无法识别图像文件 <_io.BytesIO object at 0x000001E6CF13A108>
cannot identify image file <_io.BytesIO object at 0x000001E6CF13A108>
所以我的 validation_dataset 显然收到“无法识别图像文件 <_io.BytesIO 对象在 0x7fd2278943b0>”的错误。
我对此很陌生，有点迷茫。有什么明显的地方我做错了吗？
感谢任何帮助，谢谢大家。
model.fit() 给出相同的错误
train_datagen = image.ImageDataGenerator(rescale = 1./255, shear_range= 0.2, zoom_range = 0.2, horizontal_flip = True)
test_datagen = image.ImageDataGenerator(rescale = 1./255)
training_set = train_datagen.flow_from_directory('dataset/train', target_size= (224,224), batch_size = 32, class_mode = 'binary')
test_set = test_datagen.flow_from_directory('dataset/test', target_size= (224,224), batch_size = 32, class_mode = 'binary')
hist = model.fit_generator(
training_set,
validation_data=test_set,
epochs=5,
steps_per_epoch=10,
validation_steps=8
)
{---------------------------------------- ------------------------------
UnidentifiedImageError Traceback（最近调用最后）
~\AppData\Local\Temp\ipykernel_1107649645995.py 中
4个时期= 5，
5 steps_per_epoch=10,
----> 6 validation_steps=8
7 )
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
322 'in a future version' if date is None else ('after %s' % date),
323 instructions)
--> 324 return func(*args, **kwargs)
325 return tf_decorator.make_decorator(
326 func, new_func, 'deprecated',
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\training.py in
fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1827 use_multiprocessing=use_multiprocessing,
1828 shuffle=shuffle,
-> 1829 initial_epoch=initial_epoch)
1830
1831 @deprecation.deprecated(
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
106 def _method_wrapper(self, *args, **kwargs):
107 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
--> 108 return method(self, *args, **kwargs)
109
110 # Running inside `run_distribute_coordinator` already.
~\anaconda3\envs\tf\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)
1061 use_multiprocessing=use_multiprocessing,
1062 model=self,
-> 1063 steps_per_execution=self._steps_per_execution)
1064
1065 # Container that configures and calls `tf.keras.Callback`s.
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in __init__(self, x, y, sample_weight, batch_size, steps_per_epoch, initial_epoch, epochs, shuffle, class_weight, max_queue_size, workers, use_multiprocessing, model, steps_per_execution)
1115 use_multiprocessing=use_multiprocessing,
1116 distribution_strategy=ds_context.get_strategy(),
-> 1117 model=model)
1118
1119 strategy = ds_context.get_strategy()
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in __init__(self, x, y, sample_weights, shuffle, workers, use_multiprocessing, max_queue_size, model, **kwargs)
914 max_queue_size=max_queue_size,
915 model=model,
--> 916 **kwargs)
917
918 @staticmethod
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in __init__(self, x, y, sample_weights, workers, use_multiprocessing, max_queue_size, model, **kwargs)
784 # Since we have to know the dtype of the python generator when we build the
785 # dataset, we have to look at a batch to infer the structure.
--> 786 peek, x = self._peek_and_restore(x)
787 peek = self._standardize_batch(peek)
788 peek = _process_tensorlike(peek)
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in _peek_and_restore(x)
918 @staticmethod
919 def _peek_and_restore(x):
--> 920 return x[0], x
921
922 def _handle_multiprocessing(self, x, workers, use_multiprocessing,
~\anaconda3\envs\tf\lib\site-packages\keras_preprocessing\image\iterator.py in __getitem__(self, idx)
63 index_array = self.index_array[self.batch_size * idx:
64 self.batch_size * (idx + 1)]
---> 65 return self._get_batches_of_transformed_samples(index_array)
66
67 def __len__(self):
~\anaconda3\envs\tf\lib\site-packages\keras_preprocessing\image\iterator.py in _get_batches_of_transformed_samples(self, index_array)
228 color_mode=self.color_mode,
229 target_size=self.target_size,
--> 230 interpolation=self.interpolation)
231 x = img_to_array(img, data_format=self.data_format)
232 # Pillow images should be closed after `load_img`,
~\anaconda3\envs\tf\lib\site-packages\keras_preprocessing\image\utils.py in load_img(path, grayscale, color_mode, target_size, interpolation)
112 'The use of `load_img` requires PIL.')
