使用在 32x32 字母图像上训练的模型预测整个文档 ocr 文本
Predict an entire document ocr text using a model trained on 32x32 alphabet images
所以我使用从 here
下载的字母表数据集训练了用于 OCR 的张量流模型
创建 Xtrain、Xtest 和 Ytrain、Ytest：文件夹包含每个字母的文件夹，其中包含 15k 个 32x32 六幅图像。
import os
from PIL import Image
from numpy import asarray
folders = os.listdir(path)
train_max = 100
test_max = 10
Xtrain = []
Ytrain = []
Xtest = []
Ytest = []
for folder in folders:
folder_opened = path + folder + '/'
count = 0
for chars in os.listdir(folder_opened):
count += 1
if count <= train_max:
image = Image.open(folder_opened + chars)
data = asarray(image)
Xtrain.append(data)
Ytrain.append(folder)
elif count > train_max and count <= train_max + test_max:
image = Image.open(folder_opened + chars)
data = asarray(image)
Xtest.append(data)
Ytest.append(folder)
else:
break
我的训练代码：
import tensorflow as tf
Xtrain = tf.keras.utils.normalize(Xtrain, axis = 1)
Xtest = tf.keras.utils.normalize(Xtest, axis = 1)
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(30, activation=tf.nn.softmax))
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'],
)
model.fit(Xtrain, factorize(Ytrain)[0], epochs=40, validation_data = (Xtest, factorize(Ytest)[0]))
该模型在预测包含大小为 32x32 的单个字母表的图像时非常有效。
但对于实际应用，我需要使用此模型从文档中提取整个文本（例如：PAN 卡、身份证、护照等。）
我都试过了:
我尝试使用 pillow 读取图像并将其转换为 numpy 数组，然后在其上使用 model.predict。
image_adhar = Image.open(path_2 + 'adhar1.jpeg')
image_adhar = asarray(image_adhar)
model.predict([image_adhar])
这样做时，出现此错误
WARNING:tensorflow:Layers in a Sequential model should only have a single input tensor, but we receive a <class 'tuple'> input: (<tf.Tensor 'IteratorGetNext:0' shape=(None, 500, 3) dtype=uint8>,)
Consider rewriting this model with the Functional API.
WARNING:tensorflow:Model was constructed with shape (None, 32, 32) for input KerasTensor(type_spec=TensorSpec(shape=(None, 32, 32), dtype=tf.float32, name='flatten_30_input'), name='flatten_30_input', description="created by layer 'flatten_30_input'"), but it was called on an input with incompatible shape (None, 500, 3).
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-165-bba8716b47d4> in <module>
----> 1 model.predict([image_adhar])
~\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
1725 for step in data_handler.steps():
1726 callbacks.on_predict_batch_begin(step)
-> 1727 tmp_batch_outputs = self.predict_function(iterator)
1728 if data_handler.should_sync:
1729 context.async_wait()
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
887
888 with OptionalXlaContext(self._jit_compile):
--> 889 result = self._call(*args, **kwds)
890
891 new_tracing_count = self.experimental_get_tracing_count()
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
931 # This is the first call of __call__, so we have to initialize.
932 initializers = []
--> 933 self._initialize(args, kwds, add_initializers_to=initializers)
934 finally:
935 # 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)
761 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
762 self._concrete_stateful_fn = (
--> 763 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
764 *args, **kwds))
765
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
3048 args, kwargs = None, None
3049 with self._lock:
-> 3050 graph_function, _ = self._maybe_define_function(args, kwargs)
3051 return graph_function
3052
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
3442
3443 self._function_cache.missed.add(call_context_key)
-> 3444 graph_function = self._create_graph_function(args, kwargs)
3445 self._function_cache.primary[cache_key] = graph_function
3446
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3277 arg_names = base_arg_names + missing_arg_names
3278 graph_function = ConcreteFunction(
-> 3279 func_graph_module.func_graph_from_py_func(
3280 self._name,
3281 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)
997 _, original_func = tf_decorator.unwrap(python_func)
998
--> 999 func_outputs = python_func(*func_args, **func_kwargs)
1000
1001 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
670 # the function a weak reference to itself to avoid a reference cycle.
