我正在尝试使用来自Kaggle的IAM手写数据集和我正在使用的教科书中的一些示例代码来构建一个简单的模型，但是当我尝试拟合模型时却不断出现错误。
错误显示ValueError: Layer sequential_2 expects 1 inputs, but it received 2 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None, None, None) dtype=float32>, <tf.Tensor 'IteratorGetNext:1' shape=(None, None) dtype=float32>]
完整的源代码：
from __future__ import division
import numpy as np
import os
import glob
import tensorflow as tf
from random import *
from PIL import Image
from keras.utils import to_categorical
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import pandas as pd
import matplotlib.image as mpimg
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Lambda, ELU, Activation, BatchNormalization
from keras.layers.convolutional import Convolution2D, Cropping2D, ZeroPadding2D, MaxPooling2D
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import SGD, Adam, RMSprop
d = {}
from subprocess import check_output
with open('./forms_for_parsing.txt') as f:
for line in f:
key = line.split(' ')[0]
writer = line.split(' ')[1]
d[key] = writer
print(len(d.keys()))
tmp = []
target_list = []
path_to_files = os.path.join('./input/data_subset/data_subset', '*')
for filename in sorted(glob.glob(path_to_files)):
# print(filename)
tmp.append(filename)
image_name = filename.split('/')[-1]
file, ext = os.path.splitext(image_name)
parts = file.split('-')
p = parts[0].split('\\')
form = p[1] + '-' + parts[1]
for key in d:
if key == form:
target_list.append(str(d[form]))
# print(d)
# print(parts[0])
# p = parts[0].split('\\')
# print(p[1])
# print(form)
img_files = np.asarray(tmp)
img_targets = np.asarray(target_list)
print(img_files.shape)
print(img_targets.shape)
for filename in img_files[:20]:
img=mpimg.imread(filename)
plt.figure(figsize=(10,10))
plt.imshow(img, cmap ='gray')
encoder = LabelEncoder()
encoder.fit(img_targets)
encoded_Y = encoder.transform(img_targets)
print(img_files[:5], img_targets[:5], encoded_Y[:5])
train_files, rem_files, train_targets, rem_targets = train_test_split(
img_files, encoded_Y, train_size=0.66, random_state=52, shuffle= True)
validation_files, test_files, validation_targets, test_targets = train_test_split(
rem_files, rem_targets, train_size=0.5, random_state=22, shuffle=True)
print(train_files.shape, validation_files.shape, test_files.shape)
print(train_targets.shape, validation_targets.shape, test_targets.shape)
batch_size = 16 # 8
num_classes = 50
# Start with train generator shared in the class and add image augmentations
def generate_data(samples, target_files, batch_size=batch_size, factor = 0.1 ):
num_samples = len(samples)
from sklearn.utils import shuffle
while 1: # Loop forever so the generator never terminates
for offset in range(0, num_samples, batch_size):
batch_samples = samples[offset:offset+batch_size]
batch_targets = target_files[offset:offset+batch_size]
images = []
targets = []
for i in range(len(batch_samples)):
batch_sample = batch_samples[i]
batch_target = batch_targets[i]
im = Image.open(batch_sample)
cur_width = im.size[0]
cur_height = im.size[1]
# print(cur_width, cur_height)
height_fac = 113 / cur_height
new_width = int(cur_width * height_fac)
size = new_width, 113
imresize = im.resize((size), Image.ANTIALIAS) # Resize so height = 113 while keeping aspect ratio
now_width = imresize.size[0]
now_height = imresize.size[1]
# Generate crops of size 113x113 from this resized image and keep random 10% of crops
avail_x_points = list(range(0, now_width - 113 ))# total x start points are from 0 to width -113
# Pick random x%
pick_num = int(len(avail_x_points)*factor)
# Now pick
random_startx = sample(avail_x_points, pick_num)
for start in random_startx:
imcrop = imresize.crop((start, 0, start+113, 113))
images.append(np.asarray(imcrop))
targets.append(batch_target)
# trim image to only see section with road
X_train = np.array(images)
y_train = np.array(targets)
#reshape X_train for feeding in later
X_train = X_train.reshape(X_train.shape[0], 113, 113, 1)
#convert to float and normalize
X_train = X_train.astype('float32')
X_train /= 255
#One hot encode y
y_train = to_categorical(y_train, num_classes)
yield shuffle(X_train, y_train)
train_generator = generate_data(train_files, train_targets, batch_size=batch_size, factor = 0.3)
validation_generator = generate_data(validation_files, validation_targets, batch_size=batch_size, factor = 0.3)
test_generator = generate_data(test_files, test_targets, batch_size=batch_size, factor = 0.1)
def resize_image(image):
return tf.image.resize(image,[56,56])
# Function to resize image to 64x64
row, col, ch = 113, 113, 1
model = Sequential()
model.add(ZeroPadding2D((1, 1), input_shape=(row, col, ch)))
# Resise data within the neural network
model.add(Lambda(resize_image)) #resize images to allow for easy computation
# CNN model - Building the model suggested in paper
model.add(Convolution2D(filters= 32, kernel_size =(5,5), strides= (2,2), padding='same', name='conv1')) #96
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2), name='pool1'))
model.add(Convolution2D(filters= 64, kernel_size =(3,3), strides= (1,1), padding='same', name='conv2')) #256
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2), name='pool2'))
