33,000원
다른 수강생들이 자주 물어보는 질문이 궁금하신가요?
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
지원오류
8분12초에 코드짜신 부분을 보면, train_validation_split = tfds.Split.TRAIN.subsplit([6, 4])에서 'Split' object has no attribute 'subsplit'과 같은 오류가 발생하고, 이를 조사해보니 subsplit을 더이상 지원하지 않는다고 나와있어서, 이 문제를 해결하려면 어떠한 코드로 교체해야할까요?
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
강의자료가 어디있나요?
강의자료를 못찾겠습니다. creapple.com에 들어가봐도, 샘플코드랑, 모델 정확도99% 높이기만 보이네요 강의시 사용했던 ppt나 pdf 자료는 없나요?
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
RNN&BERT 코드 에러 질문입니다!
안녕하세요! 항상 잘 듣고 있습니다. RNN 관련 영화평 분류 강의에서 코드 에러가 발생해 질문하게 되었습니다. 문제가 된 코드는 아래와 같습니다. 분명 강의에서 알려 주신 대로 입력했는데 RUN해보니 두 번째 코드와 같은 에러가 뜨네요... 구글링해봐도 해결 방법을 찾을 수가 없어 글을 올립니다. 감사합니다! history = model.fit(train_dataset, epochs = 10, validation_data = test_dataset, validation_steps=30) Epoch 1/10 WARNING:tensorflow:Model was constructed with shape (None, None) for input KerasTensor(type_spec=TensorSpec(shape=(None, None), dtype=tf.float32, name='embedding_1_input'), name='embedding_1_input', description="created by layer 'embedding_1_input'"), but it was called on an input with incompatible shape (None, None, None, None, None). WARNING:tensorflow:Model was constructed with shape (None, None) for input KerasTensor(type_spec=TensorSpec(shape=(None, None), dtype=tf.float32, name='embedding_1_input'), name='embedding_1_input', description="created by layer 'embedding_1_input'"), but it was called on an input with incompatible shape (None, None, None, None, None). --------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-40-79f235ece0ed> in <module> ----> 1 history = model.fit(train_dataset, epochs = 10, 2 validation_data = test_dataset, 3 validation_steps=30) ~\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing) 1098 _r=1): 1099 callbacks.on_train_batch_begin(step) -> 1100 tmp_logs = self.train_function(iterator) 1101 if data_handler.should_sync: 1102 context.async_wait() ~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds) 826 tracing_count = self.experimental_get_tracing_count() 827 with trace.Trace(self._name) as tm: --> 828 result = self._call(*args, **kwds) 829 compiler = "xla" if self._experimental_compile else "nonXla" 830 new_tracing_count = self.experimental_get_tracing_count() ~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds) 869 # This is the first call of __call__, so we have to initialize. 870 initializers = [] --> 871 self._initialize(args, kwds, add_initializers_to=initializers) 872 finally: 873 # At this point we know that the initialization is complete (or less ~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to) 723 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph) 724 self._concrete_stateful_fn = ( --> 725 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access 726 *args, **kwds)) 727 ~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs) 2967 args, kwargs = None, None 2968 with self._lock: -> 2969 graph_function, _ = self._maybe_define_function(args, kwargs) 2970 return graph_function 2971 ~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs) 3359 3360 self._function_cache.missed.add(call_context_key) -> 3361 graph_function = self._create_graph_function(args, kwargs) 3362 self._function_cache.primary[cache_key] = graph_function 3363 ~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes) 3194 arg_names = base_arg_names + missing_arg_names 3195 graph_function = ConcreteFunction( -> 3196 func_graph_module.func_graph_from_py_func( 3197 self._name, 3198 self._python_function, ~\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes) 988 _, original_func = tf_decorator.unwrap(python_func) 989 --> 990 func_outputs = python_func(*func_args, **func_kwargs) 991 992 # invariant: `func_outputs` contains only Tensors, CompositeTensors, ~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds) 632 xla_context.Exit() 633 else: --> 634 out = weak_wrapped_fn().