671 with OptionalXlaContext(compile_with_xla):
--> 672 out = weak_wrapped_fn().__wrapped__(*args, **kwds)
673 return out
674
~\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
984 except Exception as e: # pylint:disable=broad-except
985 if hasattr(e, "ag_error_metadata"):
--> 986 raise e.ag_error_metadata.to_exception(e)
987 else:
988 raise
ValueError: in user code:
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:1569 predict_function *
return step_function(self, iterator)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:1559 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1285 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2833 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3608 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:1552 run_step **
outputs = model.predict_step(data)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:1525 predict_step
return self(x, training=False)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:1030 __call__
outputs = call_fn(inputs, *args, **kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\sequential.py:380 call
return super(Sequential, self).call(inputs, training=training, mask=mask)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\functional.py:420 call
return self._run_internal_graph(
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\functional.py:556 _run_internal_graph
outputs = node.layer(*args, **kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:1013 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:251 assert_input_compatibility
raise ValueError(
ValueError: Input 0 of layer dense_94 is incompatible with the layer: expected axis -1 of input shape to have value 1024 but received input with shape (None, 1500)
请原谅，我是 keras 和 tensorflow 的新手。
我知道这个错误与训练文件的形状和我传递的图像的形状有关 (adhar1.jpeg)。它们不是相同的形状。 （32x32 和 500x281）但我不知道如何修改以接受我的 adhar1.jpeg 图片
由于您使用 32x32 图像训练模型，因此需要为模型提供相同尺寸的输入图像。
第1步：从磁盘加载输入图像，将其转换为灰度图，并对其进行模糊以减少噪声
第二步：进行边缘检测，在边缘图中找到轮廓，并将得到的轮廓从左到右排序
第 3 步：循环遍历轮廓，计算轮廓的边界框并过滤掉太小和太大的框。
第四步：提取字符并对其进行阈值处理，使字符在黑色背景上显示为白色（前景），然后抓取阈值图像的宽度和高度
第 5 步：调整图像大小并根据需要应用填充
第 6 步：运行 找到的所有字符的模型
所以我使用从 here
下载的字母表数据集训练了用于 OCR 的张量流模型创建 Xtrain、Xtest 和 Ytrain、Ytest：文件夹包含每个字母的文件夹，其中包含 15k 个 32x32 六幅图像。
import os
from PIL import Image
from numpy import asarray
folders = os.listdir(path)
train_max = 100
test_max = 10
Xtrain = []
Ytrain = []
Xtest = []
Ytest = []
for folder in folders:
folder_opened = path + folder + '/'
count = 0
for chars in os.listdir(folder_opened):
count += 1
if count <= train_max:
image = Image.open(folder_opened + chars)
data = asarray(image)
Xtrain.append(data)
Ytrain.append(folder)
elif count > train_max and count <= train_max + test_max:
image = Image.open(folder_opened + chars)
data = asarray(image)
Xtest.append(data)
Ytest.append(folder)
else:
break
我的训练代码：
import tensorflow as tf
Xtrain = tf.keras.utils.normalize(Xtrain, axis = 1)
Xtest = tf.keras.utils.normalize(Xtest, axis = 1)
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(30, activation=tf.nn.softmax))
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'],
)
model.fit(Xtrain, factorize(Ytrain)[0], epochs=40, validation_data = (Xtest, factorize(Ytest)[0]))
该模型在预测包含大小为 32x32 的单个字母表的图像时非常有效。
但对于实际应用，我需要使用此模型从文档中提取整个文本（例如：PAN 卡、身份证、护照等。）
我都试过了:
我尝试使用 pillow 读取图像并将其转换为 numpy 数组，然后在其上使用 model.predict。
image_adhar = Image.open(path_2 + 'adhar1.jpeg')
image_adhar = asarray(image_adhar)
model.predict([image_adhar])
这样做时，出现此错误
WARNING:tensorflow:Layers in a Sequential model should only have a single input tensor, but we receive a <class 'tuple'> input: (<tf.Tensor 'IteratorGetNext:0' shape=(None, 500, 3) dtype=uint8>,)
Consider rewriting this model with the Functional API.