113 with open(path, 'rb') as f:
--> 114 img = pil_image.open(io.BytesIO(f.read()))
115 if color_mode == 'grayscale':
116 # if image is not already an 8-bit, 16-bit or 32-bit grayscale image
~\anaconda3\envs\tf\lib\site-packages\PIL\Image.py in open(fp, mode, formats)
3007 warnings.warn(message)
3008 raise UnidentifiedImageError(
-> 3009 "cannot identify image file %r" % (filename if filename else fp)
3010 )
3011
UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x000001E6CF13A108>}
使用以下代码在预处理后找到有问题的图像，并从数据集中删除这些图像
import PIL
from pathlib import Path
from PIL import UnidentifiedImageError
path = Path("INSERT PATH HERE").rglob("*.jpeg")
for img_p in path:
try:
img = PIL.Image.open(img_p)
except PIL.UnidentifiedImageError:
print(img_p)
以上代码将列出错误的图像。让我们知道问题是否仍然存在。谢谢！
所以我的 validation_dataset 显然收到“无法识别图像文件 <_io.BytesIO 对象在 0x7fd2278943b0>”的错误。
我对此很陌生，有点迷茫。有什么明显的地方我做错了吗？
感谢任何帮助，谢谢大家。 model.fit() 给出相同的错误
train_datagen = image.ImageDataGenerator(rescale = 1./255, shear_range= 0.2, zoom_range = 0.2, horizontal_flip = True)
test_datagen = image.ImageDataGenerator(rescale = 1./255)
training_set = train_datagen.flow_from_directory('dataset/train', target_size= (224,224), batch_size = 32, class_mode = 'binary')
test_set = test_datagen.flow_from_directory('dataset/test', target_size= (224,224), batch_size = 32, class_mode = 'binary')
hist = model.fit_generator(
training_set,
validation_data=test_set,
epochs=5,
steps_per_epoch=10,
validation_steps=8
)
{---------------------------------------- ------------------------------ UnidentifiedImageError Traceback（最近调用最后） ~\AppData\Local\Temp\ipykernel_1107649645995.py 中 4个时期= 5， 5 steps_per_epoch=10, ----> 6 validation_steps=8 7 )
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
322 'in a future version' if date is None else ('after %s' % date),
323 instructions)
--> 324 return func(*args, **kwargs)
325 return tf_decorator.make_decorator(
326 func, new_func, 'deprecated',
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\training.py in
fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1827 use_multiprocessing=use_multiprocessing,
1828 shuffle=shuffle,
-> 1829 initial_epoch=initial_epoch)
1830
1831 @deprecation.deprecated(
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
106 def _method_wrapper(self, *args, **kwargs):
107 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
--> 108 return method(self, *args, **kwargs)
109
110 # Running inside `run_distribute_coordinator` already.
~\anaconda3\envs\tf\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)
1061 use_multiprocessing=use_multiprocessing,
1062 model=self,
-> 1063 steps_per_execution=self._steps_per_execution)
1064
1065 # Container that configures and calls `tf.keras.Callback`s.
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in __init__(self, x, y, sample_weight, batch_size, steps_per_epoch, initial_epoch, epochs, shuffle, class_weight, max_queue_size, workers, use_multiprocessing, model, steps_per_execution)
1115 use_multiprocessing=use_multiprocessing,
1116 distribution_strategy=ds_context.get_strategy(),
-> 1117 model=model)
1118
1119 strategy = ds_context.get_strategy()
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in __init__(self, x, y, sample_weights, shuffle, workers, use_multiprocessing, max_queue_size, model, **kwargs)
914 max_queue_size=max_queue_size,
915 model=model,
--> 916 **kwargs)
917
918 @staticmethod
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in __init__(self, x, y, sample_weights, workers, use_multiprocessing, max_queue_size, model, **kwargs)
784 # Since we have to know the dtype of the python generator when we build the
785 # dataset, we have to look at a batch to infer the structure.
--> 786 peek, x = self._peek_and_restore(x)
787 peek = self._standardize_batch(peek)
788 peek = _process_tensorlike(peek)
~\anaconda3\envs\tf\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in _peek_and_restore(x)
918 @staticmethod
919 def _peek_and_restore(x):
--> 920 return x[0], x
921
922 def _handle_multiprocessing(self, x, workers, use_multiprocessing,
~\anaconda3\envs\tf\lib\site-packages\keras_preprocessing\image\iterator.py in __getitem__(self, idx)
63 index_array = self.index_array[self.batch_size * idx:
64 self.batch_size * (idx + 1)]
---> 65 return self._get_batches_of_transformed_samples(index_array)
66
67 def __len__(self):
~\anaconda3\envs\tf\lib\site-packages\keras_preprocessing\image\iterator.py in _get_batches_of_transformed_samples(self, index_array)
228 color_mode=self.color_mode,
229 target_size=self.target_size,
--> 230 interpolation=self.interpolation)
231 x = img_to_array(img, data_format=self.data_format)
232 # Pillow images should be closed after `load_img`,
~\anaconda3\envs\tf\lib\site-packages\keras_preprocessing\image\utils.py in load_img(path, grayscale, color_mode, target_size, interpolation)
112 'The use of `load_img` requires PIL.')
113 with open(path, 'rb') as f:
--> 114 img = pil_image.open(io.BytesIO(f.read()))
115 if color_mode == 'grayscale':
116 # if image is not already an 8-bit, 16-bit or 32-bit grayscale image
~\anaconda3\envs\tf\lib\site-packages\PIL\Image.py in open(fp, mode, formats)
3007 warnings.warn(message)
3008 raise UnidentifiedImageError(
-> 3009 "cannot identify image file %r" % (filename if filename else fp)
3010 )
3011
UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x000001E6CF13A108>}
使用以下代码在预处理后找到有问题的图像，并从数据集中删除这些图像
import PIL
from pathlib import Path
from PIL import UnidentifiedImageError
path = Path("INSERT PATH HERE").rglob("*.jpeg")
for img_p in path:
try:
img = PIL.Image.open(img_p)
except PIL.UnidentifiedImageError:
print(img_p)
以上代码将列出错误的图像。让我们知道问题是否仍然存在。谢谢！