__wrapped__(*args, **kwds) 635 return out 636 ~\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs) 975 except Exception as e: # pylint:disable=broad-except 976 if hasattr(e, "ag_error_metadata"): --> 977 raise e.ag_error_metadata.to_exception(e) 978 else: 979 raise ValueError: in user code: C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:805 train_function * return step_function(self, iterator) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:795 step_function ** outputs = model.distribute_strategy.run(run_step, args=(data,)) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1259 run return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2730 call_for_each_replica return self._call_for_each_replica(fn, args, kwargs) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3417 _call_for_each_replica return fn(*args, **kwargs) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:788 run_step ** outputs = model.train_step(data) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:754 train_step y_pred = self(x, training=True) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:1012 __call__ outputs = call_fn(inputs, *args, **kwargs) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\sequential.py:375 call return super(Sequential, self).call(inputs, training=training, mask=mask) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\functional.py:424 call return self._run_internal_graph( C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\functional.py:560 _run_internal_graph outputs = node.layer(*args, **kwargs) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\layers\wrappers.py:539 __call__ return super(Bidirectional, self).__call__(inputs, **kwargs) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:998 __call__ input_spec.assert_input_compatibility(self.input_spec, inputs, self.name) C:\Users\User\anaconda3\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:219 assert_input_compatibility raise ValueError('Input ' + str(input_index) + ' of layer ' + ValueError: Input 0 of layer bidirectional_1 is incompatible with the layer: expected ndim=3, found ndim=6. Full shape received: (None, None, None, None, None, 64)
- 해결됨[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
네이버 영화평 dataset 을 tfds.load 로 올린후 encoder method 까지 사용하려면?
안녕하세요 선생님^^ dataset, info = tfds.load('imdb_reviews/subwords8k', with_info=True, as_supervised=True)encoder = info.features['text'].encoder위와같이 imdb dataset 을 load 하였는데만약에 https://github.com/e9t/nsmc 와 같은 네이버 영화평 dataset 을 올리려면 어떻게 올릴 수 있을까요?제가 아래와 같이 올려 보았는데 아래는 info 란 인자가 load 되지않아서 encoder 가 설정되지 않아서 계속 error 가 발생하네요. train_dataset = pd.read_csv('data/nsmc/ratings_train.txt', delimiter='\t', keep_default_na=False) test_dataset = pd.read_csv('data/nsmc/ratings_test.txt', delimiter='\t', keep_default_na=False)https://github.com/e9t/nsmc 와 같은 네이버 영화평 과 tfds.load 로 googling 해봐도 실예를 찾을 수 가 없었습니다.답변주시면 나머지 수행하는데 많은 도움이 될 것 같습니다.꾸벅!!