WARNING:tensorflow:Model was constructed with shape (None, 32, 32) for input KerasTensor(type_spec=TensorSpec(shape=(None, 32, 32), dtype=tf.float32, name='flatten_30_input'), name='flatten_30_input', description="created by layer 'flatten_30_input'"), but it was called on an input with incompatible shape (None, 500, 3).
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-165-bba8716b47d4> in <module>
----> 1 model.predict([image_adhar])
~\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
1725 for step in data_handler.steps():
1726 callbacks.on_predict_batch_begin(step)
-> 1727 tmp_batch_outputs = self.predict_function(iterator)
1728 if data_handler.should_sync:
1729 context.async_wait()
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
887
888 with OptionalXlaContext(self._jit_compile):
--> 889 result = self._call(*args, **kwds)
890
891 new_tracing_count = self.experimental_get_tracing_count()
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
931 # This is the first call of __call__, so we have to initialize.
932 initializers = []
--> 933 self._initialize(args, kwds, add_initializers_to=initializers)
934 finally:
935 # 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)
761 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
762 self._concrete_stateful_fn = (
--> 763 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
764 *args, **kwds))
765
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
3048 args, kwargs = None, None
3049 with self._lock:
-> 3050 graph_function, _ = self._maybe_define_function(args, kwargs)
3051 return graph_function
3052
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
3442
3443 self._function_cache.missed.add(call_context_key)
-> 3444 graph_function = self._create_graph_function(args, kwargs)
3445 self._function_cache.primary[cache_key] = graph_function
3446
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3277 arg_names = base_arg_names + missing_arg_names
3278 graph_function = ConcreteFunction(
-> 3279 func_graph_module.func_graph_from_py_func(
3280 self._name,
3281 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)
997 _, original_func = tf_decorator.unwrap(python_func)
998
--> 999 func_outputs = python_func(*func_args, **func_kwargs)
1000
1001 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
670 # the function a weak reference to itself to avoid a reference cycle.
671 with OptionalXlaContext(compile_with_xla):
--> 672 out = weak_wrapped_fn().__wrapped__(*args, **kwds)
673 return out
674
~\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
984 except Exception as e: # pylint:disable=broad-except
985 if hasattr(e, "ag_error_metadata"):
--> 986 raise e.ag_error_metadata.to_exception(e)
987 else:
988 raise
ValueError: in user code:
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:1569 predict_function *
return step_function(self, iterator)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:1559 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1285 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2833 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3608 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:1552 run_step **
outputs = model.predict_step(data)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:1525 predict_step
return self(x, training=False)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:1030 __call__
outputs = call_fn(inputs, *args, **kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\sequential.py:380 call
return super(Sequential, self).call(inputs, training=training, mask=mask)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\functional.py:420 call
return self._run_internal_graph(
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\functional.py:556 _run_internal_graph
outputs = node.layer(*args, **kwargs)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:1013 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
C:\Users\faris\anaconda3\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:251 assert_input_compatibility
raise ValueError(
ValueError: Input 0 of layer dense_94 is incompatible with the layer: expected axis -1 of input shape to have value 1024 but received input with shape (None, 1500)
请原谅，我是 keras 和 tensorflow 的新手。
我知道这个错误与训练文件的形状和我传递的图像的形状有关 (adhar1.jpeg)。它们不是相同的形状。 （32x32 和 500x281）但我不知道如何修改以接受我的 adhar1.jpeg 图片
由于您使用 32x32 图像训练模型，因此需要为模型提供相同尺寸的输入图像。
第1步：从磁盘加载输入图像，将其转换为灰度图，并对其进行模糊以减少噪声
第二步：进行边缘检测，在边缘图中找到轮廓，并将得到的轮廓从左到右排序
第 3 步：循环遍历轮廓，计算轮廓的边界框并过滤掉太小和太大的框。
第四步：提取字符并对其进行阈值处理，使字符在黑色背景上显示为白色（前景），然后抓取阈值图像的宽度和高度
第 5 步：调整图像大小并根据需要应用填充
第 6 步：运行 找到的所有字符的模型