model.add(Convolution2D(filters= 128, kernel_size =(3,3), strides= (1,1), padding='same', name='conv3')) #256
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2), name='pool3'))
model.add(Flatten())
model.add(Dropout(0.5))
model.add(Dense(512, name='dense1')) #1024
# model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(256, name='dense2')) #1024
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes,name='output'))
model.add(Activation('softmax')) #softmax since output is within 50 classes
model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
model.summary()
nb_epoch = 8
samples_per_epoch = 3268
nb_val_samples = 842
# #save every model using Keras checkpoint
from keras.callbacks import ModelCheckpoint
#filepath="check-{epoch:02d}-{val_loss:.4f}.hdf5"
filepath="low_loss.hdf5"
checkpoint = ModelCheckpoint(filepath= filepath, verbose=1, save_best_only=False)
callbacks_list = [checkpoint]
# #Model fit generator
history_object = model.fit_generator(train_generator, steps_per_epoch = (samples_per_epoch/batch_size),
validation_data=validation_generator,
validation_steps=nb_val_samples, epochs=nb_epoch, verbose=1, callbacks=callbacks_list)
这是我得到的错误：
ValueError Traceback (most recent call last)
<ipython-input-79-99c01bc062d8> in <module>
12
13 # #Model fit generator
---> 14 history_object = model.fit_generator(train_generator, steps_per_epoch = (samples_per_epoch/batch_size),
15 validation_data=validation_generator,
16 validation_steps=nb_val_samples, epochs=nb_epoch, verbose=1, callbacks=callbacks_list)
~\anaconda3\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\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)
1813 """
1814 _keras_api_gauge.get_cell('fit_generator').set(True)
-> 1815 return self.fit(
1816 generator,
1817 steps_per_epoch=steps_per_epoch,
~\anaconda3\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\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)
1096 batch_size=batch_size):
1097 callbacks.on_train_batch_begin(step)
-> 1098 tmp_logs = train_function(iterator)
1099 if data_handler.should_sync:
1100 context.async_wait()
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
778 else:
779 compiler = "nonXla"
--> 780 result = self._call(*args, **kwds)
781
782 new_tracing_count = self._get_tracing_count()
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
812 # In this case we have not created variables on the first call. So we can
813 # run the first trace but we should fail if variables are created.
--> 814 results = self._stateful_fn(*args, **kwds)
815 if self._created_variables:
816 raise ValueError("Creating variables on a non-first call to a function"
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
2826 """Calls a graph function specialized to the inputs."""
2827 with self._lock:
-> 2828 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
2829 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
2830
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
3208 and self.input_signature is None
3209 and call_context_key in self._function_cache.missed):
-> 3210 return self._define_function_with_shape_relaxation(args, kwargs)
3211
3212 self._function_cache.missed.add(call_context_key)
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _define_function_with_shape_relaxation(self, args, kwargs)
3139 expand_composites=True)
3140
-> 3141 graph_function = self._create_graph_function(
3142 args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
3143 self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3063 arg_names = base_arg_names + missing_arg_names
3064 graph_function = ConcreteFunction(
-> 3065 func_graph_module.func_graph_from_py_func(
3066 self._name,
3067 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)
984 _, original_func = tf_decorator.unwrap(python_func)
985
--> 986 func_outputs = python_func(*func_args, **func_kwargs)
987
988 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
598 # __wrapped__ allows AutoGraph to swap in a converted function. We give
599 # the function a weak reference to itself to avoid a reference cycle.
--> 600 return weak_wrapped_fn().__wrapped__(*args, **kwds)
601 weak_wrapped_fn = weakref.ref(wrapped_fn)
602
~\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
971 except Exception as e: # pylint:disable=broad-except
972 if hasattr(e, "ag_error_metadata"):
--> 973 raise e.ag_error_metadata.to_exception(e)
974 else:
975 raise
ValueError: in user code:
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function *
return step_function(self, iterator)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step **
outputs = model.train_step(data)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:747 train_step
y_pred = self(x, training=True)
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:975 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs,
C:\Users\subha\anaconda3\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:155 assert_input_compatibility
raise ValueError('Layer ' + layer_name + ' expects ' +
ValueError: Layer sequential_2 expects 1 inputs, but it received 2 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None, None, None) dtype=float32>, <tf.Tensor 'IteratorGetNext:1' shape=(None, None) dtype=float32>]
我听不懂错误信息，所以请有人帮我！
谢谢你