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
코드를 그대로 돌렸는데 애로가 나오는 이유가 알고 싶습니다
안녕하십니까 선생님 코드를 그대로 붙여서 실행했는데 다음과 같은 애로 사항이 발생했습니다 tensorflow도 2.3이고 keras도 설치 되어있는데 어떤 제반 사항이 잘못되었는지 알려주시면 감사드리겠습니다. ImportError Traceback (most recent call last) ~\anaconda3\lib\site-packages\keras\__init__.py in <module> 2 try: ----> 3 from tensorflow.keras.layers.experimental.preprocessing import RandomRotation 4 except ImportError: ~\anaconda3\lib\site-packages\tensorflow\__init__.py in <module> 40 ---> 41 from tensorflow.python.tools import module_util as _module_util 42 from tensorflow.python.util.lazy_loader import LazyLoader as _LazyLoader ~\anaconda3\lib\site-packages\tensorflow\python\__init__.py in <module> 45 from tensorflow.python import data ---> 46 from tensorflow.python import distribute 47 from tensorflow.python import keras ~\anaconda3\lib\site-packages\tensorflow\python\distribute\__init__.py in <module> 27 from tensorflow.python.distribute import one_device_strategy ---> 28 from tensorflow.python.distribute.experimental import collective_all_reduce_strategy 29 from tensorflow.python.distribute.experimental import parameter_server_strategy ~\anaconda3\lib\site-packages\tensorflow\python\distribute\experimental\__init__.py in <module> 24 from tensorflow.python.distribute import parameter_server_strategy ---> 25 from tensorflow.python.distribute import tpu_strategy 26 # pylint: enable=unused-import ~\anaconda3\lib\site-packages\tensorflow\python\distribute\tpu_strategy.py in <module> 42 from tensorflow.python.tpu import device_assignment as device_assignment_lib ---> 43 from tensorflow.python.tpu import tpu 44 from tensorflow.python.tpu import tpu_strategy_util ~\anaconda3\lib\site-packages\tensorflow\python\tpu\tpu.py in <module> 27 from tensorflow.python.compat import compat as api_compat ---> 28 from tensorflow.python.compiler.xla import xla 29 from tensorflow.python.framework import device as pydev ~\anaconda3\lib\site-packages\tensorflow\python\compiler\xla\__init__.py in <module> 22 from tensorflow.python.compiler.xla import jit ---> 23 from tensorflow.python.compiler.xla import xla 24 # pylint: enable=unused-import ~\anaconda3\lib\site-packages\tensorflow\python\compiler\xla\xla.py in <module> 24 ---> 25 from tensorflow.compiler.jit.ops import xla_ops 26 from tensorflow.compiler.jit.ops import xla_ops_grad # pylint: disable=unused-import ~\anaconda3\lib\site-packages\tensorflow\compiler\jit\ops\xla_ops.py in <module> 7 ----> 8 from tensorflow.python import pywrap_tfe as pywrap_tfe 9 from tensorflow.python.eager import context as _context ~\anaconda3\lib\site-packages\tensorflow\python\pywrap_tfe.py in <module> 28 from tensorflow.python import pywrap_tensorflow ---> 29 from tensorflow.python._pywrap_tfe import * ImportError: DLL load failed: 지정된 프로시저를 찾을 수 없습니다. During handling of the above exception, another exception occurred: ImportError Traceback (most recent call last) <ipython-input-1-210029f2541c> in <module> 1 from __future__ import print_function ----> 2 import keras 3 from keras.datasets import mnist 4 from keras.models import Sequential 5 from keras.layers import Dense, Dropout, Flatten ~\anaconda3\lib\site-packages\keras\__init__.py in <module> 4 except ImportError: 5 raise ImportError( ----> 6 'Keras requires TensorFlow 2.2 or higher. ' 7 'Install TensorFlow via `pip install tensorflow`') 8 ImportError: Keras requires TensorFlow 2.2 or higher. Install TensorFlow via `pip install tensorflow`
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
accuracy가 훨씬 낮게 나오는 이유는 무엇인가요??
안녕하세요. 선생님. MNIST_CNN 코드를 제 PC를 통해서 돌렸을 때에 강의에서 봤던 것 처럼 0.99 accuracy 가 나오지 않고 0.84정도 밖에 나오지 않았습니다. test_loss 가 굉장이 높게 나오는 편인데, 왜 이런 현상이 나타나는 건지 궁금합니다... Test loss: 0.7218891382217407 Test accuracy: 0.8402000069618225
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
예제로 쓰인 코드가 어디있는지 모르겠습니다...
예제로 쓰인 코드가 어디있는지 모르겠습니다... 링크로라도 부탁드려요
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
ImportError : DLL load failed
tensorflow 2.2 가 현재 최신버젼인데요. 아래와 같은 에러가 계속 나옵니다. ImportError : DLL load failed 혹시 추가적인 설치가 필요한가요..?
