04-22 15:46:16

已閱回復(fù)此樓關(guān)注TA 給TA發(fā)消息送TA紅花 TA的回帖

相關(guān)版塊跳轉(zhuǎn) 我要訂閱樓主 HZSte1204 的主題更新

返回列表

最具人氣熱帖推薦 [查看全部]		作者	回/看	最后發(fā)表

[考研] 一志愿南大化學(xué)339分求調(diào)劑，四六級(jí)已過，有比賽，有文章 +3	Gallantzhou 2026-03-07	3/150	2026-03-08 07:54 by Iveryant
[考研] 301求調(diào)劑 +5	一二LV 2026-03-07	5/250	2026-03-07 22:20 by 18137688336
[考研] 考研一志愿長安大學(xué)材料與化工309分請(qǐng)求調(diào)劑 +4	dtdxzxx 2026-03-06	6/300	2026-03-07 22:03 by 星空星月
[考研] 一志愿中國石油大學(xué)（華東）本科齊魯工業(yè)大學(xué) 求調(diào)劑 +3	snw石 2026-03-07	3/150	2026-03-07 20:01 by houyaoxu
[考研] 化工284求調(diào)劑 +6	小黑想變白 2026-03-07	6/300	2026-03-07 19:05 by houyaoxu
[考研] 材料調(diào)劑 +10	ounce. 2026-03-04	12/600	2026-03-07 09:14 by Mornach1988
[考研] 一志愿211，0860總分286食品工程專業(yè)求調(diào)劑 +6	林林Winnie 2026-03-05	6/300	2026-03-06 20:06 by 我想上研究生.
[考研] 哈爾濱理工大學(xué)2026年研究生調(diào)劑，材料科學(xué)與化學(xué)工程學(xué)院研究生調(diào)劑 +3	xinliu866 2026-03-06	3/150	2026-03-06 19:42 by 祁東原神
[考研] 282求調(diào)劑 +7	夕～日 2026-03-05	8/400	2026-03-05 21:31 by zzpnuli111
[考研] 274求調(diào)劑 +9	一個(gè)學(xué)習(xí)者 2026-03-04	9/450	2026-03-05 20:56 by 黑衣饅頭人
[考研] 274環(huán)境工程求調(diào)劑 +6	扶柳盈江 2026-03-05	6/300	2026-03-05 13:16 by 夢(mèng)天888
[考研] 304分材料專碩求調(diào)劑 +11	qiuzhigril 2026-03-03	14/700	2026-03-05 09:30 by vfdbghn
[考研] 一志愿中科大080500總分324求調(diào)劑 +3	jorna 2026-03-03	6/300	2026-03-04 16:20 by 花開富貴幸福人?/a>
[考研] 085600求調(diào)劑 +4	LRZZZZZZ 2026-03-02	6/300	2026-03-04 09:11 by 無際的草原
[考研] 化工專碩調(diào)劑 +4	利好利好. 2026-03-03	7/350	2026-03-03 21:30 by L135790
[考研] 267求調(diào)劑 +6	釣魚佬as 2026-03-02	6/300	2026-03-03 13:59 by 13589
[考研] 284求調(diào)劑 +6	天下熯 2026-03-02	6/300	2026-03-03 13:46 by Iveryant
[考研] 26考研報(bào)考西工大材料308分求調(diào)劑 +4	weizhong123 2026-03-01	5/250	2026-03-03 12:22 by weizhong123
[考研] 化學(xué)，材料，環(huán)境類求調(diào)劑 +7	考研版棒棒 2026-03-02	7/350	2026-03-02 19:56 by hypershenger
[考研] 328求調(diào)劑 +3	aaadim 2026-03-01	5/250	2026-03-01 17:29 by njzyff