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
deprecated 가 의심되는 코드 하나 더 여쭙겠습니다
예제 22 IMDB_RNN.py 에서 train_dataset = train_dataset.shuffle(BUFFER_SIZE) train_dataset = train_dataset.padded_batch(BATCH_SIZE, train_dataset.output_shapes)) test_dataset = test_dataset.padded_batch(BATCH_SIZE, test_dataset.output_shapes) 이 부분에 train_dataset.output_shapes 와 test_dataset.output_shapes 가 에러입니다 에러 메세지는 다음과 같습니다'ShuffleDataset' object has no attribute 'output_shapes'이부분... 구글 colab 에서는 약간의 경고 메세지와 함께 실행은 되는데주피터 노트북에서는 위와 같은 에러가 납니다죄송하지만 이거 하나더 부탁드리겠습니다
- 해결됨[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
IMDB data 소스 코드 에러 사항
train_validation_split = tfds.Split.TRAIN.subsplit([6, 4])이 문장에서 'Split' object has no attribute 'subsplit'이 같은 에러가 나옵니다
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
자료와 예제코드
교육 교제와 예제코드는 어디있나요 . . 여기서는 찾을 수가 없네요
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
LSTM관련하여 질문드릴 수 있을까요....?
Keras를 활용하여 LSTM 학습을 하는중입력값을 판단하기 어려운 부분이 있어 질문드립니다.model = Sequential() model.add(LSTM(128, batch_input_shape=(1, 4, 1), stateful=True)) model.add(Dense(12, activation='softmax')) 이처럼 구현할때 LSTM(128 부분의 128과, Dense(12 의 12가 무슨 의미인지 알 수 있을까요?
- 미해결[텐서플로2] 파이썬 딥러닝 완전정복 - GAN, BERT, RNN, CNN 최신기법
다음을 실행하면 에러가 납니다.
from __future__ import absolute_import, division, print_function, unicode_literals import numpy as np import tensorflow as tf import tensorflow_hub as hub import tensorflow_datasets as tfds train_validation_split = tfds.Split.TRAIN.subsplit([6, 4]) (train_data, validation_data), test_data = tfds.load( name="imdb_reviews", split=(train_validation_split, tfds.Split.TEST), as_supervised=True) print("Version: ", tf.__version__) print("Eager mode: ", tf.executing_eagerly()) print("Hub version: ", hub.__version__) print("GPU is", "available" if tf.config.experimental.list_physical_devices("GPU") else "NOT AVAILABLE") Version: 2.0.0 Eager mode: True Hub version: 0.7.0 GPU is NOT AVAILABLE 다음과 같은 에러가 납니다. --------------------------------------------------------------------------- AssertionError Traceback (most recent call last) <ipython-input-6-55c5f5ff433f> in <module> 6 name="imdb_reviews", 7 split=(train_validation_split, tfds.Split.TEST), ----> 8 as_supervised=True) ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\api_utils.py in disallow_positional_args_dec(fn, instance, args, kwargs) 50 _check_no_positional(fn, args, ismethod, allowed=allowed) 51 _check_required(fn, kwargs) ---> 52 return fn(*args, **kwargs) 53 54 return disallow_positional_args_dec(wrapped) # pylint: disable=no-value-for-parameter ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\registered.py in load(name, split, data_dir, batch_size, in_memory, shuffle_files, download, as_supervised, decoders, read_config, with_info, builder_kwargs, download_and_prepare_kwargs, as_dataset_kwargs, try_gcs) 316 as_dataset_kwargs.setdefault("read_config", read_config) 317 --> 318 ds = dbuilder.as_dataset(**as_dataset_kwargs) 319 if with_info: 320 return ds, dbuilder.info ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\api_utils.py in disallow_positional_args_dec(fn, instance, args, kwargs) 50 _check_no_positional(fn, args, ismethod, allowed=allowed) 51 _check_required(fn, kwargs) ---> 52 return fn(*args, **kwargs) 53 54 return disallow_positional_args_dec(wrapped) # pylint: disable=no-value-for-parameter ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\dataset_builder.py in as_dataset(self, split, batch_size, shuffle_files, decoders, read_config, as_supervised, in_memory) 474 in_memory=in_memory, 475 ) --> 476 datasets = utils.map_nested(build_single_dataset, split, map_tuple=True) 477 return datasets 478 ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in map_nested(function, data_struct, dict_only, map_tuple) 151 if isinstance(data_struct, tuple(types)): 152 mapped = [map_nested(function, v, dict_only, map_tuple) --> 153 for v in data_struct] 154 if isinstance(data_struct, list): 155 return mapped ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in <listcomp>(.0) 151 if isinstance(data_struct, tuple(types)): 152 mapped = [map_nested(function, v, dict_only, map_tuple) --> 153 for v in data_struct] 154 if isinstance(data_struct, list): 155 return mapped ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in map_nested(function, data_struct, dict_only, map_tuple) 151 if isinstance(data_struct, tuple(types)): 152 mapped = [map_nested(function, v, dict_only, map_tuple) --> 153 for v in data_struct] 154 if isinstance(data_struct, list): 155 return mapped ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in <listcomp>(.0) 151 if isinstance(data_struct, tuple(types)): 152 mapped = [map_nested(function, v, dict_only, map_tuple) --> 153 for v in data_struct] 154 if isinstance(data_struct, list): 155 return mapped ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in map_nested(function, data_struct, dict_only, map_tuple) 157 return tuple(mapped) 158 # Singleton --> 159 return function(data_struct) 160 161 ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\dataset_builder.py in _build_single_dataset(self, split, shuffle_files, batch_size, decoders, read_config, as_supervised, in_memory) 542 shuffle_files=shuffle_files, 543 decoders=decoders, --> 544 read_config=read_config, 545 ) 546 ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\dataset_builder.py in _as_dataset(self, split, decoders, read_config, shuffle_files) 899 split_infos=self.info.splits.values(), 900 read_config=read_config, --> 901 shuffle_files=shuffle_files, 902 ) 903 else: ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\tfrecords_reader.py in read(self, name, instructions, split_infos, read_config, shuffle_files) 244 name2len=name2len, name2shard_lengths=name2shard_lengths, 245 shuffle_files=shuffle_files) --> 246 datasets = utils.map_nested(read_instruction, instructions, map_tuple=True) 247 return datasets 248 ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in map_nested(function, data_struct, dict_only, map_tuple) 157 return tuple(mapped) 158 # Singleton --> 159 return function(data_struct) 160 161 ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\tfrecords_reader.py in _read_single_instruction(instruction, parse_fn, read_config, name, path, name2len, name2shard_lengths, shuffle_files) 138 """ 139 if not isinstance(instruction, ReadInstruction): --> 140 instruction = ReadInstruction.from_spec(instruction) 141 absolute_instructions = instruction.to_absolute(name2len) 142 files = list(itertools.chain.from_iterable([ ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\tfrecords_reader.py in from_spec(cls, spec) 436 if not subs: 437 raise AssertionError('No instructions could be built out of %s' % spec) --> 438 instruction = _str_to_relative_instruction(subs[0]) 439 return sum([_str_to_relative_instruction(sub) for sub in subs[1:]], 440 instruction) ~\Anaconda3\envs\jhsong37\lib\site-packages\tensorflow_datasets\core\tfrecords_reader.py in _str_to_relative_instruction(spec) 277 res = _SUB_SPEC_RE.match(spec) 278 if not res: --> 279 raise AssertionError('Unrecognized instruction format: %s' % spec) 280 unit = '%' if res.group('from_pct') or res.group('to_pct') else 'abs' 281 return ReadInstruction( AssertionError: Unrecognized instruction format: NamedSplit('train')(tfds.percent[0:60])